Keywords: Deep Learning in Robotics and Automation
Abstract: Recognized as one of the world’s leading experts in artificial intelligence and a pioneer in deep learning, Yoshua Bengio studied in Montreal, earned his Ph.D. in computer science from McGill University in 1991, and did post-doctoral studies at MIT.

Since 1993, he has been a professor in the Department of Computer Science and Operations Research at the Université de Montréal, and he holds the Canada Research Chair in Statistical Learning Algorithms. In addition, he is Scientific Director of IVADO and Mila, the Quebec Artificial Intelligence Institute, the world’s largest deep learning academic research group.

An Officer of the Order of Canada, he is also a Fellow of the Royal Society of Canada, the recipient of the Marie-Victorin Prize in 2017, and was named Radio-Canada’s Scientist of the Year for 2017. In 2018, he was awarded the 50th anniversary medal of Quebec’s Ministry of International Relations and La Francophonie.

Yoshua Bengio is one of the world’s most cited computer scientists, thanks to his three books and more than 500 publications. His h-index stands at 130, with more than 144,000 Google Scholar citations. His ambition is to understand the principles that lead to intelligence through learning, as well as promote the development of artificial intelligence for the benefit of all.

Keywords: Learning and Adaptive Systems, Legged Robots, Deep Learning in Robotics and Automation
Abstract: In this paper, we propose a trajectory-based reinforcement learning method named deep latent policy gradient (DLPG) for learning locomotion skills. We define the policy function as a probability distribution over trajectories and train the policy using a deep latent variable model to achieve sample efficient skill learning. We first evaluate the sample efficiency of DLPG compared to the state-of-the-art reinforcement learning methods in simulated environments. Then, we apply the proposed method to a four-legged walking robot named Snapbot to learn three basic locomotion skills of turn left, go straight, and turn right. We demonstrate that, by properly designing two reward functions for curriculum learning, Snapbot successfully learns the desired locomotion skills with moderate sample complexity.

Keywords: Learning and Adaptive Systems, Reactive and Sensor-Based Planning, Motion and Path Planning
Abstract: The ability to navigate uncertain environments from a start to a goal location is a necessity in many applications. While there are many reactive algorithms for online re-planning, there has not been much investigation in leveraging past executions of the same navigation task to improve future executions. In this work, we first formalize this problem by introducing the Learned Reactive Planning Problem (LRPP). Second, we propose a method to capture these past executions and from that determine a motion policy to handle obstacles that the robot has seen before. Third, we show from our experiments that using this policy can significantly reduce the execution cost over just using reactive algorithms.

Keywords: Learning and Adaptive Systems, Deep Learning in Robotics and Automation, AI-Based Methods
Abstract: Model-free Reinforcement Learning (RL) offers an attractive approach to learn control policies for high-dimensional systems, but its relatively poor sample complexity often necessitates training in simulated environments. Even in simulation, goal-directed tasks whose natural reward function is sparse remain intractable for state-of-the-art model-free algorithms for continuous control. The bottleneck in these tasks is the prohibitive amount of exploration required to obtain a learning signal from the initial state of the system. In this work, we leverage physical priors in the form of an approximate system dynamics model to design a curriculum for a model-free policy optimization algorithm. Our Backward Reachability Curriculum (BaRC) begins policy training from states that require a small number of actions to accomplish the task, and expands the initial state distribution backwards in a dynamically-consistent manner once the policy optimization algorithm demonstrates sufficient performance. Its curriculum strategy is physically intuitive, easy-to-tune, and allows incorporating physical priors to accelerate training without hindering the performance, flexibility, and applicability of the model-free RL algorithm. We evaluate our approach on two representative dynamic robotic learning problems and find substantial performance improvement relative to previous curriculum generation techniques and naive exploration strategies.

Keywords: Learning and Adaptive Systems, Learning from Demonstration, Robot Safety
Abstract: Learning the dynamical system (DS) model from data that preserves dynamical system properties is an important problem in many robot learning applications. Typically, the joint data coming from cyber-physical systems, such as robots have some underlying DS properties associated with it, e.g., convergence, invariance to a set, etc. In this paper, a model learning method is developed such that the trajectories of the DS are invariant in a given compact set. Such invariant DS models can be used to generate trajectories of the robot that will always remain in a prescribed set. In order to achieve invariance to a set, Barrier certificates are employed. The DS is approximated using Extreme Learning Machine (ELM), and a parameter learning problem subject to Barrier certificates enforced at all the points in the prescribed set is solved. To solve an infinite constraint problem for enforcing Barrier Certificates at every point in a given compact set, a modified constraint is developed that is sufficient to hold the Barrier certificates in the entire set. An active sampling strategy is formulated to minimize the number of constraints in learning. Simulation results of ELM learning with and without Barrier certificates are presented which show the invariance property being preserved in the ELM learning when learning procedure involves Barrier constraints. The method is validated using experiments conducted on a robot arm recreating invariant trajectories inside a prescribed set.

Keywords: Learning and Adaptive Systems, Motion and Path Planning
Abstract: To enable autonomous robot navigation among unknown dynamic obstacles, a real-time adaptive motion planner (RAMP) plans the robot motion online based on sensing the environment as the robot moves with sensors mounted on the robot. However, the sensed environmental data from the robot’s local view is usually incomplete due to occlusions from obstacles and limited sensing range.

This paper incorporates learning about the environment into the RAMP framework by leveraging the Hilbert Maps framework to generate a probabilistic model of occupancy of the unknown dynamic environment based on past observations. Utilizing this probabilistic model enables RAMP to reason about trajectory fitness when sensing information is partial and incomplete. This allows the RAMP robot to take advantage of what it has experienced from being in the dynamic environment before to inform its subsequent executions even though the dynamic environment changes in unknown ways. The effectiveness of incorporating such learned probabilistic data into RAMP is shown in both simulation and real experiments.

Keywords: Learning and Adaptive Systems, Deep Learning in Robotics and Automation
Abstract: Reinforcement Learning methods are capable of solving complex problems, but resulting policies might perform poorly in environments that are even slightly different. In robotics especially, training and deployment conditions often vary and data collection is expensive, making retraining undesirable. Simulation training allows for feasible training times, but on the other hand suffer from a reality-gap when applied in real-world settings. This raises the need of efficient adaptation of policies acting in new environments.

We consider the problem of transferring knowledge within a family of similar Markov decision processes. We assume that Q-functions are generated by some low-dimensional latent variable. Given such a Q-function, we can find a master policy that can adapt given different values of this latent variable. Our method learns both the generative mapping and an approximate posterior of the latent variables, enabling identification of policies for new tasks by searching only in the latent space, rather than the space of all policies. The low-dimensional space, and master policy found by our method enables policies to quickly adapt to new environments. We demonstrate the method on both a pendulum swing-up task in simulation, and for simulation-to-real transfer on a pushing task.

Keywords: Object Detection, Segmentation and Categorization, Autonomous Vehicle Navigation, Human-Centered Automation
Abstract: Following improvements in deep neural networks, state-of-the-art networks have been proposed for human recognition using point clouds captured by LiDAR. However, the performance of these networks strongly depends on the training data. An issue with collecting training data is labeling. Labeling by humans is necessary to obtain the ground truth label; however, labeling requires huge costs. Therefore, we propose an automatic labeled data generation pipeline, for which we can change any parameters or data generation environments. Our approach uses a human model named Dhaiba and a background of Miraikan and consequently generated realistic artificial data. We present 500k+ data generated by the proposed pipeline. This paper also describes the specification of the pipeline and data details with evaluations of various approaches.

Keywords: Object Detection, Segmentation and Categorization, Visual Learning, Human-Centered Automation
Abstract: Video object segmentation is an essential task in robot manipulation to facilitate grasping and learning affordances. Incremental learning is important for robotics in unstructured environments. Inspired by the children learning process, human robot interaction (HRI) can be utilized to teach robots about the world guided by humans similar to how children learn from a parent or a teacher. A human teacher can show potential objects of interest to the robot, which is able to self adapt to the teaching signal without providing manual segmentation labels. We propose a novel teacher-student learning paradigm to teach robots about their surrounding environment. A two-stream motion and appearance "teacher" network provides pseudo-labels to adapt an appearance "student" network. The student network is able to segment the newly learned objects in other scenes, whether they are static or in motion. We also introduce a carefully designed dataset that serves the proposed HRI setup, denoted as (I)nteractive (V)ideo (O)bject (S)egmentation. Our IVOS dataset contains teaching videos of different objects, and manipulation tasks. Our proposed adaptation method outperforms the state-of-the-art on DAVIS and FBMS with 6.8% and 1.2% in F-measure respectively. It improves over the baseline on IVOS dataset with 46.1% and 25.9% in mIoU.

Keywords: Object Detection, Segmentation and Categorization, Perception for Grasping and Manipulation, Force and Tactile Sensing
Abstract: Distributed tactile sensors on multi-fingered hands can provide high-dimensional information for grasping objects, but it is not clear how to optimally process such abundant tactile information. The current paper explores the possibility of using a morphology-specific convolutional neural network (MS-CNN). uSkin tactile sensors are mounted on an Allegro Hand, which provides 720 force measurements (15 patches of uSkin modules with 16 triaxial force sensors each) in addition to 16 joint angle measurements. Consecutive layers in the CNN get input from parts of one finger segment, one finger, and the whole hand. Since the sensors give 3D (x, y, z) vector tactile information, inputs with 3 channels (x, y and z) are used in the first layer, based on the idea of such inputs for RGB images from cameras. Overall, the layers are combined, resulting in the building of a tactile map based on the relative position of the tactile sensors on the hand. Seven different combination variations were evaluated, and an over-95% object recognition rate with 20 objects was achieved, even though only one random time instance from a repeated squeezing motion of an object in an unknown pose within the hand was used as input.

Keywords: Object Detection, Segmentation and Categorization, Optimization and Optimal Control, Recognition
Abstract: Markov Random Fields (MRFs) are a popular model for several pattern recognition and reconstruction problems in robotics and computer vision. Inference in MRFs is intractable in general and related work resorts to approximation algorithms. Among those techniques, semidefinite programming (SDP) relaxations have been shown to provide accurate estimates while scaling poorly with the problem size and being typically slow for practical applications. Our first contribution is to design a dual ascent method to solve standard SDP relaxations that takes advantage of the geometric structure of the problem to speed up computation. This technique, named Dual Ascent Riemannian Staircase (DARS), is able to solve large problem instances in seconds. Our second contribution is to develop a second and faster approach. The backbone of this second approach is a novel SDP relaxation combined with a fast and scalable solver based on smooth Riemannian optimization. We show that this approach, named Fast Unconstrained SEmidefinite Solver (FUSES), can solve large problems in milliseconds. Contrarily to local MRF solvers, e.g., loopy belief propagation, our approaches do not require an initial guess. Moreover, we leverage recent results from optimization theory to provide per-instance sub-optimality guarantees. We demonstrate the proposed approaches in multi-class image segmentation problems. Extensive experimental evidence shows that (i) FUSES and DARS produce near-optimal solutions, attaining a

Keywords: Object Detection, Segmentation and Categorization, Range Sensing, Probability and Statistical Methods
Abstract: Whether it is object detection, model reconstruction, laser odometry, or point cloud registration: Plane extraction is a vital component of many robotic systems. In this paper, we propose a strictly probabilistic method to detect finite planes in organized 3-D laser range scans. An agglomerative hierarchical clustering technique, our algorithm builds planes from bottom up, always extending a plane by the point that decreases the measurement likelihood of the scan the least. In contrast to most related methods, which rely on heuristics like orthogonal point-to-plane distance, we leverage the ray path information to compute the measurement likelihood. We evaluate our approach not only on the popular SegComp benchmark, but also provide a challenging synthetic dataset that overcomes SegComp's deficiencies. Both our implementation and the suggested dataset are available at https://github.com/acschaefer/ppe.

Keywords: Object Detection, Segmentation and Categorization, Localization, Visual Tracking
Abstract: We consider the problem of matching a pair of point sets in the Euclidean d-dimensional space REAL^d, where clusters from the first point set are arbitrarily translated with additional noise, resulting in the second point set. The goal is to minimize the sum of squared distances between the paired sets over every translation and possible matching among the n! permutations. The result can be used as a seeding clustering for existing algorithms, e.g. to compute the optimal rotation on each cluster. This is a fundamental problem for tracking systems (e.g. OptiTrack or Vicon) where the user registers k objects (rigid bodies) by attaching a set of markers to each object. Based on the position of these markers in real-time, the system estimates the position of the moving objects by simultaneously clustering, matching and transforming the n observed markers to the k objects. Similarly, an autonomous robot equipped with a camera may estimate its position by tracking n visual features from k recognized objects.

We suggest the first provable algorithm for solving this point matching problem. Unlike common heuristics, it yields a constant factor approximation for the emph{global optimum} in expected dn^{k+2}log n) time. We validate our theoretical results with experimental results using low-cost (<30) ``toy" quadcopters that are safe and lawful for indoor navigation due to their < 200 grams weight. Comparisons to existing algorithms and commercial system are

Keywords: Biologically-Inspired Robots, Motion Control, AI-Based Methods
Abstract: In this paper, we design novel liquid time-constant recurrent neural networks for robotic control, inspired by the brain of the nematode, C. elegans. In the worm's nervous system, neurons communicate through nonlinear time-varying synaptic links established amongst them by their particular wiring structure. This property enables neurons to express liquid time-constants dynamics and therefore allows the network to originate complex behaviors with a small number of neurons. We identify neuron-pair communication motifs as design operators and use them to configure compact neuronal network structures to govern sequential robotic tasks. The networks are systematically designed to map the environmental observations to motor actions, by their hierarchical topology from sensory neurons, through recurrently-wired interneurons, to motor neurons. The networks are then parametrized in a supervised-learning scheme by a search-based algorithm. We demonstrate that obtained networks realize interpretable dynamics. We evaluate their performance in controlling mobile and arm robots, and compare their attributes to other artificial neural network-based control agents. Finally, we experimentally show their superior resilience to environmental noise, compared to the existing machine learning-based methods.

Keywords: Biologically-Inspired Robots, Biomimetics, Aerial Systems: Mechanics and Control
Abstract: Wings of flying animals not only can generate lift and control torque but also can sense their surroundings. Such dual functions of sensing and actuation coupled in one element are particularly useful for small sized bio-inspired robotic flyers, whose weight, size, and power are under constraint. In this work, we present the first flapping-wing robot using its flapping wings for environmental perception and navigation in tight space, without the need for any visual feedback. Specifically, we introduce Purdue Hummingbird, a flapping-wing robot with 17cm wingspan and 12 grams weight, as our test platform. By interpreting the wing loading feedback and its variations, the vehicle can detect the presence of environmental changes such as grounds, walls, stairs, obstacles and wind gust. The instantaneous wing loading can be obtained through the measurements and interpretation of the current feedback by the motor that actuates the wing. The effectiveness of the proposed approach is experimentally demonstrated on several challenging flight tasks without vision: terrain following, wall following and going through a narrow corridor. To ensure flight stability, a robust controller was designed for handling unforeseen disturbances during the flight. Sensing and navigating one's environment through actuator loading is a promising method for mobile robots and it can serve as an alternative or complementary method to visual perception.

Keywords: Biologically-Inspired Robots, Tendon/Wire Mechanism, Flexible Robots
Abstract: Developments of robot arms are countless, but there has been little focus on robot surfaces for the reshaping of a habitable space—especially compliant surfaces. In this paper we introduce a novel, tendon-driven, robot surface comprised of aggregated, overlapping panels organized in a herringbone pattern. The individual 3D-printed panels and their behavior as an aggregation are inspired by the form and behavior of a pinecone. This paper presents our concept, design, and realization of this robot, and compares our prototype to simulations of four physical configurations that are formally distinct and suggestive of how the surface might be applied to habitable, physical space in response to human needs and wants. For the four configurations studied, we found a validating match between prototype and simulations. The paper concludes with a consideration of potential applications for robot surfaces like this one.

Keywords: Biologically-Inspired Robots, Biomimetics, Aerial Systems: Mechanics and Control
Abstract: Biological studies show that hummingbirds can perform extreme aerobatic maneuvers during fast escape. Given a sudden looming visual stimulus at hover, a hummingbird initiates a fast backward translation coupled with a 180-degree yaw turn, which is followed by instant posture stabilization in just under 10 wingbeats. Consider the wingbeat frequency of 40Hz, this aggressive maneuver is carried out in just 0.2 seconds. Inspired by the hummingbirds' near-maximal performance during such extreme maneuvers, we developed a flight control strategy and experimentally demonstrated that such maneuverability can be achieved by an at-scale 12-gram hummingbird robot equipped with just two actuators driving a pair of flapping wings up to 40Hz. The proposed hybrid control policy combines model-based nonlinear control with model-free reinforcement learning. We used the model-based nonlinear control for nominal flight conditions where dynamic models are relatively accurate. During extreme maneuvers when the modeling error becomes unmanageable, we use a model-free reinforcement learning policy trained and optimized in simulation to 'destabilize' the system for peak performance during maneuvering. The hybrid policy manifests a maneuver that is close to that observed in hummingbirds. Direct simulation-to-real transfer is achieved, demonstrating the hummingbird-like fast evasive maneuvers on the at-scale hummingbird robot.

Keywords: Biologically-Inspired Robots, Soft Material Robotics, Biomimetics
Abstract: Multimodal deformations of soft materials such as compression and bending are a commonplace event on soft-bodied animals (e.g., worms) and soft-bodied robots. Usually, such deformation modes are separately analyzed or constrained to decrease the degrees of freedom when one design motion of the soft-bodied robots. This paper proposes to use multiple deformation modes and presents a highly deformable crawling robot that employs both compression and bending deformations simultaneously during the locomotion. This locomotion gait is inspired by the motion analysis experiment of a biological caterpillar, i.e., crawling gait of a silkworm Bombyx mori. Based on the biological experiment we propose a compressive/bendable beam and develop a crawling robot using the proposed beam. The experimental results of the simulation and the prototype demonstrate that the combination of the multiple deformation modes can contribute to the locomotion speed increase. This also indicates that we can design an enormous variety of locomotion gaits by combining multiple deformation modes, which may increase the adaptability of soft-bodied robots for use in our living and natural environments. These results shed new light on how to design behavioral diversity of soft-bodied robots.

Keywords: Autonomous Vehicle Navigation, Biologically-Inspired Robots, SLAM
Abstract: This paper presents a novel biomimetic radar sensor for autonomous navigation. To accomplish this, we have drawn inspiration from the sensory mechanisms present in an echolocating mammal, the common big-eared bat (Micronycteris microtis). We demonstrate the correspondence in both the hardware, system model and signal processing. To validate the performance of the sensor we have developed a complementary control system based on subsumption architecture, which allows the system to autonomously navigate unknown environments. This architecture consists of separate behaviors with different levels of complexity, which are combined to produce the overall functionality of the system. We describe each behavior separately and examine their performance in real-world navigation experiments. For this purpose, the system is placed in two distinct office environments with the goal of achieving smooth and stable trajectories. Here we can observe noticeable improvements when employing high-level behaviors. Furthermore, we utilize the data collected during the navigation experiments to perform simultaneous localization and mapping, using an algorithm developed in our earlier work. These results show a substantial improvement over the odometry. We attribute this to the fact that the system traverses stable and repetitive paths, which facilitates place recognition.

Keywords: SLAM, Localization, Mapping
Abstract: We propose a novel stereo visual SLAM framework considering both accuracy and speed at the same time. The framework makes full use of the advantages of key-feature-based multiple view geometry (MVG) and direct-based formulation. At the front-end, our system performs direct formulation and constant motion model to predict a robust initial pose, reprojects local map to find 3D-2D correspondence and finally refines pose by the reprojection error minimization. This front-end process makes our system faster. At the back-end, MVG is used to estimate 3D structure. When a new keyframe is inserted, new mappoints are generated by triangulating. In order to improve the accuracy of the proposed system, bad mappoints are removed and a global map is kept by bundle adjustment. Especially, the stereo constraint is performed to optimize the map. This back-end process makes our system more accurate. Experimental evaluation on EuRoC dataset shows that the proposed algorithm can run at more than 100 frames per second on a consumer computer while achieving highly competitive accuracy.

Keywords: SLAM, Mapping, RGB-D Perception
Abstract: Dense 3D reconstructions generate globally consisent data of the environment suitable for many robot applications. Current RGB-D based reconstructions, however, only maintain the color resolution equal to the depth resolution of the used sensor. This firmly limits the precision and realism of the generated reconstructions. In this paper we present a real-time approach for creating and maintaining a surface reconstruction in as high as possible geometrical fidelity with full sensor resolution for its colorization (or surface texture). A multi-scale memory management process and a level of detail scheme enable equally detailed reconstructions to be generated at small scales, such as objects, as well as large scales, such as rooms or buildings. We showcase the benefit of this novel pipeline with a PrimeSense RGB-D camera as well as combining the depth channel of this camera with a high resolution global shutter camera. Further experiments show that our memory management approach allows us to scale up to larger domains that are not achievable with current state-of-the-art methods.

Keywords: SLAM, Localization, Visual-Based Navigation
Abstract: We present a Deep Learning based system for the twin tasks of localization and obstacle avoidance essential to any mobile robot. Our system learns from conventional geometric SLAM, and outputs, using a single camera, the topological pose of the camera in an environment, and the depth map of obstacles around it. We use a CNN to localize in a topological map, and a conditional VAE to output depth for a camera image, conditional on this topological location estimation. We demonstrate the effectiveness of our monocular localization and depth estimation system on simulated and real datasets.

Keywords: SLAM, Visual-Based Navigation, RGB-D Perception
Abstract: Simultaneous Localization and Mapping is a key requirement for many practical applications in robotics. In this work, we present RESLAM, a novel edge-based SLAM system for RGBD sensors. Due to their sparse representation, larger convergence basin and stability under illumination changes, edges are a promising alternative to feature-based or other direct approaches. We build a complete SLAM pipeline with camera pose estimation, sliding window optimization, loop closure and relocalisation capabilities that utilizes edges throughout all steps. In our system, we additionally refine the initial depth from the sensor, the camera poses and the camera intrinsics in a sliding window to increase accuracy. Further, we introduce an edge-based verification for loop closures that can also be applied for relocalisation. We evaluate RESLAM on wide variety of benchmark datasets that include difficult scenes and camera motions and also present qualitative results. We show that this novel edge-based SLAM system performs comparable to state-of-the-art methods, while running in real-time on a CPU. RESLAM is available as open-source software

Keywords: SLAM, Industrial Robots
Abstract: The SLAM problem is known to have a special property that when robot orientation is known, estimating the history of robot poses can be posed as a standard linear least squares problem. In this work, we develop a robust pose- graph SLAM framework that uses absolute orientation sensing to exploit this structural property of SLAM. Our contribution are as follows; (i) we show that absolute orientation can be estimated using local structural cues, and (ii) we develop a method to incorporate absolute orientation measurements in both the front and back-end of pose-graph SLAM. We demonstrate our method through extensive simulations and a physical real- world demonstration along with comparisons against existing state-of-the-art solvers that do not use absolute orientation.

Keywords: SLAM, Motion and Path Planning
Abstract: In this paper, we present an on-line active pose-graph simultaneous localization and mapping (SLAM) framework for robots in three-dimensional (3D) environments using graph topology and sub-maps. This framework aims to find the best trajectory for loop-closure by re-visiting old poses based on the T-optimality and D-optimality metrics of the Fisher information matrix (FIM) in pose-graph SLAM. In order to reduce computational complexity, graph topologies are introduced, including weighted node degree (T-optimality metric) and weighted tree-connectivity (D-optimality metric), to choose a candidate trajectory and several key poses. With the help of the key poses, a sampling-based path planning method and a continuous-time trajectory optimization method are combined hierarchically and applied in the whole framework. So as to further improve the real-time capability of the method, the sub-map joining method is used in the estimation and planning process for large-scale active SLAM problems. In simulations and experiments, we validate our approach by comparing against existing methods, and we demonstrate the on-line planning part using a quad-rotor unmanned aerial vehicle (UAV).

Keywords: Manipulation Planning
Abstract: In this paper we propose a new model for sequential manipulation tasks that also considers robot dynamics and time-variant environments. From this model we automatically derive constraint-based controllers and use them as steering functions in a kinodynamic manipulation planner. The resulting plan is not a trajectory, but a sequence of controllers that react on-line to disturbances. We validated our approach in simulation and on a real robot. In the experiments our approach plans and executes dual-robot manipulation tasks with on-line collision avoidance and reactions to estimates of object poses.

Keywords: Manipulation Planning, Motion and Path Planning, Service Robots
Abstract: We present an algorithm that produces a plan for relocating obstacles in order to grasp a target in clutter by a robotic manipulator without collisions. We consider configurations where objects are densely populated in a constrained and confined space. Thus, there exists no collision-free path for the manipulator without relocating obstacles. Since the problem of planning for object rearrangement has shown to be NP-hard, it is difficult to perform manipulation tasks efficiently which could frequently happen in service domains (e.g., taking out a target from a shelf or a fridge).

Our proposed planner employs a collision avoidance scheme which has been widely used in mobile robot navigation. The planner determines an obstacle to be removed quickly in real time. It also can deal with dynamic changes in the configuration (e.g., changes in object poses). Our method is shown to be complete and runs in polynomial time. Experimental results in a realistic simulated environment show that our method improves up to 31% of the execution time compared to other competitors.

Keywords: Manipulation Planning, Task Planning
Abstract: A lot of motion planning research in robotics focuses on efficient means to find trajectories between individual start and goal regions, but it remains challenging to specify and plan robotic manipulation actions which consist of multiple interdependent subtasks. The Task Constructor framework we present in this work provides a flexible and transparent way to define and plan such actions, enhancing the capabilities of the popular robotic manipulation framework MoveIt!. Subproblems are solved in isolation in black-box planning stages and a common interface is used to pass solution hypotheses between stages. The framework enables the hierarchical organization of basic stages using containers, allowing for sequential as well as parallel compositions. The flexibility of the framework is illustrated in multiple scenarios performed on various robot platforms, including bimanual ones.

Keywords: Manipulation Planning, Motion Control, Industrial Robots
Abstract: We explore the characteristics of secondary contacts when applying forces with the end-effector of a robot and address the question when these secondary contacts can increase maximum applicable end-effector forces or reduce required actuator efforts. To this end, we formalize the effect of such secondary contacts in terms of required actuator efforts and derive efficiency bounds depending on the contact characteristics and robot configuration. Our findings are confirmed by experiments with a redundant serial manipulator.

Keywords: Manipulation Planning, Kinematics, Robotics in Hazardous Fields
Abstract: This paper presents a new method of maximizing the free space for a robot operating in a constrained environment under operator supervision. The objective is to make the resulting trajectories more robust to operator commands and/or changes in the environment. To represent the volume of free space, the constrained manipulability polytopes are used. These polytopes embed the distance to obstacles, the distance to joint limits and the distance to singular configurations. The volume of the resulting Cartesian polyhedron is used in an optimization-based motion planner to create the trajectories. Additionally, we show how fast collision-free inverse kinematic solutions can be obtained by exploiting the pre-computed inequality constraints. The proposed algorithm is validated in simulation and experimentally.

Keywords: Manipulation Planning
Abstract: This paper describes a new robotic tabletop rearrangement system, and presents experimental results. The tasks involve rearranging as many as 30 to 100 blocks, sometimes packed with a density of up to 40%. The high packing factor forces the system to push several objects at a time, making accurate simulation difficult, if not impossible. Nonetheless, the system achieves goals specifying the pose of every object, with an average precision of SI{pm 1}{mm} and SI{pm 2}{degree}. The system searches through policy rollouts of simulated pushing actions, using an Iterated Local Search technique to escape local minima. In real world execution, the system executes just one action from a policy, then uses a vision system to update the estimated task state, and replans. The system accepts a fully general description of task goals, which means it can solve the singulation and separation problems addressed in prior work, but can also solve sorting problems and spell out words, among other things. The paper includes examples of several solved problems, statistical analysis of the system's behavior on different types of problems, and some discussion of limitations, insights, and future work.

Keywords: Micro/Nano Robots, Nanomanufacturing
Abstract: A manipulation technique based on optothermally generated surface bubbles is proposed in this paper. The manipulation and assembly of microstructures are completed by using bubbles. In addition, the hydrogel microstructures are also used as microrobots driven by the bubble to operate and pattern the microspheres. Considering that many materials and lasers with different wavelength have been used for generating bubbles by optothermal effects, absorptivity and transmissivity are used as indicators of selections. Besides, the size of the bubble can be controlled by the frequency and time of the laser. This technique is supposed to be applied for manipulation of cells, microparticles and microstructures.

Keywords: Micro/Nano Robots, Soft Material Robotics, Mechanism Design
Abstract: This paper presents the design, fabrication, and operation of compound micromachines powered by acoustic streaming. The machine components were directly incorporated around pillars serving as shafts without further assembly steps using a single-step in situ polymerization process controlled by a programmable projector. Two strategies were presented for harvesting acoustic energy using sharp-edged structures. The first method is based on on-board pumping of fluids and the second method involves engineering of rotors. The implementation of these strategies resulted in the construction of microscale turbines and engines that can be coupled to gear trains for adaptable transmission of mechanical power. We provide a number of further improvements that may together lead to development of compact yet powerful robotic manipulation systems inside microfluidic devices.

Keywords: Micro/Nano Robots, Automation at Micro-Nano Scales, Nanomanufacturing
Abstract: In this paper, we introduce a new class of submillimeter robot (ChevBot) for microfactory applications in dry environments, powered by a 532 nm laser beam. ChevBot is an untethered microrobot propelled by a thermal Micro Electro Mechanical (MEMS) actuator upon exposure to the laser light. Novel models for opto-thermal-mechanical energy conversion are proposed to describe the microrobot’s locomotion mechanism. First, an opto-thermal simulation model is presented which is experimentally validated with static displacement measurements with microrobots tethered to the substrate. Then, stick and slip motion of the microrobot was predicted using a dynamic extension of our simulation model, and experiments were conducted to validate this model in one dimension. Promising microrobot designs were fabricated on a silicon on insulator (SOI) wafer with 20μm device layer and a dimple was assembled at the bottom to initiate directional locomotion on a silicon substrate. Validation experiments demonstrate that exposure to laser power below 2W and repetition frequencies below 60 kHz can generate actuator displacements of a few microns, and 46 µm/s locomotion velocity.

Keywords: Micro/Nano Robots, Product Design, Development and Prototyping, Automation at Micro-Nano Scales
Abstract: Capillary Ionic Transistor (CIT) is introduced as a nanodevice which provides control of ionic transport through nanochannel by gate voltage. CIT is Ionic transistor which employs pulled capillary as nanochannel with tip diameter smaller than 100 nm. We observed that gate voltage applied to gate electrode, deposited on the outer wall of capillary, affect a conductance of nanochannel, due to change of surface charge at the solution/capillary interface. Negative gate voltage corresponds to lower conductivity and positive gate increase conductance of the channel. This effect strongly depends on the size of the channel. In general, at least one dimension of the channel has to be small enough for electrical double layer to overlap. As a demonstration of the gate control ability, we performed Si nanoparticle delivery via CIT and recorded the deliverance through resistive pulse method. Size and velocity measurement are also conducted, to showcase the versatility of CIT device.

Keywords: Micro/Nano Robots
Abstract: Untethered microrobot has been regarded as one of the most powerful tool for performing specific in vitro/vivo tasks, especially magnetic actuated microrobot owing to its biocompatible energy source. However, despite numerous design and fabrication technologies of magnetic microrobot have been developed, the improvement of magnetic actuation manner reaches the limit, which mainly relies on the specific structure design (helix) or strong gradient magnetic field to realize locomotion.

Inspired from surface cilia dependent paramecium swimming, this paper reports a new self-assembly magnetic actuation concept design for bulk biomaterial motion based on the partial asymmetrical hetero-function of magnetic chain units. Compared with existing design and fabrication of magnetic microrobot actuators, our proposed self-assembly magnetic chain unit method is succinct, economical, structure unconstrained and material unconstrained. In this work, the tanglesome bulk fiber fabrication based on flow-focusing microcapillary system is firstly introduced, which is utilized for structure unconstrained and material unconstrained actuation demonstration. Secondly, the six degrees-of-freedom (DOFs) electromagnetic coil system is proposed for presenting the magnetic actuation based on self-assembly magnetic chain units. After that, the self-assembly mechanism and magnetic control mechanism are developed to explain the fabrication and actuation procedure. Finally, the self-assembled magnetic chain

Keywords: Humanoid and Bipedal Locomotion, Kinematics, Optimization and Optimal Control
Abstract: This paper describes a stable knee-stretched walking of a humanoid by the resolved viscoelasticity control (RVC). The RVC method resolves multiple viscoelasticities in task-space, including the center of mass viscoelasticity for balancing, into joint-space viscoelasticity. Although a robust and compliant motion was achieved by the RVC method in previous studies, the conventional knee-bent posture to avoid the kinematic singularity suffered large knee joint torque. In this study, we propose an extension of the RVC capable of the kinematic singularity. We demonstrate through simulations and experiments that the RVC method considering the singularity achieves a stable and human-like walking, reducing the knee joint torque and improving the energy efficiency

Keywords: Humanoid and Bipedal Locomotion, Optimization and Optimal Control, Dynamics
Abstract: When experiencing disturbances during locomotion, human beings use several strategies to maintain balance, e.g. changing posture, modulating step frequency and location. However, when it comes to the gait generation for humanoid robots, modifying step time or body posture in real time introduces nonlinearities in the walking dynamics, thus increases the complexity of the planning. In this paper, we propose a two-layer hierarchical optimization framework to address this issue and provide the humanoids with the abilities of step time and step location adjustment, Center of Mass(CoM) height variation and angular momentum adaptation. In the first layer, times and locations of consecutive two steps are modulated online based on the current CoM state using the Linear Inverted Pendulum Model. By introducing new optimization variables to substitute the hyperbolic functions of step time, the derivatives of the objective function and feasibility constraints are analytically derived, thus reduces the computational cost. Then, taking the generated horizontal CoM trajectory, step times and step locations as inputs, CoM height and angular momentum changes are optimized by the second-layer nonlinear model predictive control. This whole procedure will be repeated until the termination condition is met. The improved recovery capability under external disturbances is validated in simulation studies.

Keywords: Humanoid and Bipedal Locomotion, Learning and Adaptive Systems, Robust/Adaptive Control of Robotic Systems
Abstract: Learning controllers for bipedal robots is a challenging problem, often requiring expert knowledge and extensive tuning of parameters that vary in different situations. Recently, deep reinforcement learning has shown promise at automatically learning controllers for complex systems in simulation. This has been followed by a push towards learning controllers that can be transferred between simulation and hardware. In this work, we explore whether policies learned in simulation can be transferred to hardware with the use of high-fidelity simulators and structured controllers. We learn a neural network policy which is a part of a more structured controller. While the neural network is learned in simulation, the rest of the controller stays fixed and can be tuned by the expert as needed. We show that using this approach can greatly speed up the rate of learning in simulation, as well as enable transfer of policies between simulation and hardware. Our results show that structured policies can indeed be learned in simulation and implemented on hardware successfully. This has several advantages, as the structure preserves the intuitive nature of the policy, and the neural network improves the performance of the hand-designed policy. In this way, we propose a way of using neural networks to improve expert designed controllers, while maintaining ease of understanding.

Keywords: Humanoid and Bipedal Locomotion, Sensor Fusion
Abstract: Contact detection is an important topic in contemporary humanoid robotic research. Up to date control and state estimation schemes readily assume that feet contact status is known in advance. In this work, we elaborate on a broader question: in which gait phase is the robot currently in? We introduce an unsupervised learning framework for gait phase estimation based solely on proprioceptive sensing, namely joint encoder, inertial measurement unit and force/torque data. Initially, a meaningful physical explanation on data acquisition is presented. Subsequently, dimensionality reduction is performed to obtain a compact low-dimensional feature representation followed by clustering into three groups, one for each gait phase. The proposed framework is qualitatively and quantitatively assessed in simulation with ground-truth data of uneven/rough terrain walking gaits and insights about the latent gait phase dynamics are drawn. Additionally, its efficacy and robustness is demonstrated when incorporated in leg odometry computation. Since our implementation is based on sensing that is commonly available on humanoids today, we release an open-source ROS/Python package to reinforce further research endeavors.

Keywords: Humanoid and Bipedal Locomotion
Abstract: We consider dynamic stair climbing with the HRP-4 humanoid robot as part of an Airbus manufacturing use-case demonstrator. We share experimental knowledge gathered so as to achieve this task, which HRP-4 had never been challenged to before. In particular, we extend walking stabilization based on linear inverted pendulum tracking by quadratic programming-based wrench distribution and a whole-body admittance controller that applies both end-effector and CoM strategies. While existing stabilizers tend to use either one or the other, our experience suggests that the combination of these two approaches improves tracking performance. We demonstrate this solution in an on-site experiment where HRP-4 climbs an industrial staircase with 18.5 cm high steps, and release our walking controller as open source software.

Keywords: Humanoid and Bipedal Locomotion, Deep Learning in Robotics and Automation, Robust/Adaptive Control of Robotic Systems
Abstract: The design of feedback controllers for bipedal robots is challenging due to the hybrid nature of its dynamics and the complexity imposed by high-dimensional bipedal models. In this paper, we present a novel approach for the design of feedback controllers using Reinforcement Learning (RL) and Hybrid Zero Dynamics (HZD). Existing RL approaches for bipedal walking are inefficient as they do not consider the underlying physics, often requires substantial training, and the resulting controller may not be applicable to real robots. HZD is a powerful tool for bipedal control with local stability guarantees of the walking limit cycles. In this paper, we propose a non traditional RL structure that embeds the HZD framework into the policy learning. More specifically, we propose to use RL to find a control policy that maps from the robot's reduced order states to a set of parameters that define the desired trajectories for the robot's joints through the virtual constraints. Then, these trajectories are tracked using an adaptive PD controller. The method results in a stable and robust control policy that is able to track variable speed within a continuous interval. Robustness of the policy is evaluated by applying external forces to the torso of the robot. The proposed RL framework is implemented and demonstrated in OpenAI Gym with the MuJoCo physics engine based on the well-known RABBIT robot model.

Keywords: Localization, Deep Learning in Robotics and Automation, Autonomous Vehicle Navigation
Abstract: Odometry techniques are key to autonomous robot navigation, since they enable self-localization in the environment. However, designing a robust odometry system is particularly challenging when camera and LiDAR are uninformative or unavailable. In this paper, we leverage recent advances in deep learning and variational inference to correct dynamical and observation models for state-space systems. The methodology trains Gaussian processes on the residual between the original model and the ground truth, and is applied on publicly available datasets for robot navigation based on two wheel encoders, a fiber optic gyro, and an Inertial Measurement Unit (IMU). We also propose to build an Extended Kalman Filter (EKF) on the learned model using wheel speed sensors and the fiber optic gyro for state propagation, and the IMU to update the estimated state. Experimental results clearly demonstrate that the (learned) corrected models and EKF are more accurate than their original counterparts.

Keywords: Localization, Autonomous Vehicle Navigation, Range Sensing
Abstract: Radar detects stable, long-range objects under variable weather and lighting conditions, making it a reliable and versatile sensor well suited for ego-motion estimation. In this work, we propose a radar-only odometry pipeline that is highly robust to radar artifacts (e.g., speckle noise and false positives) and requires only one input parameter. We demonstrate its ability to adapt across diverse settings, from urban UK to off-road Iceland, achieving a scan matching accuracy of approximately 5.20 cm and 0.0929 deg when using GPS as ground truth (compared to visual odometry's 5.77 cm and 0.1032 deg). We present algorithms for keypoint extraction and data association, framing the latter as a graph matching optimization problem, and provide an in-depth system analysis.

Keywords: Localization, Autonomous Vehicle Navigation, Sensor Fusion
Abstract: This paper presents a new methodology to quantify robot localization safety by evaluating integrity risk, a performance metric widely used in open-sky aviation applications that has been recently extended to mobile ground robots. Here, a robot is localized by feeding relative measurements to mapped landmarks into an Extended Kalman Filter while a sequence of innovations is evaluated for fault detection. The main contribution is the derivation of a sequential chi-squared integrity monitoring methodology that maintains constant computation requirements by employing a preceding time window and, at the same time, is robust against faults occurring prior to the window. Additionally, no assumptions are made on either the nature or shape of the faults because safety is evaluated under the worst possible combination of sensor faults.

Keywords: Localization, Calibration and Identification, Autonomous Vehicle Navigation
Abstract: Localization is one of the main challenges to be addressed to develop autonomous vehicles able to perform complex maneuvers on roads opened to public traffic. Having an accurate dead-reckoning system is an essential step to reach this objective. This paper presents a dead-reckoning model for car-like vehicles that performs the data fusion of complementary and redundant sensors: wheel encoders, yaw rate gyro and steering wheel measurements. In order to get an accurate dead-reckoning system with a drift reduced to the minimum, the parameters have to be well calibrated and the procedure has to be simple and efficient. We present a method able to accurately calibrate the parameters without knowing the ground truth by using a Rauch-Tung-Striebel smoothing scheme which enables to obtain state estimates as close to the ground truth as possible. The smoothed estimates are then used within a optimization process to calibrate the model parameters. The method has been tested using data recorded from an experimental vehicle on public roads. The results show a significant diminution of the dead-reckoning drift compared to a commonly used calibration method. We evaluate finally the average distance a vehicle can navigate without exteroceptive sensors by using the proposed four-wheeled dead reckoning system.

Keywords: Localization, SLAM, Performance Evaluation and Benchmarking
Abstract: Visual Place Recognition (VPR) is an important component in both computer vision and robotics applications, thanks to its ability to determine whether a place has been visited and where specifically. A major challenge in VPR is to handle changes of environmental conditions including weather, season and illumination. Most VPR methods try to improve the place recognition performance by ignoring the environmental factors, leading to decreased accuracy decreases when environmental conditions change significantly, such as day versus night. To this end, we propose an end-to-end conditional visual place recognition method. Specifically, we introduce the multi-domain feature learning method (MDFL) to capture multiple attribute-descriptions for a given place, and then use a feature detaching module to separate the environmental condition-related features from those that are not. The only label required within this feature learning pipeline is the environmental condition. Evaluation of the proposed method is conducted on the multi-season textit{NORDLAND} dataset, and the multi-weather textit{GTAV} dataset. Experimental results show that our method improves the feature robustness against variant environmental conditions.

Keywords: Localization, Visual Tracking
Abstract: Event cameras are novel bio-inspired vision sensors that output pixel-level intensity changes, called "events", instead of traditional video images. These asynchronous sensors naturally respond to motion in the scene with very low latency (microseconds) and have a very high dynamic range. These features, along with a very low power consumption, make event cameras an ideal sensor for fast robot localization and wearable applications, such as AR/VR and gaming. Considering these applications, we present a method to track the 6-DOF pose of an event camera in a known environment, which we contemplate to be described by a photometric 3D map (i.e., intensity plus depth information) built via classic dense 3D reconstruction algorithms. Our approach uses the raw events, directly, without intermediate features, within a maximum-likelihood framework to estimate the camera motion that best explains the events via a generative model. We successfully evaluate the method using both simulated and real data, and show improved results over the state of the art. We release the datasets to the public to foster reproducibility and research in this topic.

Keywords: Cellular and Modular Robots
Abstract: Reconfiguring heterogeneous modular robots in which all modules are not identical is much more time consuming than reconfiguring homogeneous ones, because ordinary heterogeneous reconfiguration is a combination of homogeneous transformation and heterogeneous permutation. While linear homogeneous transformation has been accomplished in previous research, linear heterogeneous permutation has not. This paper studies a reconfiguration algorithm for heterogeneous lattice modular robots with linear operation time cost. The algorithm is based on simultaneous tunneling and permutation, where a robot transforms its configuration via tunneling motion while permutation of each module’s position is performed simultaneously during the tunneling transformation. To achieve this, we introduce the idea of a transparent meta-module that allows modules belonging to a meta-module to pass through the spaces occupied by other meta-modules. We prove the correctness and completeness of the proposed algorithm for a 2×2×2 cubic meta-module-based connected robot structure. We also show examples of the reconfiguration simulations of heterogeneous modular robots by the proposed algorithm.

Keywords: Cellular and Modular Robots, Robotics in Construction, Swarms
Abstract: Soil stabilization is a fundamental component of nearly all construction projects, ranging from commercial construction to environmental restoration projects. Previous work in autonomous construction has generally not considered these essential stabilization and anchoring tasks. In this work we present Romu, an autonomous robot capable of building continuous linear structures by using a vibratory hammer to drive interlocking sheet piles into soil. We report on hardware parameters and their effects on pile driving performance, and demonstrate autonomous operation in both controlled and natural environments. Finally, we present simulations in which a small swarm of robots build with sheet piles in example terrains, or apply an alternate spray-based stabilizing agent, and quantify the ability of each intervention to mitigate hydraulic erosion.

Keywords: Cellular and Modular Robots, Aerial Systems: Mechanics and Control, Aerial Systems: Perception and Autonomy
Abstract: Flying modular robots have the potential to rapidly form temporary structures. In the literature, docking actions rely on external systems and indoor infrastructures for relative pose estimation. Different from the related work, we provide local estimation during the self-assembly process to avoid dependency on external systems. In this paper, we introduce ModQuad-Vi, a flying modular robot that is aimed to operate in outdoor environments. We propose a new robot design and vision-based docking method. Our design is based on a quadrotor platform with onboard computation and visual perception. Our control method is able to accurately align modules for docking actions. Additionally, we present the dynamics and a geometric controller for the aerial modular system. Experiments validate the vision-based docking method with successful results.

Keywords: Cellular and Modular Robots, Redundant Robots
Abstract: A variable geometry truss (VGT) is a modular truss-structured robot consisting of linear actuators and 3-degree-of-freedom joints. Having a sophisticated structure, the VGT can easily be damaged when it rolls and impacts the ground. This paper proposes a non-impact rolling locomotion scheme to avoid VGT damage. It is assumed that the VGT moves quasi-statically and maintains a static stability. There exists a control phase and a rolling phase during locomotion. During the control phase, the VGT can freely move its center of mass within the supporting polygon. During the rolling phase, the VGT’s center of mass is fixed at the edge of the support polygon and it tilts forward until a node touches the ground to make a new support polygon. This algorithm optimizes the velocity of the VGT’s nodes at every time step so that the center of mass follows a desired trajectory of rolling motion. A simulation verifies that the algorithm ensures that the VGT maintains its static stability, does not tumble, and accurately follows its desired trajectory.

Keywords: Mechanism Design, Kinematics, Cellular and Modular Robots
Abstract: This paper addresses the challenge of determining the optimal design of a customizable robot for a given task. We present a motion planner that not only prescribes a path, but also synthesizes the robot design to follow that path. Our approach treats design variables as part of an inverse kinematics problem to jointly optimize manipulator design parameters and trajectory. We apply our method to two distinct problems where rapid prototyping and customization are desirable: an arm prototyped for a future Mars mission, and a wearable backpack-mounted arm. We then propose a novel method to minimize the number of joints in the mechanism while maintaining its ability to reach workspace task poses. We combine these methods into a framework in which we iteratively optimize and simplify task-specialized manipulator designs.

Keywords: Medical Robots and Systems, Flexible Robots
Abstract: The use of flexible endoscope has been rising inconveniences. Steering of the distal section is not intuitive and the weight of the endoscope burdens a physical pressure on physicians who use it continuously for a long time. Also, the limited dexterity of an instrument makes therapeutic procedures more difficult, and further the unintended communications often occur during cooperation with assistants. These degrade the efficiency and thus increase the procedure time. In this paper, we propose a robotic endoscopy system (easyEndo) that can be mounted on a conventional endoscope and facilitate solo-endoscopy with two intuitive hand-held controllers. Furthermore, a robotic arm is presented that can be attached to the endoscope to assist with tissue traction. To validate the robotic endoscopy system, experiments to simulate biopsy and lesion marking were conducted with novices. The results showed that the robotic manipulations improved efficiency and reduced workload than manual manipulation. Subsequently, a prototype of the robotic arm was attached at the distal end of the endoscope, and the feasibility of tissue traction was confirmed by a simulation of pulling a rubber band.

Keywords: Surgical Robotics: Steerable Catheters/Needles, Product Design, Development and Prototyping, Tendon/Wire Mechanism
Abstract: We present a transformable catheter head structure for endoscopic catheter allowing the simultaneous use of a camera module and a large tool channel introduced through a small incision. At the site of interest, the head with a camera can be expanded from the initial straight configuration, which opens a window for advancing a tool that is located behind the camera. Two different designs were proposed and prototyped. One option has flexure joints directly fabricated at the distal end of a polymer catheter by laser micro-machining, while another design employs a hinged metal head assembled at the tip of the same type of catheter. The kinematic behavior of each head was evaluated during the head-up and tip steering motions, and compared with each other to draw a selection guideline between them. Experimental results prove the feasibility of the proposed head structure for smarter endoscopic catheters.

Keywords: Surgical Robotics: Laparoscopy, Medical Robots and Systems, Surgical Robotics: Steerable Catheters/Needles
Abstract: Snake-like robots are commonly used in Minimally Invasive Surgery as they are able to reach areas deep inside the human body. These robots have instruments that are deployed out of the robot’s head and controlled via tendons, which connect the instrument to motors at the proximal end. In most currently available systems the instruments are lacking a rolling motion of the end-effector. In this paper, we present a new instrument prototype for a snake-like robot that can perform a stable in-place rolling motion. The prototype has a diameter of 4mm, uses 13 tendons and has 6 degrees of freedom. The robot can bend and roll to high angles, and strongly improves the dexterity compared to an instrument without rolling capabilities. In the evaluation we show that the rolling-tip gripper can rotate about 165◦ and is capable of applying forces up to 6.5N.

Keywords: Medical Robots and Systems, Computer Vision for Medical Robotics, RGB-D Perception
Abstract: Laser scalpels are utilized across a variety of surgical and dermatological procedures due to their precision and non-contact nature. This paper presents a novel laser scalpel system for superficial laser therapy applications. The system integrates a RGB-D camera, a 3D triangulation sensor and a carbon dioxide (CO2) laser scalpel for computer-assisted laser surgery. To accurately ablate targets chosen from the color image, a 3D extrinsic calibration method between the RGB-D camera frame and the laser coordinate system is implemented. The accuracy of the calibration method is tested on phantoms with planar and cylindrical surfaces. Positive error and negative error, as defined as undershooting and overshooting over the target area, are reported for each test. For 60 total test cases, the root-mean-square of the positive and negative error in both planar and cylindrical phantoms is less than 1.0 mm, with a maximum absolute error less than 2.0 mm. This work demonstrates the feasibility of automated laser therapy with surgeon oversight via our sensor system.

Keywords: Medical Robots and Systems
Abstract: Peripheral intravenous catheterization (PIVC) is pervasively needed in hospitals. However, given the levels of precision and controllability needed for PIVC, this operation suffers from very low success rates. For young patients, about half of the first insertions fail. Robotic systems have great potential to effectively assist the operation and improve the success rates, which has led to the recent development of different robots to automate PIVC. These robots are equipped with various sensors and actuators, resulting in expensive, complex and grounded machines. Yet, fully automating the operation is neither needed nor desired, as current clinical preference is oriented towards keeping the practitioner involved and in control of the operation. Therefore, in this study we proposed an innovative smart hand-held robotic device, named CathBot, to enhance intra-operative control during PIVC with automatic features. It exploits an electrical bioimpedance sensor to detect the venipuncture and a crank-slider mechanism to automate the subsequent cannula advancement and needle retraction. CathBot is first tested through engineering experiments for ensuring its capability to perform the whole PIVC on a realistic baby arm phantom without human involvement. Subsequent experiments evaluate the device with naïve subjects on the same realistic scenario. The results show that CathBot can greatly improve the PIVC experience with an average 86% success rate, and a 80% first stick accuracy.

Keywords: Force and Tactile Sensing, Surgical Robotics: Laparoscopy, Medical Robots and Systems
Abstract: For more secure and delicate robotic surgery, force sensing ability is essential but it has still not used in actual robot surgery. This is because the environmental factors that occur during actual operation affect the sensor and the sensor cannot give a reliable force information. In this paper, we aim to develop reliable sensorized-forceps that can be used in practical surgical tasks by compensating environmental influences. The environmental factors affecting the sensor were analyzed. And humidity, temperature and high voltage were considered as main factors. At first, to compensate the humidity influences, the humidity sensing capability was integrated in the sensorized-forceps and humidity compensation algorithm is applied. Secondly, to eliminate the temperature-sensitive element, AC shield is applied to the signal processing board. Finally, for cutting off electric conduction, entire surface of forceps is covered by an oxide layer. To verify the proposed solutions, revised sensorized-forceps is installed in surgical robot platform and ex vivo experiments with electro-cautery task were conducted.

Keywords: Telerobotics and Teleoperation, Manipulation Planning
Abstract: Promoting a robot agent’s autonomy level, which allows it to understand the human operator’s intent and provide motion assistance to achieve it, has demonstrated great advantages to the operator’s intent in teleoperation. However, the research has been limited to the target approaching process. We advance the shared control technique one step further to deal with the more challenging object manipulation task. Appropriately manipulating an object is challenging as it requires fine motion constraints for a certain manipulation task. Although these motion constraints are critical for task success, they are subtle to observe from ambiguous human motion. The disembodiment problem and physical discrepancy between the human and robot hands bring additional uncertainty, make the object manipulation task more challenging. Moreover, there is a lack of modeling and planning techniques that can effectively combine the human motion input and robot agent’s motion input while accounting for the ambiguity of the human intent. To overcome this challenge, we built a multi-task robot grasping model and developed an intent-uncertainty-aware grasp planner to generate robust grasp poses given the ambiguous human intent inference inputs. With this validated modeling and planning techniques, it is expected to extend teleoperated robots’ functionality and adoption in practical telemanipulation scenarios.

Keywords: Telerobotics and Teleoperation, Computer Vision for Automation, Dexterous Manipulation
Abstract: In this paper, we present TeachNet, a novel neural network architecture for intuitive and markerless vision-based teleoperation of robotic hands. Robot joint angles are directly generated by depth images of the human hand that produce visually similar robot hand poses in an end-to-end fashion. The special structure of TeachNet, combined with a consistency loss function, handles the differences in appearance and anatomy between human and robotic hands. A synchronized human-robot training set is generated from an existing dataset of labeled depth images of the human hand and from simulated depth images of a robotic hand. The final training set includes 400K pairwise depth images and corresponding joint angles of a Shadow C6 robotic hand. The network evaluation results verify the superiority of TeachNet, especially regarding the high-precision condition. Imitation experiments and grasp tasks teleoperated by novice users demonstrate that TeachNet is more reliable and faster than the state-of-the-art vision-based teleoperation method.

Keywords: Telerobotics and Teleoperation, Control Architectures and Programming, Surgical Robotics: Laparoscopy
Abstract: In this paper, a two-layer architecture for the bilateral teleoperation of multi-arms systems with communication delay is presented. We extend the single-master-single-slave two layer approach proposed in [1] by connecting multiple robots to a single energy tank. This allows to minimize the conservativeness due to passivity preservation and to increment the level of transparency that can be achieved. The proposed approach is implemented on a realistic surgical scenario developed within the EU-funded SARAS project.

Keywords: Telerobotics and Teleoperation, Haptics and Haptic Interfaces
Abstract: Robot teleoperation is widely used for several hazardous applications. To increase teleoperator capabilities shared-control methods can be employed. In this paper, we present a passive task-prioritized shared-control method for remote telemanipulation of redundant robots. The proposed method fuses the task-prioritized control architecture with haptic guidance techniques to realize a shared-control framework for teleoperation systems. To preserve the semi-autonomous telerobotic system safety, passivity is analyzed and an energy-tanks passivity-based controller is developed. The proposed theoretical results are validated through experiments involving a real haptic device and a simulated slave robot.

Keywords: Telerobotics and Teleoperation, Compliant Joint/Mechanism, Compliance and Impedance Control
Abstract: Robots must cost less and be force-controlled to enable widespread, safe deployment in unconstrained human environments. We propose Quasi-Direct Drive actuation as a capable paradigm for robotic force-controlled manipulation in human environments at low-cost. Our prototype -Blue- is a human scale 7 Degree of Freedom arm with 2kg payload. Blue can cost less than 5000. We show that Blue has dynamic properties that meet or exceed the needs of human operators: the robot has a nominal position-control bandwidth of 7.5Hz and repeatability within 4mm. We demonstrate a Virtual Reality based interface that can be used as a method for telepresence and collecting robot training demonstrations. Manufacturability, scaling, and potential use-cases for the Blue system are also addressed. Videos and additional information can be found online at berkeleyopenarms.github.io.

Keywords: Telerobotics and Teleoperation, Medical Robots and Systems, Virtual Reality and Interfaces
Abstract: Surgical robots offer the exciting potential for remote telesurgery, but advances are needed to make this technology efficient and accurate to ensure patient safety. Achieving these goals is hindered by the deleterious effects of latency between the remote operator and the bedside robot. Predictive displays have found success in overcoming these effects by giving the operator immediate visual feedback. However, previously developed predictive displays can not be directly applied to telesurgery due to the unique challenges in tracking the 3D geometry of the surgical environment. In this paper, we present the first predictive display for teleoperated surgical robots. The predicted display is stereoscopic, utilizes Augmented Reality (AR) to show the predicted motions alongside the complex tissue found in-situ within surgical environments, and overcomes the challenges in accurately tracking slave-tools in real-time. We call this a Stereoscopic AR Predictive Display (SARPD). To test the SARPD's performance, we conducted a user study with ten participants on the da Vinci Surgical System. The results showed with statistical significance that using SARPD decreased time to complete task while having no effect on error rates when operating under delay.

Keywords: Grasping, Rehabilitation Robotics, Prosthetics and Exoskeletons
Abstract: In this paper, we present a constrained optimization framework for evaluating the post-contact stability of underactuated precision grasping configurations with a single degree of actuation. Relationships between key anthropomorphic design parameters including link length ratios, transmission ratios, joint stiffness ratios and palm width are developed with applications in upper limb prosthetic design. In addition to grasp stability, we examine post-contact system work, to reduce reconfiguration, and consider the range of objects that can be stably grasped. External wrenches were simulated on a subset of the heuristically evaluated optimal solutions and an optimal configuration was experimentally tested to determine favorable wrench resistible gripper orientations for grasp planning applications.These relationships provide insight for the development of a variety of prosthetic hands that can successfully grasp an object in precision grasp, be proprioceptively secure and be robust to interactions with its environment.

Keywords: Grasping, Sensor Fusion, Sensor-based Control
Abstract: In this paper, we propose the combination of sensing and control modules for catching soft objects (i.e., marshmallow and paper balloons) at a high speed without deforming them. In order to track the object that is dropped, we use a high-speed vision sensor, and control the positions of the fingertips of a robot to some extent. As the distance to the object decreases, the fingertip positions and velocity of the robot are accurately controlled by high-speed proximity sensor feedback. Furthermore, the fingertips are stopped before the object surface is deformed by them, by using contact detection based on the distance determined by the proximity sensor. The combination of the feedback from the two sensors enables high-speed, seamless, and high-resolution sensing without visual occlusion. In the experiment, we demonstrate that the hand could catch plastic deformable objects (i.e., a paper balloon or a marshmallow piece) with the simple sensor feedback control modules.

Keywords: Grasping, Perception for Grasping and Manipulation
Abstract: Different manipulation tasks require different types of grasps. For example, holding a heavy tool like a hammer requires a multi-fingered power grasp offering stability, while holding a pen to write requires a multi-fingered precision grasp to impart dexterity on the object. In this paper, we propose a probabilistic grasp planner that explicitly models grasp type for planning high-quality precision and power grasps in real-time. We take a learning approach in order to plan grasps of different types for previously unseen objects when only partial visual information is available. Our work demonstrates the first supervised learning approach to grasp planning that can explicitly plan both power and precision grasps for a given object. Additionally, we compare our learned grasp model with a model that does not encode type and show that modeling grasp type improves the success rate of generated grasps. Furthermore we show the benefit of learning a prior over grasp configurations to improve grasp inference with a learned classifier.

Keywords: Grasping, Force and Tactile Sensing, Soft Material Robotics
Abstract: We present a capacitive sensor suitable for a gripper that uses thin films of gecko-inspired adhesives. The sensor is fabricated directly on the films and measures the area over which the adhesive makes intimate contact. In experiments, a new under-actuated gripper uses adhesive films to acquire and hold objects having a variety of shapes and textures. Using the adhesive films, the gripper achieves 2.6x greater pullout force on rough surfaces as compared to using soft rubber. For a good grip, as the applied load increases, the films adhere more tightly to object surfaces and the local capacitance increases at contact regions. With six taxels per finger, the sensor can also detect whether the contact pattern of a grasp matches expectations.

Keywords: Grasping, Multifingered Hands, Computational Geometry
Abstract: Caging offers a robust strategy for grasping objects with robot hands. This paper utilizes caging for locking polygonal objects against a wall using minimalistic two-finger robot hands. From the object's perspective, the wall and two-finger hand form an equivalent three-finger hand. The object is first caged by trapezoidal finger formations of the equivalent three-finger hand, and the hand is then closed until the object is locked against the wall in the desired grasp. The object can then be safely grasped and moved away from the wall, or it can be held fixed against it to be worked on by tools. This paper presents a novel and efficient caging-to-locking algorithm. While the equivalent hand's configuration space is four-dimensional, the algorithm uses the hand's two-dimensional contact space, which represents all contacts by two and three of the equivalent hand's fingers along the object boundary. The problem of computing the critical cage formation that allows the object to escape the equivalent hand is reduced to a search along a caging graph constructed incrementally in the equivalent hand's contact space. Starting from the desired locking grasp, the graph is searched for an escape path which passes through the critical cage formation. The technique is demonstrated with a detailed example.

Keywords: Grasping, Deep Learning in Robotics and Automation
Abstract: Rapid and reliable robot grasping for a diverse set of objects has applications from warehouse automation to home de-cluttering. One promising approach is to learn deep policies from synthetic training datasets of point clouds, grasps, and rewards sampled using analytic models with stochastic noise models for domain randomization. In this paper, we explore how the distribution of synthetic training examples affects the rate and reliability of the learned robot policy. We propose a synthetic data sampling distribution that combines grasps sampled from the policy action set with guiding samples from a robust grasping supervisor that has full state knowledge. We use this to train a robot policy based on a fully convolutional network architecture that evaluates millions of grasp candidates in 4-DOF (3D position and planar orientation). Physical robot experiments suggest that a policy based on Fully Convolutional Grasp Quality CNNs (FC-GQ-CNNs) can plan grasps in 0.625s, considering 5000x more grasps than our prior policy based on iterative grasp sampling and evaluation. This computational efficiency improves rate and reliability, achieving 296 mean picks per hour (MPPH) compared to 250 MPPH for iterative policies. Sensitivity experiments explore the effect of supervisor guidance level and granularity of the policy action space.

Keywords: Parallel Robots, Motion Control
Abstract: In this contribution, a new adaptive motion cueing algorithm for a full motion driving simulator at the University of Stuttgart is presented, which allows kinematic vehicle movements to be taken into account. These are adequately processed via a state-flow chart and transferred to the motion cueing algorithm in such a way that the dynamic of the Stuttgart Driving Simulator can be used much more efficiently. Furthermore, a linear quadratic error minimization of the mentioned algorithm is presented. The primary objective is to provide a more realistic driving experience to the driver.

Keywords: Parallel Robots, Kinematics, Tendon/Wire Mechanism
Abstract: This paper addresses for the first time the singularity analysis of cable-driven parallel robot (CDPR) with sagging cables using the Irvine model. We present the mathematical framework of singularity analysis of CDPR using this cable model. We then show that, besides a cable model representation singularity, both the inverse and forward kinematics (IK and FK) have a singularity type, called {em parallel robot singularity}, which correspond to the singularity of an equivalent parallel robot with rigid legs. We then show that both the IK and FK have also {em full singularities}, that are not parallel robot singularity and are obtained when two of the IK or FK solution branches intersect. IK singularity will usually lie on the border of the CDPR workspace. We then exhibit an algorithm that allow one to prove that a singularity exist in the neighborhood of a given pose and to estimate its location with an arbitrary accuracy. Examples are provided for parallel robot, IK and FK singularities. However we have not been able to determine examples of {em combined singularity} where both the IK and FK are singular (besides parallel robot singularity).

Keywords: Failure Detection and Recovery, Parallel Robots, Manufacturing, Maintenance and Supply Chains
Abstract: In order to improve the machining efficiency and the flexibility of manufacturing system, the study of multi-duty parallel manipulators has attracted the interest of some researchers. In this paper, according to the effects of different operations on the driving element, a demarcation diagram for distinguishing different duties, such as statics, low-speed but heavy-load, high-speed but low-load and high-speed but heavy-load, is proposed, and a defect identification approach to prevent the occurrence of defects for multi-duty parallel manipulators is presented. Taking the 1PU+3UPS parallel manipulator as an instance, an analysis method to the statics and dynamics is investigated by means of the screw theory and the proposed virtual screw. Based on the numerical example, the results show that the classification and practicability of operations can be accurately identified by the proposed demarcation diagram and defect identification approach, respectively.

Keywords: Tendon/Wire Mechanism, Motion Control of Manipulators
Abstract: This paper proposes a point-to-point dynamic trajectory planning technique for reaching a series of poses with a sixdegree-of-freedom (six-DOF) cable-suspended parallel robot. Each trajectory segment is designed to have zero translational and rotational velocity at its endpoints; transitions between segments have translational and rotational acceleration continuity. This formulation facilitates the synthesis of trajectories that extend beyond the static workspace of the robot. A basis motion is introduced, which is a mathematical function that can be adapted for each coordinate direction along each trajectory segment.Kinematic constraints are satisfied through the selection of the coefficients for this function. Dynamic constraints are imposed by defining feasible regions within the workspace for each segment endpoint, based on the previous endpoint. Spherical linear interpolation (SLERP) is used to produce singularity-free, optimally interpolated rotational trajectory segments. An experimental implementation is presented using a six-DOF prototype and a supplementary video file is included to demonstrate the results.

Keywords: Hydraulic/Pneumatic Actuators, Parallel Robots, Flexible Robots
Abstract: This work is a preliminary study assessing the feasibility of using cold-gas thrusters for active damping of flexible cable-driven parallel robots. The concept is validated experimentally on a planar robot embedding custom-built supersonic air thrusters operating at an industry-standard pressure level. The stability of the proposed active damping strategy is proved using Lyapunov theory.

Keywords: Parallel Robots, Kinematics, Mechanism Design
Abstract: In this paper, we present a new family of overhead traveling cranes based on variable radius drums (VRDs), called cable-based robotic cranes (CBRCs). A VRD is characterized by the variation of the spool radius along its profile. This kind of device is used, in this context, for the development of a cable-robot, which can support and move a load through a planar working area with just two degrees of freedom. First we present the kinematic analysis and the synthesis of the geometry of a VRD profile. Then, the schema of a bidimensional horizontal moving mechanism, based on the VRD theory, and an experimental prototype of a threedimensional CBRC are presented. The features of this wire-based overhead crane and an analysis of cables tensions are discussed. Finally, the performance of this mechanism is evaluated, demonstrating a deviation between the end-effector and the nominal planar surface of less than 1% throughout the whole working area.

Keywords: Human Factors and Human-in-the-Loop, Human Performance Augmentation, Prosthetics and Exoskeletons
Abstract: In this study, we propose a novel human-in-the-loop optimization approach for exoskeleton robot control. We develop a method to optimize widely-used Electromyography (EMG)-based assistive strategies. If we use multiple EMG channels to control multi-DoF robots, optimization process becomes complex and requires a large amount of data. To make the optimization tractable, we exploit the synergies both of the human muscles and artificial muscles of the exoskeleton robots to reduce the number of parameters of the assistive strategies. We show that we can extract the synergies not only from the user’s muscle activities but from pneumatic artificial muscle (PAMs) contractions of the exoskeleton robot. Then, we adopt a Bayesian optimization method to acquire the parameters for assisting human movements by iteratively identifying the user’s preferences of the assistive strategies. We conducted experiments to evaluate our proposed method with a PAMs-driven upper limb exoskeleton robot. Our method successfully learned assistive strategies from the human-in-the-loop optimization with a practicable number of interactions.

Keywords: Prosthetics and Exoskeletons
Abstract: The purpose of this work is to introduce a newly developed exoskeleton robot designed to characterize the neuromuscular properties of the shoulder, including intrinsic and reflexive mechanisms, during static posture and dynamic movement in a 3-dimensional space. Quantitative characterization of these properties requires fast perturbation (>100 deg/s) to separate their contribution from that of voluntary mechanism. Understanding these properties of the shoulder control could assist in the rehabilitation or enhancement of upper limb performance during physical human-robot interaction. The device can be described as a new type of spherical parallel manipulator (SPM) that utilizes three 4-bar (4B) substructures to decouple and control roll, pitch and yaw of the shoulder. By utilizing a parallel architecture, the 4B-SPM exoskeleton has the advantage of high acceleration, fast enough to satisfy the speed requirement for the characterization of distinct neuromuscular properties of the shoulder. In this work, the prototype is presented, along with an evaluation of its position accuracy and step response tracking capabilities. The development and preliminary testing of the 4B-SPM exoskeleton presented in this work demonstrates its potential to be a useful tool for studying the neuromuscular mechanisms of the shoulder joint.

Keywords: Rehabilitation Robotics, Prosthetics and Exoskeletons, Human Factors and Human-in-the-Loop
Abstract: Robotic exoskeletons open up promising interventions during post-stroke rehabilitation by assisting individuals with sensorimotor impairments to complete therapy tasks. These devices have the ability to provide variable assistance tailored to individual-specific needs and, additionally, can measure several parameters associated with the movement execution. Metrics representative of movement quality are important to guide individualized treatment. While robots can provide data with high resolution, robustness, and consistency, the delineation of the human contribution in the presence of the kinematic guidance introduced by the robotic assistance is a significant challenge. In this paper, we propose a method for assessing voluntary effort from an individual fitted in an upper-body exoskeleton called Harmony. The method separates the active torques generated by the wearer from the effects caused by unmodeled dynamics and passive neuromuscular properties and involuntary forces. Preliminary results show that the effort estimated using the proposed method is consistent with the effort associated with muscle activity and is also sensitive to different levels, indicating that it can reliably evaluate user's contribution to movement. This method has the potential to serve as a high resolution assessment tool to monitor progress of movement quality throughout the treatment and evaluate motor recovery.

Keywords: Soft Material Robotics, Prosthetics and Exoskeletons, Hydraulic/Pneumatic Actuators
Abstract: Low weight and innate compliance make soft pneumatic actuators an attractive method for actuating wearable robots. Performance of soft pneumatic actuators can be tailored to an application by combining them in novel architectures. We modeled and constructed nested linear and pennate architectures using fiber-reinforced elastomeric enclosures (FREEs) with identical manufacturing parameters and total effective lengths to compare their suitability for a cable-driven exoskeleton for augmenting shoulder flexion. We determined actuator performance requirements using a static model for the transmission of actuator forces to the upper arm via Bowden cables. We experimentally characterized the architectures by measuring their force-displacement curves at a range of pressures, yielding greater force and displacement from the nested architecture in the domain required by our exoskeleton. Results also indicated a force threshold above which the pennate structure produced greater force at any given displacement. We validated the nested linear architecture using a prototype exoskeleton installed on a passive mannequin. Measured joint angles at varying pressures were close to predicted values, adjusted for measured losses due to cable anchor movement.

Keywords: Rehabilitation Robotics, Mechanism Design, Robot Safety
Abstract: This paper presents a novel light-weight back-drivable inherently-safe robotic mechanism for delivering ankle rehabilitation therapies. The implemented robot is designed to be used as the ankle module of a multi-purpose lower rehabilitation robot. A novel friction-based safety feature has been introduced that enables mechanical adjustment of the maximum amount of allowable transfer forces and torques to the patient’s limb. The design procedure, mathematical modeling, and experimental validations are provided to demonstrate the performance of the proposed system.

Keywords: Software, Middleware and Programming Environments, Control Architectures and Programming
Abstract: Scaling up the software system on service robots increases the maintenance burden of developers and the risk of resource contention of the computer embedded on robots. As a result, developers spend much time on configuring, deploying, and monitoring the robot software system; robots may utilize significant computer resources when all software processes are running. We present Rorg, a Linux container-based scheme to manage, schedule, and monitor software components on service robots. Although Linux containers are already widely-used in cloud environments, this technique is challenging to efficiently adopt in service robot systems due to multi-tasking, resource constraints and performance requirements. To pave the way of Linux containers on service robots in an efficient manner, we present a programmable container management interface and a resource time-sharing mechanism incorporated with the Robot Operating System (ROS). Rorg allows developers to pack software into self-contained images and runs them in isolated environments using Linux containers; it also allows the robot to turn on and off software components on demand to avoid resource contention. We evaluate Rorg with a long-term autonomous tour guide robot: It manages 41 software components on the robot and relieved our maintenance burden, and it also reduces CPU load by 45.5% and memory usage by 16.5% on average.

Keywords: Software, Middleware and Programming Environments, Control Architectures and Programming, Motion Control
Abstract: This work introduces a framework for the Cartesian control of multi-legged, highly redundant robots. The proposed framework allows the untrained user to perform complex motion tasks with robotics platforms by leveraging a simple, auto-generated ROS-based interface. Contrary to other motion control frameworks (e.g. ROS MoveIt!), we focus on the execution of Cartesian trajectories that are specified online, rather than planned in advance, as it is the case, for instance, in tele-operation and locomotion tasks. Moreover, we address the problem of generating such motions within a hard real-time (RT) control loop. Finally, we demonstrate the capabilities of our framework both on the COMAN+ humanoid robot, and on the hybrid wheeled-legged quadruped CENTAURO.

Keywords: Failure Detection and Recovery, Software, Middleware and Programming Environments, Formal Methods in Robotics and Automation
Abstract: Fault-tolerant architectures are mandatory to ensure the robustness of autonomous robots performing missions in complex and uncertain environments. The first step of a fault-tolerant mechanism is the detection of a faulty behavior of the system. It is then important to provide tools to help robot developers specify relevant observers. It is moreover crucial to guarantee a correct implementation of the observers, i.e. that the observers do not miss data and do not trigger unsuitable recovery actions in case of false detection. In this paper, we propose a specification language for observers that uses Past-Time LTL to express complex formulas on data produced by software components, and timed constraints on the evaluations of these formulas. We moreover provide an implementation of this specification that guarantees a real-time evaluation of the observers. We briefly describe the observers we have specified for a patrolling mission, and we evaluate the performance of our approach compared to state of the art on a benchmark in which we detect errors on a laser range sensor.

Keywords: Software, Middleware and Programming Environments, Motion Control, Dynamics
Abstract: Robotics applications often suffer from the `two-language problem', requiring a low-level language for performance-sensitive components and a high-level language for interactivity and experimentation, which tends to increase software complexity. We demonstrate the use of the Julia programming language to solve this problem by being fast enough for efficient online control of a humanoid robot and flexible enough for prototyping. We present several Julia packages developed by the authors, which together enable roughly 2x realtime simulation of the Boston Dynamics Atlas humanoid robot balancing on flat ground using a standard quadratic-programming-based controller. Benchmarks show a sufficiently low variation in control frequency to make deployment on the physical robot feasible. We also show that Julia's naturally generic programming style can be used to create versatile packages that are easy to compose and adapt to a wide variety of computational tasks in robotics.

Keywords: Software, Middleware and Programming Environments, Motion and Path Planning
Abstract: Motion Planning Templates (MPT) is a C++ template-based library that uses compile-time polymorphism to generate robot-specific motion planning code and is geared towards eking out as much performance as possible when running on the low-power CPU of a battery-powered small robot. To use MPT, developers of robot software write or leverage code specific to their robot platform and motion planning problem, and then have MPT generate a robot-specific motion planner and its associated data-structures. The resulting motion planner implementation is faster and uses less memory than general motion planning implementations based upon runtime polymorphism. While MPT loses runtime flexibility, it gains advantages associated with compile-time polymorphism---including the ability to change scalar precision, generate tightly-packed data structures, and store robot-specific data in the motion planning graph. MPT also uses compile-time algorithms to resolve the algorithm implementation, and select the best nearest neighbor algorithm to integrate into it. We demonstrate MPT's performance, lower memory footprint, and ability to adapt to varying robots in motion planning scenarios on a small humanoid robot and on 3D rigid-body motions.

Keywords: Software, Middleware and Programming Environments, Autonomous Agents, Mobile Manipulation
Abstract: Robot task programming often leads to inefficient plans, as opportunities for parallelization and precomputation are usually not exploited by the programmer. This inefficiency is often especially obvious in mobile manipulation, where path planning and pose estimation algorithms are time-consuming operations. In this paper, we introduce the concept of Resource-Aware Task Nodes (RATNs), a powerful descriptive action model for robots. Next, we propose an algorithm that executes so-called Concurrent Dataflow Task Networks (CDTNs), robot plans consisting of RATNs. It optimizes programmed plans based on two sources of information: 1) The control flow represented in the original task plan, whose constraints are relaxed to generate opportunities for parallelization and precomputation. 2) Dependencies between actions pertaining to resources, data flows and world model changes, the latter being equivalent to preconditions and effects. CDTNs have been integrated in our open-source task programming framework RAFCON, and we show that it leads to 11-29 % improvement in terms of execution time in two simulated mobile manipulation scenarios.

Keywords: Entertainment Robotics, Compliance and Impedance Control, Virtual Reality and Interfaces
Abstract: We present a robotic pen-drawing system that is capable of faithfully reproducing pen art on an unknown surface. Our robotic system relies on an industrial, seven-degree-of-freedom manipulator that can be both position- and impedance-controlled. In order to estimate a rough geometry of the target, continuous surface, we first generate a point cloud of the surface using an RGB-D camera, which is filtered to remove outliers and calibrated to the physical canvas surface. Then, our control algorithm physically reproduces digital drawing on the surface by impedance-controlling the manipulator. Our impedance-controlled drawing algorithm compensates for the uncertainty and incompleteness inherent to a point-cloud estimation of the drawing surface. Moreover, since drawing 2D vector pen art on a 3D surface requires surface parameterization that does not destroy the original 2D drawing, we rely on the least squares conformal mapping. Specifically, the conformal map reduces angle distortion during surface parameterization. As a result, our system can create distortion-free and complicated pen drawings on general surfaces with many unpredictable bumps robustly and faithfully.

Keywords: Biological Cell Manipulation, Automation at Micro-Nano Scales
Abstract: The ability to patterning cells is an important technique to facilitate cell-based assay and characterization. In this paper, an automated cell patterning system was developed for the fabrication of large-scale cell patterns. To resolve the challenge of the limited printable area, the cell-printing microchip and the substrate were mounted on the movable stages of the system, and large-scale cell patterns were realized through coordination between the stages. An autofocusing technique was integrated in the system to evaluate the gap between the microchip and the substrate. In order to enhance the performance of the patterning system, different experimental parameters, including the velocity of the moving stage, were examined. Yeast cells suspending in 6-aminohexanoic acid (AHA) solution were considered in this study, and a sequence of characters was successfully printed using the proposed system. The results confirm that this system offers an automatic method with high flexibility to construct large-scale cell patterns for various applications.

Keywords: Computer Vision for Other Robotic Applications, Deep Learning in Robotics and Automation
Abstract: Robotic painting is well-established in controlled factory environments, but there is now potential for mobile robots to do functional painting tasks around the everyday world. An obvious first target for such robots is painting a uniform single color. A step further is the painting of textured images. Texture involves a varying appearance, and requires that paint is delivered accurately onto the physical surface to produce the desired effect. Robotic painting of texture is relevant for architecture and in themed environments.

A key challenge for robotic painting of texture is to take a desired image as input, and to generate the paint commands to as closely as possible create the desired appearance, according to the robotic capabilities. This paper describes a deep learning approach to take an input ink map of a desired texture, and infer robotic paint commands to produce that texture.

We analyze the trade-offs between quality of reconstructed appearance and ease of execution. Our method is general for different kinds of robotic paint delivery systems, but the emphasis here is on spray painting. More generally, the framework can be viewed as an approach for solving a specific class of inverse imaging problems.

Keywords: Object Detection, Segmentation and Categorization, Robotics in Agriculture and Forestry, Agricultural Automation
Abstract: A key aspect to controlling and reducing the effects invasive insect species have on agriculture is to obtain knowledge about the migration patterns of these species. Current state-of-the-art methods of studying these migration patterns involve a mark-release-recapture technique, in which insects are released after being marked and researchers attempt to recapture them later. However, this approach involves a human researcher manually searching for these insects in large fields and results in very low recapture rates. In this paper, we propose an automated system for detecting released insects using an unmanned aerial vehicle. This system utilizes ultraviolet lighting technology, digital cameras, and lightweight computer vision algorithms to more quickly and accurately detect insects compared to the current state of the art. The efficiency and accuracy that this system provides will allow for a more comprehensive understanding of invasive insect species migration patterns. Our experimental results demonstrate that our system can detect real target insects in field conditions with high precision and recall rates.

Keywords: Entertainment Robotics, Human-Centered Robotics, Virtual Reality and Interfaces
Abstract: Motion simulators have been used extensively by both industry and academia to train pilots, conduct psychological experiments on drivers, understand the perception of motion by humans, and cater to the burgeoning gaming industry among others. Working of a motion simulator can be summarized as follows: i) acquisition of motion signals, ii) motion cueing: signal processing to generate motion references, iii) control: tracking the desired references. A motion cueing algorithm (MCA) acts as a bridge between the actual motions and the ones recreated by the simulator. Mathematically, MCA is constituted of the following operations: scaling, saturation, filtering, and tilt-coordination. The existing MCAs make use of causal filters to process the signals, thereby precluding the possibility of utilizing future motion signals to emulate pre-recorded scenarios. We present a new approach, referred to as acausal cueing algorithm (ACA), to generate motion cues by explicitly making use of future motion signals and causal linear filters. We present the developed methodology using discrete-time (DT) models to facilitate its quick implementation. The veracity of the presented methodology is examined by actuating SP7 motion simulator, based on the references generated by ACA, in response to test trajectories. The conducted experiments assert better performance of ACA (over MCA) in the beginning, which eventually degrades in the last few seconds due to unavailability of future motion signals.

Keywords: Entertainment Robotics, Humanoid Robots
Abstract: Talented musicians can deliver a powerful emotional experience to the audience by skillfully modifying several musical parameters, such as dynamics, articulation and tempo. Musical robots are expected to control those musical parameters in the same way to give the audience an experience comparable to listening to a professional human musician. But practical control of those parameters depends on the type of musical instrument being played. In this study, we describe our newly developed music dynamics control system for the Waseda Anthropomorphic Saxophonist robot. We first built a physical model for the saxophone reed motion and verified the dynamics-related parameters of the overall robot-saxophone system. We found that the magnitude of air flow is related to the sound pressure level, as expected, but also that the lower lip is critical to the sound stability. Accordingly, we then implemented a music dynamics control system for the robot and succeeded in enabling the robot to perform a music piece with different sound pressure levels.

Keywords: Aerial Systems: Perception and Autonomy, Autonomous Vehicle Navigation, Mapping
Abstract: We present Robust Object-based SLAM for High-speed Autonomous Navigation (ROSHAN), a novel approach to object-level mapping suitable for autonomous navigation. In ROSHAN, we represent objects as ellipsoids and infer their parameters using three sources of information -- bounding box detections, image texture, and semantic knowledge -- to overcome the observability problem in ellipsoid-based SLAM under common forward-translating vehicle motions. Each bounding box provides four planar constraints on an object surface and we add a fifth planar constraint using the texture on the objects along with a semantic prior on the shape of ellipsoids. We demonstrate ROSHAN in simulation where we outperform the baseline, reducing the median shape error by 83% and the median position error by 72% in a forward-moving camera sequence. We demonstrate similar qualitative result on data collected on a fast-moving autonomous quadrotor.

Keywords: Failure Detection and Recovery, Aerial Systems: Perception and Autonomy
Abstract: MAVLink is a popular message protocol for small Unmanned Aerial Vehicles (UAVs). In this work, we present a Fault Detection and Isolation (FDI) framework for fixed-wing UAVs which takes advantage of the information conveyed in MAVLink telemetry streams and produces a bank of residual generators. Structural Analysis is employed to systematically handle the varying set of available measurements, identify the observable faults and adjust the FDI system accordingly. %find calculable matchings in the structural graph. Structural detectability and isolability analyses are carried out. A case-study on a real-life telemetry log of a UAV crash demonstrates the efficacy of the proposed approach.

Keywords: AI-Based Methods, Aerial Systems: Perception and Autonomy, Motion and Path Planning
Abstract: This paper addresses the problem of generating quadcopter minimum snap trajectories for real time applications. Previous efforts addressed this problem by either employing a gradient descent method, or by greatly sacrificing optimality for faster solutions that are amenable for onboard implementation. In this work, outputs of the gradient descent method are used offline to train a supervised neural network. We show that the use of neural networks results typically in two orders of magnitude reduction in computational time. Our proposed approach can be used for warm-starting onboard implementable iterative methods with an ``educated'' initial guess. This work is motivated by the application for human-machine interface in which a human provides desired trajectory through a smart-tablet interface, which has to be translated into a dynamically feasible trajectory for a quadcopter. The proposed solution is tested in thousands of different examples, demonstrating its effectiveness as a booster for minimum snap trajectory generation for quadcopters.

Keywords: Aerial Systems: Perception and Autonomy, Learning from Demonstration, Deep Learning in Robotics and Automation
Abstract: Autonomous micro aerial vehicles still struggle with fast and agile maneuvers, dynamic environments, imperfect sensing, and state estimation drift. Autonomous drone racing brings these challenges to the fore. Human pilots can fly a previously unseen track after a handful of practice runs. In contrast, state-of-the-art autonomous navigation algorithms require either a precise metric map of the environment or a large amount of training data collected in the track of interest. To bridge this gap, we propose an approach that can fly a new track in a previously unseen environment without a precise map or expensive data collection. Our approach represents the global track layout with coarse gate locations, which can be easily estimated from a single demonstration flight. At test time, a convolutional network predicts the poses of the closest gates along with their uncertainty. These predictions are incorporated by an extended Kalman filter to maintain optimal maximum-a-posteriori estimates of gate locations. This allows the framework to cope with misleading high-variance estimates that could stem from poor observability or lack of visible gates. Given the estimated gate poses, we use model predictive control to quickly and accurately navigate through the track. The presented approach was used to win the IROS 2018 Autonomous Drone Race Competition, outracing the second-placing team by a factor of two.

Keywords: Aerial Systems: Perception and Autonomy, Aerial Systems: Applications, Semantic Scene Understanding
Abstract: We extend the ability of cameras to perceive obstacles for aircraft safety systems by enabling 3d sensing of free hanging wires. Our algorithm exploits the specialized 2d and 3d structure of wires to exceed state of the art performance in 2d sensing and 3d location estimation of wire obstacles. In 2d, a new neural network architecture, Deep Wire CNN, directly predicts the location of wire line segments in the image. In 3d, the detections are tracked and triangulated as the aircraft flies in order to estimated the wire's location. Our triangulation uses a new formulation of wire reconstruction as the estimation of the wire's vertical plane. Together these advancements enable real-time detections of wire hazards at ranges of over 1km. The system performance is evaluated on prior image level wire detection datasets and we introduce a new public dataset in order to evaluate full system results on over 40 approaches to power lines from a manned helicopter.

Keywords: Aerial Systems: Perception and Autonomy, Aerial Systems: Applications, Field Robots
Abstract: We present a novel pose and posture estimation framework of aerial skeleton system for outdoor flying. To exploit redundant/independent sensing while rendering the system “modular”, we attach an IMU (inertial measurement unit) sensor and a GNSS (global navigation satellite system) module on each link and perform SE(3)-motion EKF (extended Kalman filtering). We then apply the kinematic constraints of the aerial skeleton system to these EKF estimates of all the links through SCKF (smoothly constrained Kalman filtering), thereby, enforcing the kinematic coherency of the skeleton system and, consequently, significantly enhancing the estimation accuracy and the control performance/stability of the aerial skeleton system. A semi-distributed version of the obtained estimation framework is also presented to address the issue of scalability. The theory is then verified/demonstrated with real outdoor flying experiments and simulation studies of a three-link aerial skeleton system.

Keywords: Agricultural Automation, Motion and Path Planning
Abstract: A method was previously developed by this author to optimise the flight path of a fixed wing UAV performing aerial surveys of complex concave agricultural fields. This relies heavily on a flight time in wind prediction model as its cost function. This paper aims to validate this model by comparing flight test results with the model prediction. There are a number of assumptions that this model relies on. The major assumption is that wind is steady and uniform over the small area and time scales involved in a survey. To show that this is reasonable, wind fields measurements will be taken from a multi rotor UAV with an ultrasonic windspeed sensor.

Keywords: Motion and Path Planning, Search and Rescue Robots, Aerial Systems: Perception and Autonomy
Abstract: Target search with unmanned aerial vehicles (UAVs) is relevant problem to many scenarios, e.g., search and rescue (SaR). However, a key challenge is planning paths for maximal search efficiency given flight time constraints. To address this, we propose the Obstacle-aware Adaptive Informative Path Planning (OA-IPP) algorithm for target search in cluttered environments using UAVs. Our approach leverages a layered planning strategy using a Gaussian Process (GP)-based model of target occupancy to generate informative paths in continuous 3D space. Within this framework, we introduce an adaptive replanning scheme which allows us to trade off between information gain, field coverage, sensor performance, and collision avoidance for efficient target detection. Extensive simulations show that our OA-IPP method performs better than state-of-the-art planners, and we demonstrate its application in a realistic urban SaR scenario.

Keywords: Autonomous Vehicle Navigation, Motion and Path Planning, Collision Avoidance
Abstract: Autonomous navigation through unknown environments is a challenging task that entails real-time localization, perception, planning, and control. UAVs with this capability have begun to emerge in the literature with advances in lightweight sensing and computing. Although the planning methodologies vary from platform to platform, many algorithms adopt a hierarchical planning architecture where a slow, low-fidelity global planner guides a fast, high-fidelity local planner. However, in unknown environments, this approach can lead to erratic or unstable behavior due to the interaction between the global planner, whose solution is changing constantly, and the local planner; a consequence of not capturing higher-order dynamics in the global plan. This work proposes a planning framework in which multi-fidelity models are used to reduce the discrepancy between the local and global planner. Our approach uses high-, medium-, and low-fidelity models to compose a path that captures higher-order dynamics while remaining computationally tractable. In addition, we address the interaction between a fast planner and a slower mapper by considering the sensor data not yet fused into the map during the collision check. This novel mapping and planning framework for agile flights is validated in simulation and hardware experiments, showing replanning times of 5-40 ms in cluttered environments.

Keywords: Field Robots, Aerial Systems: Applications, Autonomous Vehicle Navigation
Abstract: There has been considerable recent work in motion planning for UAVs to enable aggressive, highly dynamic flight in known environments with motion capture systems. However, these existing planners have not been shown to enable the same kind of flight in unknown, outdoor environments. In this paper we present a receding horizon planning architecture that enables the fast replanning necessary for reactive obstacle avoidance by combining three techniques. First, we show how previous work in computationally efficient, closed-form trajectory generation method can be coupled with spatial partitioning data structures to reason about the geometry of the environment in real-time. Second, we show how to maintain safety margins during fast flight in unknown environments by planning velocities according to obstacle density. Third, our receding horizon, sampling-based motion planner uses minimum-jerk trajectories and closed-loop tracking to enable smooth, robust, high-speed flight with the low angular rates necessary for accurate visual-inertial navigation. We compare against two state-of-the-art, reactive motion planners in simulation and benchmark solution quality against an offline global planner. Finally, we demonstrate our planner over 80 flights with a combined distance of 22km of autonomous quadrotor flights in an urban environment at speeds up to 9.4 m/s.

Keywords: Environment Monitoring and Management, Motion and Path Planning, Optimization and Optimal Control
Abstract: Unmanned Aerial Vehicle (UAV) path planning algorithms often assume a knowledge reward function or priority map, indicating the most important areas to visit. In this paper we propose a method to create priority maps for monitoring or intervention of dynamic spreading processes such as wildfires. The presented optimization framework utilizes the properties of positive systems, in particular the separable structure of value (cost-to-go) functions, to provide scalable algorithms for surveillance and intervention. We present results obtained for a 16 and 1000 node example and convey how the priority map responds to changes in the dynamics of the system. The larger example of 1000 nodes, representing a fictional landscape, shows how the method can integrate bushfire spreading dynamics, landscape and wind conditions. Finally, we give an example of combining the proposed method with a travelling salesman problem for UAV path planning for wildfire intervention.

Keywords: Robotics in Agriculture and Forestry, Mapping, Multi-Robot Systems
Abstract: The combination of aerial survey capabilities of Unmanned Aerial Vehicles with targeted intervention abilities of agricultural Unmanned Ground Vehicles can significantly improve the effectiveness of robotic systems applied to precision agriculture. In this context, building and updating a common map of the field is an essential but challenging task. The maps built using robots of different types show differences in size, resolution and scale, the associated geolocation data may be inaccurate and biased, while the repetitiveness of both visual appearance and geometric structures found within agricultural contexts render classical map merging techniques ineffective. In this paper we propose AgriColMap, a novel map registration pipeline that leverages a grid-based multimodal environment representation which includes a vegetation index map and a Digital Surface Model. We cast the data association problem between maps built from UAVs and UGVs as a multimodal, large displacement dense optical flow estimation. The dominant, coherent flows, selected using a voting scheme, are used as point-to-point correspondences to infer a preliminary non-rigid alignment between the maps. A final refinement is then performed, by exploiting only meaningful parts of the registered maps. We evaluate our system using real world data for 3 fields with different crop species. The results show that our method outperforms several state of the art map registration and matching techniques by a large margin.

Keywords: Learning from Demonstration, Deep Learning in Robotics and Automation
Abstract: Insertion is a challenging haptic and visual control problem with significant practical value for manufacturing. Existing approaches in the model-based robotics community can be highly effective when task geometry is known, but are complex and cumbersome to implement, and must be tailored to each individual problem by a qualified engineer. Within the learning community there is a long history of insertion research, but existing approaches are either too sample-inefficient to run on real robots, or assume access to high-level object features, e.g. socket pose. In this paper we show that relatively minor modifications to an off-the-shelf Deep-RL algorithm (DDPG), combined with a small number of human demonstrations, allows the robot to quickly learn to solve these tasks efficiently and robustly. Our approach requires no modeling or simulation, no parameterized search or alignment behaviors, no vision system aside from raw images, and no reward shaping. We evaluate our approach on a narrow-clearance peg-insertion task and a deformable clip-insertion task, both of which include variability in the socket position. Our results show that these tasks can be solved reliably on the real robot in less than 10 minutes of interaction time, and that the resulting policies are robust to variance in the socket position and orientation.

Keywords: Learning from Demonstration, Deep Learning in Robotics and Automation, Autonomous Vehicle Navigation
Abstract: Estimating statistical uncertainties allows autonomous agents to communicate their confidence during task execution and is important for applications in safety-critical domains such as autonomous driving. In this work, we present the uncertainty-aware imitation learning (UAIL) algorithm for improving end-to-end control systems via data aggregation. UAIL applies Monte Carlo Dropout to estimate uncertainty in the control output of end-to-end systems, using states where it is uncertain to selectively acquire new training data. In contrast to prior data aggregation algorithms that force human experts to visit sub-optimal states at random, UAIL can anticipate its own mistakes and switch control to the expert in order to prevent visiting a series of sub-optimal states. Our experimental results from simulated driving tasks demonstrate that our proposed uncertainty estimation method can be leveraged to reliably predict infractions. Our analysis shows that UAIL outperforms existing data aggregation algorithms on a series of benchmark tasks.

Keywords: Learning from Demonstration, Deep Learning in Robotics and Automation
Abstract: Diversity of environments is a key challenge that causes learned robotic controllers to fail due to the discrepancies between the training and evaluation conditions. Training from demonstrations in various conditions can mitigate---but not completely prevent---such failures. Learned controllers such as neural networks typically do not have a notion of uncertainty that allows to diagnose an offset between training and testing conditions, and potentially intervene. In this work, we propose to use Bayesian Neural Networks, which have such a notion of uncertainty. We show that uncertainty can be leveraged to consistently detect situations in high-dimensional simulated and real robotic domains in which the performance of the learned controller would be sub-par. Also, we show that such an uncertainty based solution allows making an informed decision about when to invoke a fallback strategy. One fallback strategy is to request more data. We empirically show that providing data only when requested results in increased data-efficiency.

Keywords: Learning from Demonstration, Deep Learning in Robotics and Automation, Simulation and Animation
Abstract: Learning from demonstration (LfD) is useful in settings where hand-coding behaviour or a reward function is impractical. It has succeeded in a wide range of problems but typically relies on manually generated demonstrations or specially deployed sensors and has not generally been able to leverage the copious demonstrations available in the wild: those that capture behaviours that were occurring anyway using sensors that were already deployed for another purpose, e.g., traffic camera footage capturing demonstrations of natural behaviour of vehicles, cyclists, and pedestrians. We propose video to behaviour (ViBe), a new approach to learn models of behaviour from unlabelled raw video data of a traffic scene collected from a single, monocular, initially uncalibrated camera with ordinary resolution. Our approach calibrates the camera, detects relevant objects, tracks them through time, and uses the resulting trajectories to perform LfD, yielding models of naturalistic behaviour. We apply ViBe to raw videos of a traffic intersection and show that it can learn purely from videos, without additional expert knowledge.

Keywords: Learning from Demonstration, Model Learning for Control, Visual Learning
Abstract: Learning effective visuomotor policies for robots purely from data is challenging, but also appealing since a learning-based system should not require manual tuning or calibration. In the case a robot operating in a real environment the training process can be costly, time-consuming, and even dangerous since failures are common at the start of training. For this reason, it is desirable to be able to leverage simulation and off-policy data to the extent possible to train the robot. In this work, we introduce a robust framework that plans in simulation and transfers well to the real environment. Our model incorporates a gradient-descent based planning module, which given the initial image and goal image, encodes the images to a lower dimensional latent state and plans a trajectory to reach the goal. The model consisting of the encoder and planner modules is trained through a meta-learning strategy in simulation first. We subsequently perform adversarial domain transfer on the encoder by using a bank of unlabelled but random images from the simulation and real environments to enable the encoder to map images from the real and simulated environments to a similarly distributed latent representation. By fine tuning the entire model (encoder + planner) with far fewer real expert demonstrations, we show successful planning performances in different navigation tasks.

Keywords: Learning from Demonstration, Deep Learning in Robotics and Automation, Autonomous Agents
Abstract: Recent developments in multi-agent imitation learning have shown promising results for modeling the behavior of human drivers. However, it is challenging to capture emergent traffic behaviors that are observed in real-world datasets. Such behaviors arise due to the many local interactions between agents that are not commonly accounted for in imitation learning. This paper proposes Reward Augmented Imitation Learning (RAIL), which integrates reward augmentation into the multi-agent imitation learning framework and allows the designer to specify prior knowledge in a principled fashion. We prove that convergence guarantees for the imitation learning process are preserved under the application of reward augmentation. This method is validated in a driving scenario, where an entire traffic scene is controlled by driving policies learned using our proposed algorithm. Further, we demonstrate improved performance in comparison to traditional imitation learning algorithms both in terms of the local actions of a single agent and the behavior of emergent properties in complex, multi-agent settings.

Keywords: RGB-D Perception, Perception for Grasping and Manipulation, Deep Learning in Robotics and Automation
Abstract: Modern robotic systems are very complex and need to be tested in simulations with detailed sensor noise models to effectively verify robotic behavior. Unfortunately, many depth camera simulations contain limited noise models, or can only support generating realistic depth images of simple scenes. We propose a data driven approach to generate more realistic noise for complex simulated environments by using a convolutional neural network (CNN) to predict which pixels of a simulated noise-free depth image will not have returns (no-depth-return pixels, or NDP). We choose to focus on NDP here, as these dropouts are the most common and dramatic form of depth image noise. To train this network, we use reconstructed real-world scenes from the Label Fusion dataset to provide ground truth depth for each noisy depth image used to scan the scene. We use the resulting noise-free and noisy depth image pairs as labeled examples and train the network to predict which pixels of the noise-free image will be NDP. When used to post-process a simulation of a depth sensor, this system produces realistic depth images, even in cluttered scenes. To demonstrate that our approach successfully closes the reality gap for depth imagery, we show that the popular ICP algorithm for object pose estimation fails more realistically on our CNN-corrupted simulated depth images than on uncorrupted depth images and unsupervised domain adaptation baselines.

Keywords: Deep Learning in Robotics and Automation, Manipulation Planning, Software, Middleware and Programming Environments
Abstract: Using the effects of quantum mechanics for computing challenges has been an often discussed topic for decades. The frequent successes and early products in this area, which we have seen in recent years, indicate that we are currently entering a new era of computing. This paradigm shift will also impact the work of robotic scientists and the applications of robotics. New possibilities as well as new approaches to known problems will enable the creation of even more powerful and intelligent robots that make use of quantum computing cloud services or co-processors. In this position paper, we discuss potential application areas and also point out open research topics in quantum computing for robotics. We go into detail on the impact of quantum computing in artificial intelligence and machine learning, sensing and perception, kinematics as well as system diagnosis. For each topic we point out where quantum computing could be applied based on results from current research.

Keywords: Deep Learning in Robotics and Automation, Assembly, Manipulation Planning
Abstract: Automatic assembly has broad applications in industries. Traditional assembly tasks utilize predefined trajectories or tuned force control parameters, which make the automatic assembly time-consuming, difficult to generalize, and not robust to uncertainties. In this paper, we propose a learning framework for high precision industrial assembly. The framework combines both the supervised learning and the reinforcement learning. The supervised learning utilizes trajectory optimization to provide the initial guidance to the policy, while the reinforcement learning utilizes actor-critic algorithm to establish the evaluation system even the supervisor is not accurate. The proposed learning framework is more efficient compared with the reinforcement learning and achieves better stability performance than the supervised learning. The effectiveness of the method is verified by both the simulation and experiment.

Keywords: Deep Learning in Robotics and Automation, Model Learning for Control, Force and Tactile Sensing
Abstract: Touch sensing is widely acknowledged to be important for dexterous robotic manipulation, but exploiting tactile sensing for continuous, non-prehensile manipulation is challenging. General purpose control techniques that are able to effectively leverage tactile sensing as well as accurate physics models of contacts and forces remain largely elusive, and it is unclear how to even specify a desired behavior in terms of tactile percepts. In this paper, we take a step towards addressing these issues by combining high-resolution tactile sensing with data-driven modeling using deep neural network dynamics models. We propose deep tactile MPC, a framework for learning to perform tactile servoing from raw tactile sensor inputs, without manual supervision. We show that this method enables a robot equipped with a GelSight-style tactile sensor to manipulate a ball, analog stick, and 20-sided die, learning from unsupervised autonomous interaction and then using the learned tactile predictive model to reposition each object to user-specified configurations, indicated by a goal tactile reading.

Keywords: Deep Learning in Robotics and Automation, Motion and Path Planning, Intelligent Transportation Systems
Abstract: Sampling-based motion planning is an effective tool to compute safe trajectories for automated vehicles in complex environments. However, a fast convergence to the optimal solution can only be ensured with the use of problem-specific sampling distributions. Due to the large variety of driving situations within the context of automated driving, it is very challenging to manually design such distributions. This paper introduces therefore a data-driven approach utilizing a deep convolutional neural network (CNN): Given the current driving situation, future ego-vehicle poses can be directly generated from the output of the CNN allowing to guide the motion planner efficiently towards the optimal solution. A benchmark highlights that the CNN predicts future vehicle poses with a higher accuracy compared to uniform sampling and a state-of-the-art A*-based approach. Combining this CNN-guided sampling with the motion planner Bidirectional RRT* reduces the computation time by up to an order of magnitude and yields a faster convergence to a lower cost as well as a success rate of 100% in the tested scenarios.

Keywords: Natural Machine Motion, Multifingered Hands, Deep Learning in Robotics and Automation
Abstract: Human can purposefully exploit the intrinsic compliance of their hands to achieve reliable grasps. Recently, robotics community has tried to replicate this characteristic, by realizing soft hands that embed compliant elements in their mechanical design. This enables an effective adaptation with the items and the environment, and, ultimately, an increase of grasping performance. However, the human example is still unmatched on the robotic side, especially for what concerns autonomous grasp execution, which requires a synergistic integration of sensory, motor and computation capabilities.

In this work we propose an approach to enable soft hands to autonomously grasp objects, starting from the observations of human strategies. The architecture we propose integrates feedforward components with sensory-triggered reactive actions. A classifier realized through a deep neural network takes as input visual information on the object to be grasped, and predicts which action a human would perform to achieve the goal. The network is trained using first person videos of human strategies. This information is employed to select one among a set of human-inspired primitives defining the evolution of soft hand’s posture as a combination of anticipatory action and touch-based reactive grasp. The architecture is completed by the hardware component, which consists of a webcam to look at the scene, a Kuka LWR arm, and a soft hand. The latter is equipped with IMUs at the fingernails for detecting c

Keywords: Soft Material Robotics, Wearable Robots, Rehabilitation Robotics
Abstract: Loss of functional motor skills are common and often require patients to undergo rehabilitation so that they have a chance at motor recovery. Advancement in technology has seen to a rise in the use of robotic technology in conducting rehabilitative exercises that are traditionally carried out by physiotherapists. In recent years, soft robotic exoskeletons, using pneumatic-based actuation in particular, have gained much interest due to their compliant characteristics and safe operating conditions. In order to carry out complex task-based rehabilitative exercises, these soft pneumatic actuators must ideally be able to move with multiple degrees of freedom or minimally, in a bidirectional motion. Majority of the research covering soft actuators can only achieve finger flexion with some providing passive finger extension. Non-invasive intent detection in the control of these exoskeletons is also lacking in sensing both finger flexion and extension. In this paper we present our work on a fold-based bidirectional 3D printed intent-sensing soft pneumatic actuator (ISPA) that can achieve bidirectional motion and provide intent detection for finger flexion and extension for application in upper limb rehabilitative exoskeletons.

Keywords: Prosthetics and Exoskeletons, Tendon/Wire Mechanism
Abstract: Soft, under-actuated and compliant robotic exogloves have received an increased interest over the last decade. Possible applications of these systems range from augmenting the capabilities of healthy individuals to restoring the mobility of people that suffer from paralysis or stroke. Despite the significant progress in the field, most existing solutions are still heavy and expensive, they require an external power source to operate, and they are not wearable. In this paper, we focus on the development of adaptive (underactuated and compliant), tendon-driven, wearable exo-gloves and we propose two compact, affordable and lightweight assistive devices that provide grasping capabilities enhancement to the user. The devices are experimentally tested and their efficiency is validated using three different types of tests: i) grasping tests that involve different everyday objects, ii) force exertion capability tests that assess the fingertip forces that can be exerted while using the exo-gloves, and iii) motion tracking experiments focusing on the finger bending profile. The devices are able to significantly enhance the grasping capabilities of their user with a weight of 335 g and a cost of 92 USD for the body powered version and a weight of 562 g and a cost of 369 USD for the motorized exo-glove version.

Keywords: Haptics and Haptic Interfaces, Prosthetics and Exoskeletons, Human-Centered Robotics
Abstract: Without proprioception, i.e. the intrinsic capability of a body to perceive its own limb position, completing daily life activities would require constant visual attention and it would challenging or even impossible. This situation is similar to the one experienced after limb amputation and in robotic tele-operation, where the natural sensory-motor loop is broken. While some promising solutions based on skin stretch sensory substitution have been proposed to restore tactile properties in these conditions, there is still room for enhancing the intuitiveness of stimulus delivery and the integration of haptic feedback devices within user's body. Here we propose a wearable device based on skin stretch stimulation, the Stretch-Pro, which can provide proprioceptive information on artificial hand aperture. This system can be suitably integrated in a prosthetic socket, or can be easily worn by a user controlling remote robots. The system can imitate the stretching of the skin that would naturally occur on the intact limb, when it is used to accomplish motor tasks. Two versions of the system are presented, with 1 and 2 actuators, respectively, which deliver the stretch stimulus in different ways. Experiments with able-bodied participants and a preliminary test with one prosthesis user are reported. Results suggest that Stretch-Pro could be a viable solution to convey proprioceptive cues to upper limb prosthesis users, opening promising perspectives for tele-robotics applications.

Keywords: Physically Assistive Devices, Human Factors and Human-in-the-Loop, Rehabilitation Robotics
Abstract: Assistive robotic systems endeavour to support those with movement disabilities, enabling them to move again and regain functionality. Main issue with these systems is the complexity of their low-level control, and how to translate this to simpler, higher level commands that are easy and intuitive for a human user to interact with. We have created a multi-modal system, consisting of different sensing, decision making and actuating modalities, leading to intuitive, human-in-the-loop assistive robotics. The system takes its cue from the user's gaze, to decode their intentions and implement low-level motion actions to achieve high-level tasks. This results in the user simply having to look at the objects of interest, for the robotic system to assist them in reaching for those objects, grasping them, and using them to interact with other objects. We present our method for 3D gaze estimation, and grammars-based implementation of sequences of action with the robotic system. The 3D gaze estimation is evaluated with 8 subjects, showing an overall accuracy of 4.68+/-0.14cm. The full system is tested with 5 subjects, showing successful implementation of 100% of reach to gaze point actions and full implementation of pick and place tasks in 96%, and pick and pour tasks in 76% of cases. Finally we present a discussion on our results and what future work is needed to improve the system.

Keywords: Rehabilitation Robotics, Telerobotics and Teleoperation
Abstract: Due to the limitations of therapists’ time and healthcare resources to cover the increasing demand for rehabilitation services, robot-assisted rehabilitation is becoming an appealing, powerful and economical solution. In our previous research, a solution that combines Learning from Demonstration (LfD) and robotic rehabilitation to save the therapist’s time and reduce the therapy costs was proposed. In this paper we compare two modalities, Robot- and Telerobotic-Mediated Kinesthetic Teaching (RMKT and TMKT), for implementing LfD in robotic rehabilitation. Our results show that behaviors demonstrated in both modalities are able to be imitated accurately, but demonstrations in TMKT have less repeatability.

Keywords: Rehabilitation Robotics, Medical Robots and Systems
Abstract: To date, the aim of spinal cord injury researches in animals is to find the most effective treatment method which can lead to faster recovery. In order to evaluate if the method is effective, robust functional assessments are crucial. From the past to present, indicators to observe the recovery of the motor function in rodent SCI models are using human observance or the Basso, Beattie, and Bresnahan score, force detection, and imaging approaches. Nevertheless, these indicators do not meet some requirements for a severe full transection injury case. The goal of this project is to develop a novel force sensing system for measuring the ground reaction force of rats with severe SCI. In total, this system was tested with 12 spinalized rats. Following a full transection at the T9-T10 level of the spinal cord in rats with a 2mm gap, a nanofiber scaffold containing Neurotrophin-3 was implanted. After 12 weeks of training, results showed that rehabilitated rats were able to gradually exert more force as compared to non-rehabilitated rats. Results not only showed that rehabilitation enhanced recovery of motor function, but also demonstrated the viability of measuring the ground reaction force applied by the rats as an assessment for a full spinal cord transection injury model.

Keywords: Medical Robots and Systems, Automation at Micro-Nano Scales, Micro/Nano Robots
Abstract: This paper presents a novel permanent magnets based actuator capable of injecting and 2D wireless control the motion of an untethered microrobot. The actuator is obtained with a simple, but an effective arrangement of four permanent magnets. Its novelty is that it creates local maxima of the magnetic field in a planar workspace. This results in a convergence point for magnetic particles that are in its influence zone. Trapping particles in the local maxima makes their open-loop guidance possible, even in presence of reasonable perturbations. Actually, open-loop control is the only way to achieve some drug delivery when there are no sensors to provide us a feedback on the particle's positions. This is case of most treatments where targeted drug delivery is to be used, such as in inner ear treatment, cardiac arrhythmias and antibiotic-resistant skin infections. Experimental results are provided in the paper to show the soundness of the proposed actuator design.

Keywords: Micro/Nano Robots, Medical Robots and Systems
Abstract: A hybrid manufacturing process combining abrasive jet and laser micromaching enables the creation of living hinges in nitinol that retain the superelastic properties of the bulk material. The former selectively etches through the thickness of a workpiece and the latter defines the part's final geometry. Because the majority of the material removal is done with the room-temperature mechanical etching procedure, thermal damage to the part is minimized. Processing parameters to achieve desired geometries are described, a bending stiffness model for the living hinges is provided, and validation experiments are presented. Lastly, to demonstrate the usefulness of these components to millimeter-sized robotic systems and medical devices, we show their integration in two prototype devices: an endoscopic camera wrist and a simple laser beam steering system.

Keywords: Medical Robots and Systems, Micro/Nano Robots, Mechanism Design
Abstract: Current minimally-invasive surgical tools suffer from lack of scalability and restricted access to some surgical sites using a laparoscopic probe. This paper introduces a proof-of-concept prototype of the first completely wireless surgical scissors capable of dexterous motion and cutting in a remote environment as a mobile microrobotic device. The 15 mm untethered surgical scissors are custom made from sharpened titanium sheets with a magnet on each blade for actuating force and control. A super-elastic nitinol wire acts as a restoring spring and results in a simple design with no pin joint which is difficult to fabricate at small sizes. To actuate and control the scissors, a 3D magnetic coil system is used here for testing and demonstration. An external magnetic flux density of 20 mT can be generated using the coils and is used for cutting as well as orienting, moving and closing the scissors. In this first prototype setup, the scissors can generate up to 75 mN of cutting force, and we demonstrate the cutting of agar. As a proof of concept demonstration of the potential use of the scissors as a completely untethered surgical tool, we robotically maneuver the scissors to a target location in a confined environment where they cut through agar and return to their initial position.

Keywords: Medical Robots and Systems, Surgical Robotics: Steerable Catheters/Needles, Mechanism Design
Abstract: This paper presents the development of a fiber Bragg grating (FBG) bending sensor for shape memory alloy (SMA) bending modules. Due to the small form factor, low cost, and large-deflection capability, SMA bending modules can be used to construct disposable surgical robots for a variety of minimally invasive procedures. To realize a closed-loop control of SMA bending modules, an intrinsic bending sensor is imperative. Due to the lack of bending sensors for SMA bending modules, we have developed an FBG bending sensor by integrating FBG fibers with a superelastic substrate using flexible adhesive. Since the substrate is ultra-thin and adhesive is flexible, the sensor has low stiffness and can measure large curvatures. Additionally, due to the orthogonal arrangement of the sensor/actuator assembly, the influence of temperature variation caused by SMA actuation can be compensated. The working principle of the developed sensor was modeled followed by simulations. After experimentally evaluating the developed model, the sensor was integrated with an SMA bending module and cyclically bi-directionally deflected. The experimental results proved the relatively high measurement accuracy, high repeatability, and large measurable curvatures of the sensor, although hysteresis was observed due to friction.

Keywords: Medical Robots and Systems, Tendon/Wire Mechanism, Kinematics
Abstract: We present a modular sensing system to measure the deflection of a minimally invasive neurosurgical intracranial robot: MINIR-II. The MINIR-II robot is a tendon-driven continuum robot comprised of multiple spring backbone segments, which has been developed in our prior work. Due to the flexibility of the spring backbone and unique tendon routing configuration, each segment of MINIR-II can bend up to a large curvature (>=100 m-1) in multiple directions. However, the shape measurement of the robot based on tendon displacement is not precise due to friction and unknown external load/disturbance. In this regard, we propose a bending sensor module comprised of a fiber Bragg grating (FBG) fiber, a Polydimethylsiloxane (PDMS) cylinder, and a superelastic spring. The grating segment of the FBG fiber is enclosed inside a PDMS cylinder (1 mm in diameter), and the PDMS cylinder is bonded with the superelastic spring in series. The deflection or bending of the robot backbone segment is translated into an axial loading in the superelastic spring, which applies tension to the FBG; therefore, by measuring the peak wavelength shift of the FBG, the bending angle can be estimated. This paper describes the design, fabrication, and kinematic aspects of the sensor module in detail. To evaluate the proposed concept, one such sensor module has been tested and evaluated on the MINIR-II robot.

Keywords: Medical Robots and Systems, Tendon/Wire Mechanism, Soft Material Robotics
Abstract: A wide range of commonly-performed dental procedures, from operative caries removal, crown preparation, filling, to Orthodontia, could potentially benefit from robotic assistance or enhancement. Despite the wide applicability, dental robots have received far less research attention in comparison with surgical robots in general, with the vast majority of state-of-the-art dental robot systems built around commercially available industrial robotic manipulators. In this work, we propose a novel robotic manipulator system dedicated to dental applications. The proposed robot design utilizes tendon-sheath transmission, by which the electric-motor actuators could be placed away from the manipulator, resulting in substantially more compact size and lighter weight than industrial-arm-based state-of-the-art systems. The main contribution of this work is introducing a soft-robotic bracing element, which could substantially improve manipulator performance including stiffness, force capability, and accuracy. The concept, design, and fabrication aspects of the soft bracer are presented in detail in the paper. Design and system integration of the entire dental robot system are also introduced, and the performance of the system is validated using a fabricated prototype, where the benefits and unique performances of using the soft bracer are highlighted from experimental results. With compact size, excellent tool interchangeability, and fully customized towards dental procedure specifications,

Keywords: Motion and Path Planning, Deep Learning in Robotics and Automation, Autonomous Vehicle Navigation
Abstract: Ground robots which are able to navigate a variety of terrains are needed in many domains. One of the key aspects is the capability to adapt to the ground structure, which can be realized through movable body parts coming along with additional degrees of freedom (DoF). However, planning respective locomotion is challenging since suitable representations result in large state spaces. Employing an additional abstract representation - which is coarser, lower-dimensional, and semantically enriched - can support the planning.

While a desired robot representation and action set of such an abstract representation can be easily defined, the cost function requires large tuning efforts. We propose a method to represent the cost function as a CNN. Training of the network is done on generated artificial data, while it generalizes well to the abstraction of real world scenes. We further apply our method to the problem of search-based planning of hybrid driving-stepping locomotion. The abstract representation is used as a powerful informed heuristic which accelerates planning by multiple orders of magnitude.

Keywords: Motion and Path Planning, Learning and Adaptive Systems
Abstract: Path planners are generally categorised as either trajectory optimisers or sampling-based planners. The latter is the predominant planning paradigm for occupancy maps. Most trajectory optimisers require a fully defined artificial potential field for planning and cannot incorporate updates from a partially observed model such as an occupancy map. A stochastic trajectory optimiser capable of planning over occupancy map was presented in [1]. However, its scalability is limited by the cubic complexity of the Gaussian process path representation. In this work, we introduce a novel highly expressive path representation based on kernel approximation to perform trajectory optimisation over occupancy maps. This approach reduces the computational complexity to a fixed cost that only depends on the number of features. We show that stochastic sampling is crucial for planning in occupancy maps and present comparisons to other state-of-the-art planning methods, using simulated and real occupancy data. These experiments demonstrate the significant reduction in runtime, resulting in performance comparable to or better than sampling-based methods.

Keywords: Path Planning for Multiple Mobile Robots or Agents, Robust/Adaptive Control of Robotic Systems, Collision Avoidance
Abstract: Robust motion planning is a well-studied problem in the robotics literature, yet current algorithms struggle to operate scalably and safely in the presence of other moving agents, such as humans. This paper introduces a novel framework for robot navigation that accounts for high-order system dynamics and maintains safety in the presence of external disturbances, other robots, and humans. Our approach precomputes a tracking error margin for each robot, generates confidence-aware human motion predictions, and coordinates multiple robots with a sequential priority ordering, effectively enabling scalable safe trajectory planning and execution. We demonstrate our approach in hardware with two robots and two humans, and showcase scalability in a larger simulation.

Keywords: Motion and Path Planning
Abstract: Nowadays robotic systems are expected to share workspaces and collaborate with humans. In such collaborative environments, an important challenge is to ground or establish the correct semantic interpretation of a human request. Once such an interpretation is available, the request must be translated into robot motion commands in order to complete the desired task. It is not unusual that a human request cannot be grounded to a unique interpretation, thus leading to an ambiguous request. A simple example is to ask a robot to "put a cup on the table," when there are multiple cups available. In order to deal with this kind of ambiguous request, we propose a delayed or lazy variable grounding. The focus of this paper is a motion planning algorithm that, given goal regions that represent different valid groundings, lazily finds a feasible path to any one valid grounding. This algorithm includes a reward-penalty strategy, which attempts to prioritize those goal regions that seem more promising to provide a solution. We validate our approach by solving requests with multiple valid alternatives in both simulation and real-world experiments.

Keywords: Formal Methods in Robotics and Automation, Autonomous Agents, Task Planning
Abstract: This work addresses the problem of robot navigation under timed temporal specifications in workspaces cluttered with obstacles. We propose a hybrid control strategy that guarantees the accomplishment of a high-level specification expressed as a timed temporal logic formula, while preserving safety (i.e., obstacle avoidance) of the system. In particular, we utilize a motion controller that achieves safe navigation inside the workspace in predetermined time, thus allowing us to abstract the motion of the agent as a finite timed transition system among certain regions of interest. Next, we employ standard formal verification and convex optimization techniques to derive high-level timed plans that satisfy the agent's specifications. A simulation study illustrates and clarifies the proposed scheme.

Keywords: Motion and Path Planning, Deep Learning in Robotics and Automation
Abstract: We learn end-to-end point-to-point and path-following navigation behaviors that avoid moving obstacles. These policies receive noisy lidar observations and output robot linear and angular velocities. The policies are trained in small, static environments with AutoRL, an evolutionary automation layer around Reinforcement Learning (RL) that searches for a deep RL reward and neural network architecture with large-scale hyper-parameter optimization. AutoRL first finds a reward that maximizes task completion, and then finds a neural network architecture that maximizes the cumulative of the found reward. Empirical evaluations, both in simulation and on-robot, show that AutoRL policies do not suffer from the catastrophic forgetfulness that plagues many other deep reinforcement learning algorithms, generalize to new environments and moving obstacles, are robust to sensor, actuator, and localization noise, and can serve as robust building blocks for larger navigation tasks. Our path-following and point-to-point policies are respectively 23% and 26% more successful than comparison methods across new environments.

Keywords: Mobile Manipulation, Service Robots, Computer Vision for Automation
Abstract: This paper presents a holistic approach for door opening with a cartesian impedance controlled mobile robot, a KUKA KMR iiwa. Based on a given map of the environment, the robot autonomously detects the door handle, opens doors and traverses doorways without knowledge of a door model or the door’s geometry. The door handle detection uses a convolutional neural network (CNN)-based architecture to obtain the handle’s bounding box in a RGB image that works robustly for various handle shapes and colors. We achieve a detection rate of 100% for an evaluation set of 38 different door handles, by always selecting for highest confidence score. Registered depth data segmentation defines the door plane to construct a handle coordinate frame. We introduce a control structure based on the task frame formalism that uses the handle frame for reference in an outer loop for the manipulator’s impedance controller. It runs in soft real-time on an external computer with approximately 20 Hz since access to inner controller loops is not available for the KMR iiwa. With the approach proposed in this paper, the robot successfully opened and traversed for 22 out of 25 trials at five different doors.

Keywords: Probability and Statistical Methods, Autonomous Agents, Reactive and Sensor-Based Planning
Abstract: Finding sources of airborne chemicals with mobile sensing systems finds applications across the security, safety, domestic, medical, and environmental domains. In this paper, we present an algorithm based on source term estimation for odor source localization that is coupled with a navigation method based on partially observable Markov decision processes. We propose an innovative strategy to balance exploration and exploitation in navigation. The method has been evaluated systematically through high-fidelity simulations and in a wind tunnel emulating realistic and repeatable conditions. The impact of multiple algorithmic and environmental parameters has been studied in the experiments.

Keywords: Mining Robotics, Neural and Fuzzy Control, Learning from Demonstration
Abstract: This paper presents the development and testing of end-to-end Neural Network (NN) controllers for automated pile loading with a robotic wheel loader. NNs were trained using the Learning from Demonstration approach, i.e. by first recording sensor and control signals during manually-driven pile loading actions. Training made use of three input signals: boom angle, bucket angle and hydrostatic driving pressure; and three output signals: boom control, bucket control and the gas command. Most testing was conducted using NNs with 5 neurons in a single hidden layer, which were able to fill the bucket reasonably well. Qualitative comparisons were made to ascertain how the amount of training data and number of hidden neurons affects bucket filling performance, for NNs trained using both the Levenberg-Marquardt and Bayesian Regularization backpropagation algorithms. Different NNs trained with the same data were also compared. An additional pile transfer experiment compared the performance of an NN controller with a heuristic automated controller and manual human control. By estimating the total volume of material transferred using 3D laser scans, human control was found to have the highest performance, though the NN outperformed the heuristic controller. This indicated that end-to-end NN control trained by demonstration could offer improvement over current heuristic methods for automated pile loading.

Keywords: Field Robots, Wheeled Robots, Hydraulic/Pneumatic Actuators
Abstract: This paper proposes a novel configurable wheel that exhibits desired properties of varied radius wheels. Positional manipulation of the centre hub is proposed and tested to achieve these desired characteristics of `virtual' wheels in a physical system. The centre hub is manipulated via the use of pneumatic actuators mounted to and constricted by the outer rim of the wheel, which allows for fast and accurate control to enable the vehicle ride height and wheel gear ratios to be adjusted continuously and be maintained during the wheels' full rotation. Experiments are presented, validating this ability of the system. We envision uses for this system to extend from off-road robotics to space exploration as these wheels exhibit novel characteristics not demonstrated by other platforms.

Keywords: Mining Robotics, Robotics in Construction, Field Robots
Abstract: A new approach to autonomous excavator control that allows the machine to adapt to unknown soil properties is presented. Unlike traditional force control or trajectory control, the new method uses the product of force and velocity, namely, the power transmitted from the excavator to the soil, as a signal for adaptive excavation. Using an extremum-seeking algorithm, an optimal excavation condition where the force and velocity at the bucket take a particular combination that maximizes the output power of the machine is sought and maintained. Under this condition, the system finds the optimal depth of digging by controlling the boom of the excavator. Also under this condition, the output impedance of the excavator matches the impedance of the load and, thereby, transmits the maximum power from the machine to the soil. Theoretical analysis proves that an optimal combination of force and velocity exists and is unique under mild assumptions. An extremum-seeking algorithm using recursive least squares is developed for maximizing the output power. The method is implemented on a small-scale prototype system where torque motors emulate nonlinear force-speed characteristics of hydraulic actuators. Experiments demonstrate that the prototype can execute excavation tasks adaptively against varying soil properties and terrain profile.

Keywords: Mechanism Design, Environment Monitoring and Management
Abstract: This paper presents the SlothBot, a wire-traversing robot envisioned for long-term environmental monitoring applications. The SlothBot is a solar-powered, slow-paced, energy-efficient robot—hence its name—capable of moving on a mesh of wires by switching between branching wires. Unlike ground mobile robots or aerial robots employed in environmental monitoring applications, the use of wire-traversing robots allows for longer-term deployment because of the significantly lower energy consumption. Wire-traversing, coupled with the use of solar panels, facilitates the self-sustainability of the SlothBot. Locomotion and wire-switching maneuvers are performed in a fail-safe fashion, inasmuch the robot is always firmly attached to the wires, even when switching between branching wires. This is achieved by employing a two-body structure featuring an actuated decoupling mechanism. In this paper we show the design and the motion control of the SlothBot, together with the results of long-term monitoring experiments.

Keywords: Path Planning for Multiple Mobile Robots or Agents, Multi-Robot Systems, Networked Robots
Abstract: We consider the problem of feasible coordination control for multiple homogeneous or heterogeneous mobile vehicles subject to various constraints (nonholonomic motion constraints, holonomic coordination constraints, equality/inequality constraints etc). We develop a general framework involving differential-algebraic equations and viability theory to describe and determine coordination feasibility for a coordinated motion control under heterogeneous vehicle dynamics and various constraints. A heuristic algorithm is proposed for generating feasible trajectories for each individual vehicle. We show several application examples and simulation experiments on multi-vehicle coordination under various constraints to validate the theory and the effectiveness of the proposed algorithm and control schemes.

Keywords: Path Planning for Multiple Mobile Robots or Agents, Multi-Robot Systems, Planning, Scheduling and Coordination
Abstract: Multirobot coverage is the problem of planning paths for several identical robots such that the combined regions traced out by the robots completely cover their environment. We consider the problem of multirobot coverage with the objective of minimizing the mission time, which depends on the number of turns taken by the robots. To solve this problem, we first partition the environment into ranks which are long thin rectangles the width of the robot's coverage tool. Our novel partitioning heuristic produces a set of ranks which minimizes the number of turns. Next, we solve a variant of the multiple travelling salesperson problem (m-TSP) on the set of ranks to minimize the robots' mission time. The resulting coverage plan is guaranteed to cover the entire environment. We present coverage plans for a robotic vacuum using real maps of 25 indoor environments and compare the solutions to paths planned without the objective of minimizing turns. Turn minimization reduced the number of turns by 6.7% and coverage time by 3.8% on average for teams of 1--5 robots.

Keywords: Path Planning for Multiple Mobile Robots or Agents, Planning, Scheduling and Coordination
Abstract: In this work, we consider the problem of online centralized kinodynamic multi-robot replanning (from potentially non-stationary initial states) and coordination in known and cluttered workspaces. Offline state lattice reachability analysis is leveraged to decouple the planning problem into two sequential graph searches---one in the explicit geometric graph of the environment and the other in the graph of the higher-order derivatives of the robot's state---in a manner such that the intermediate vertices of a safe set of geometric paths are guaranteed to have a feasible assignment of higher-order derivatives. Without additional iterative refinement procedures, the resulting time parameterized polynomial trajectories are dynamically feasible and collision-free. Planning results with up to 20 robots in two and three dimensional workspaces suggest the suitability of the proposed approach for multi-robot replanning in known environments.

Keywords: Path Planning for Multiple Mobile Robots or Agents, Collision Avoidance, Motion and Path Planning
Abstract: Safe autonomous navigation of micro air vehicles in cluttered dynamic environments is challenging due to the uncertainties arising from robot localization, sensing and motion disturbances. This paper presents a probabilistic collision avoidance method for navigation among other robots and moving obstacles, such as humans. The approach explicitly considers the collision probability between each robot and obstacle and formulates a chance constrained nonlinear model predictive control problem (CCNMPC). A tight bound for approximation of collision probability is developed which makes the CCNMPC formulation tractable and solvable in real time. For multi-robot coordination we describe three approaches, one distributed without communication (constant velocity assumption), one distributed with communication (of previous plans) and one centralized (sequential planning). We evaluate the proposed method in experiments with two quadrotors sharing the space with two humans and verify the multi-robot coordination strategy in simulation with up to sixteen quadrotors.

Keywords: Path Planning for Multiple Mobile Robots or Agents, Deep Learning in Robotics and Automation, Distributed Robot Systems
Abstract: Multi-agent path finding (MAPF) is an essential component of many large-scale, real-world robot deployments, from aerial swarms to warehouse automation. However, despite the community's continued efforts, most state-of-the-art MAPF planners still rely on centralized planning and scale poorly past a few hundred agents. Such planning approaches are maladapted to real-world deployments, where noise and uncertainty often require paths be recomputed online, which is impossible when planning times are in seconds to minutes. We present PRIMAL, a novel framework for MAPF that combines reinforcement and imitation learning to teach fully-decentralized policies, where agents reactively plan paths online in a partially-observable world while exhibiting implicit coordination. This framework extends our previous work on distributed learning of collaborative policies by introducing demonstrations of an expert MAPF planner during training, as well as careful reward shaping and environment sampling. Once learned, the resulting policy can be copied onto any number of agents and naturally scales to different team sizes and world dimensions. We present results on randomized worlds with up to 1024 agents and compare success rates against state-of-the-art MAPF planners. Finally, we experimentally validate the learned policies in a hybrid simulation of a factory mockup, involving both real-world and simulated robots.

Keywords: Motion and Path Planning
Abstract: This paper combines sampling-based motion planning with multi-agent search to efficiently solve challenging multi-robot motion-planning problems with dynamics. This idea has shown promise in prior work which developed a centralized approach to expand a motion tree in the composite state space of all the robots along routes obtained by multi-agent search over a discrete abstraction. Still, the centralized expansion imposes a significant bottleneck due to the curse of dimensionality associated with the high-dimensional composite state space.

To improve efficiency and scalability, we propose a coordinated expansion of the motion tree along routes obtained by the multi-agent search. We first develop a single-robot sampling-based approach to closely follow a given route. The salient aspect of the proposed coordinated expansion is to invoke the route follower one robot at a time, ensuring that robot i follows route_i while avoiding not only the obstacles but also robots 1, ..., i-1. In the next iteration, the motion tree could be expanded from another state along other routes. This enables the approach to progress rapidly and achieve significant speedups over a centralized approach.

Keywords: Multi-Robot Systems, Task Planning, Planning, Scheduling and Coordination
Abstract: Multi-robot systems are deployed in a warehouse to automate the process of storing and retrieving objects in and out of the warehouse. The efficiency of the system largely depends on how the tasks are allocated to the robots. Though there exists a number of techniques that can perform multi-robot task allocation quite efficiently, they hardly consider deadline for task completion while assigning tasks to the robots. A careful allocation is of paramount importance when there is an associated penalty with each of the tasks if it is not completed within a stipulated time. In this work, we develop an algorithm, called Minimum Penalty Scheduling (MPS) that allocates tasks among a group of robots with the goal that the overall penalty of executing all the tasks can be minimized. Our algorithm provides a robust, scalable, and near-optimal real-time task schedule. By comparing with the state-of-the-art algorithm, we show that MPS attracts up to 62.5% less penalty when a significant number of tasks are bound to miss the deadline. Additionally, MPS is also suitable for real-time multi-processor scheduling since it schedules a higher number of tasks within their deadline.

Keywords: Multi-Robot Systems, Distributed Robot Systems, Virtual Reality and Interfaces
Abstract: We present an augmented reality human-swarm interface that combines two modalities of interaction: environment-oriented and robot-oriented. The environment-oriented modality allows the user to modify the environment (either virtual or physical) to indicate a goal to attain for the robot swarm. The robot-oriented modality makes it possible to select individual robots to reassign them to other tasks to increase performance or remedy failures. Previous research has concluded that environment-oriented interaction might prove more difficult to grasp for untrained users. In this paper, we report a user study which indicates that, at least in collective transport, environment-oriented interaction is more effective than purely robot-oriented interaction, and that the two combined achieve remarkable efficacy.

Keywords: Factory Automation, Industrial Robots, Multi-Robot Systems
Abstract: In this paper, we present a fully-integrated end-effector positioning system for large-scale multi-robotic setups used for non-repetitive manufacturing tasks. The system provides static and dynamic correction of the end-effector pose using an external pose tracking system. It consists of multiple modules which extend the capabilities of the conventional robot setup and fundamentally improve its usability and efficiency, since the user can easily set up, execute and monitor the manufacturing tasks in a universal reference frame. To increase the performance of closed-loop control of the end-effector pose, a sensor fusion algorithm is implemented for fusing the data of the tracking system iGPS with an IMU. Experiments are carried out which show a reduction of the average error down to 0.11 mm for the static correction, a significant increase of the measurement quality of the tracking system with the sensor fusion and a path error below 0.5 mm for the dynamic correction. The presented correction system enables new applications in digital building construction which require high accuracy target poses spread through a large workspace of cooperating robots.

Keywords: Cooperating Robots, Swarms, Multi-Robot Systems
Abstract: We propose a combined method for the collaborative transportation of a suspended payload by a team of rotorcraft. A recent distance-based formation-motion control algorithm based on assigning distance disagreements among robots generates the acceleration signals to be tracked by the vehicles. In particular, the proposed method does not need global positions nor tracking prescribed trajectories for the motion of the members of the team. The acceleration signals are followed accurately by an Incremental Nonlinear Dynamic Inversion controller designed for rotorcraft that measures and resists the tensions from the payload. Our approach allows us to analyze the involved accelerations and forces in the system so that we can calculate the worst case conditions explicitly to guarantee a nominal performance, provided that the payload starts at rest in the 2D centroid of the formation, and it is not under significant disturbances. For example, we can calculate the maximum safe deformation of the team with respect to its desired shape. We demonstrate our method with a team of four rotorcraft carrying a suspended object two times heavier than the maximum payload for an individual. Last but not least, our proposed algorithm is available for the community in the open-source autopilot Paparazzi.

Keywords: Dynamics, Kinematics, Multi-Robot Systems
Abstract: This paper addresses the circular formation and concentric formation stabilization problem of kinematic unicycles. We design distributed control laws driving unicycles to converge to a common circle at the first stage and a velocity control law enabling unicycles to achieve a specific formation on the circle at the second stage. We also achieve the concentric formation by dividing unicycles into groups and design distributed control laws reinforcing each group at a desired circular orbit from the stationary center. We provide analysis to show that both the circular and concentric formations are asymptotically stable using set stabilization theory. Typical examples are selected to demonstrate and support the theoretical results.

Keywords: Motion Control, Autonomous Vehicle Navigation, Multi-Robot Systems
Abstract: This paper formally constructs navigation functions with time-varying destinations on star worlds. The construction is based on appropriate diffeomorphic transformations and extends an earlier sphere-world formulation. A new obstacle modeling method is also introduced, reducing analytical complexity and offering unified expressions of common classes of n-dimensional obstacles. The method allows for dynamic target tracking and is validated through simulations and experiments.

Keywords: Field Robots, Telerobotics and Teleoperation, Mechanism Design
Abstract: Robotic platforms dedicated to powerline inspection are often complex to operate, take several minutes to cross any obstacle, and must be operated by highly trained specialists. To further its goal of massive inspection of its power grid, Hydro-Québec developed an innovative robot that is simple to operate and can be used directly by line maintenance technicians. LineRanger was developed following the field deployment of LineROVer and LineScout but aims at surpassing them in terms of inspection efficiency. With an ingenious and passive obstacle-crossing system, this new robot allows large-scale inspection of bundled-type powerlines, since the obstacle crossing time is considerably reduced. In this paper, details on the robot’s key features are presented along with its mathematical analysis, which guarantees its stability on flexible bundles and directly influenced the design. Finally, the LineRanger prototype is presented, with insights about its first field deployments.

Keywords: Mechanism Design, Kinematics, Computational Geometry
Abstract: Recent work in the design of mechanical systems for terrestrial locomotion has indicated successful strategies for increasing the energetic performance of a robotic locomotor without upgrading its actuator system. We apply one such strategy, termed power modulation, in a new way: for the design of a leg mechanism useful for running. Power modulation geometrically defines force/torque ratios between robot components to mechanically achieve certain energy transmission characteristics during fast stance dynamics that increase the kinetic power output of the overall system. This attribute should be useful for a running robot by extending the range of available footholds that can be accessed in a single step. To find a suitable leg mechanism, we leverage the Finite Root Generation to compute a design. The design is advanced to a prototype and basic experiments are conducted to investigate its behavior as an implementation of power modulation and adjusted into a low-power mode.

Keywords: Mechanism Design, Aerial Systems: Applications, Search and Rescue Robots
Abstract: Aerial robotics is a fast-growing field of robotics and has been successfully used in various applications. However, similar to other areas of robotics, many challenges remain, such as dealing with unavoidable obstacle in a cluttered environment. A few years ago, a flying robot with a protective shell that can passively rotate was introduced. However, such a system also has some limitations. Because of the passive rotation of the protective shell, the ability to physically interact outside the shell is limited, and the onboard camera and other remote sensors are constantly obstructed. In this study, a new idea is introduced in response to the limitations of the previous system while retaining the protective shell and maintaining some degree of passive rotation of the shell. It is proposed to position two passive rotating hemispherical shells in each rotor to directly protect the propeller. This paper presents the concept, discusses the design and proof of concept, and validates the concept through experiments. Various experiments demonstrate the capabilities of the proposed flying robot, and resolution of the problem of physical interaction and camera obstruction, and the introduction of new advantages.

Keywords: Biological Cell Manipulation, Automation at Micro-Nano Scales
Abstract: Robotic manipulation of deformable objects (vs. rigid objects) has been a classic topic in robotics. Compared to deformable synthetic objects such as rubber balls and clothes, biological cells are highly deformable and more prone to damage. This paper presents robotic manipulation of deformable cells for orientation control (both out-of-plane and in-plane), which is required in both clinical (e.g., in vitro fertilization) and biomedical (e.g., clone) applications. Compared to manual cell rotation based on empirical experience, the robotic approach, based on mathematical modeling and path planning, effectively rotates a cell while consistently maintaining minimal cell deformation to avoid cell damage. A force model is established to determine the minimal force applied by the micropipette to rotate a spherical or more generally, an ellipsoidal mouse oocyte. The force information is translated into indentation through a contact mechanics model, and the manipulation path of the micropipette is formed by connecting the indentation positions on the oocyte. A compensation controller is designed to compensate for the variations of mechanical properties across cells. The polar body of an oocyte is detected by deep neural networks with robustness to shape and size differences. Experimental results demonstrate that the system achieved an accuracy of 97.6% in polar body detection and an accuracy of 0.7 degree in oocyte orientation control with maximum oocyte deformation of 2.69 um.

Keywords: Manipulation Planning, Factory Automation, Perception for Grasping and Manipulation
Abstract: Advances in sensor technologies, object detection algorithms, planning frameworks and hardware designs have motivated the deployment of robots in warehouse automation. A variety of such applications, like order fulfillment or packing tasks, require picking objects from unstructured piles and carefully arranging them in bins or containers. Desirable solutions need to be low-cost, easily deployable and controllable, making minimalistic hardware choices desirable. The challenge in designing an effective solution to this problem relates to appropriately integrating multiple components, so as to achieve a robust pipeline that minimizes failure conditions. The current work proposes a complete pipeline for solving such packing tasks, given access only to RGB-D data and a single robot arm with a minimalistic, vacuum-based end-effector. To achieve the desired level of robustness, three key manipulation primitives are identified, which take advantage of the environment and simple operations to successfully pack multiple cubic objects. The overall approach is demonstrated to be robust to execution and perception errors. The impact of each manipulation primitive is evaluated by considering different versions of the proposed pipeline that incrementally introduce reasoning about object poses and corrective manipulation actions.

Keywords: Micro/Nano Robots, Dexterous Manipulation, Automation at Micro-Nano Scales
Abstract: Precise and dexterous handling of micrometer to millimeter-scale objects are the two key and challenging factors for mincromanipualtion, especially in the fields of biotechnology where delicate microcomponents can be easily damaged by contact during handling. Many complex microrobotic techniques, scaling from fully autonomous to teleoperated, have been developed to address the limitations individually. However, a scalable, reliable, and versatile method which can be applied to a wide range of applications is not present. This work uniquely combines the advantages of magnetic and acoustic micromanipulation methods to achieve three-dimensional, contactless, and semi-autonomous micromanipulation, with potential for full automation, for use in microassembly applications. Solid and liquid materials, with sizes less than 3 mm (down to 300 m), are handled in a cylindrical workspace of 30 mm in height and 4 mm in diameter using acoustic levitation while an externally applied magnetic field controls the orientation of magnetically active components. A maximum vertical positioning RMSE of 1.5% of parts length was observed. This paper presents the concept, design, characterization, and modeling of the new method, along with a demonstration of a typical assembly process.

Keywords: Wheeled Robots
Abstract: Ryan Gariepy is the CTO and co-founder of Clearpath Robotics and OTTO Motors, because if one startup isn't stressful enough, why not run two? He completed both a B.A.Sc. degree in Mechatronics Engineering and a M.A.Sc. degree in Mechanical Engineering at the University of Waterloo, and has over three dozen pending patents in the field of intelligent systems. He worked at a pre-acquisition Kiva Systems, as well as a pre-product Aeryon Labs. He has spent his professional career working to make autonomous systems ubiquitous, whether that is via the rapidly growing OTTO Motors product line, the Clearpath Robotics support of the global robotics community, or the co-organization of eight consecutive ROSCons. He is on the board of directors for the Open Source Robotics Foundation, Next Generation Manufacturing Canada, and the NSERC Canadian Robotics Network, and is an advisor for several startups and venture capital groups. He has filled almost every role in a robotics startup possible, most of them with very little warning.

Keywords: Simulation and Animation
Abstract: Demetri Terzopoulos is a Chancellor's Professor of Computer Science at the University of California, Los Angeles, where he holds the rank of Distinguished Professor and directs the UCLA Computer Graphics & Vision Laboratory. He is also Co-Founder and Chief Scientist of VoxelCloud, Inc., a multinational company that applies AI to healthcare. He graduated from McGill University and received his PhD degree ('84) in Artificial Intelligence from MIT. He is or was a Guggenheim Fellow, a Fellow of the ACM, a Fellow of the IEEE, a Fellow of the Royal Society of London, a Fellow of the Royal Society of Canada, a member of the European Academy of Sciences and the New York Academy of Sciences, and a life member of Sigma Xi. His many awards include an Academy Award for Technical Achievement from the Academy of Motion Picture Arts and Sciences for his pioneering work on physics-based computer animation, and the inaugural Computer Vision Distinguished Researcher Award from the IEEE for his pioneering and sustained research on deformable models and their applications. ISI and other indexes list him among the most highly-cited authors in engineering and computer science, with more than 400 published research papers and several volumes, primarily in computer graphics, computer vision, medical imaging, computer-aided design, and artificial intelligence/life.

Keywords: Robust/Adaptive Control of Robotic Systems, Motion Control, Redundant Robots
Abstract: Tracking multiple prioritized tasks simultaneously with redundant robots have been investigated extensively over the last decades. Recent research focuses on combining advantages from both classical soft and strict prioritization schemes which is non-trivial. Among the proposed methods to tackle this issue, Generalized Hierarchical Control (GHC) seems to have a reasonable performance, however, it does not include a weighting matrix in the computation of the nullspace projection operator and hence cannot construct dynamically-consistent stack-of-tasks hierarchies as a special case. We extend GHC by adding dynamic-consistency to the control scheme and refer to it as DynGHC. The extension is also advantageous when choosing non-strict priorities because inertia coupling between tasks is reduced. DynGHC allows to smoothly rearrange priorities which is important for robots acting in dynamically changing contexts. Comparative simulations with a 4~DOF planar manipulator and a KUKA LWR validate our approach. Matlab and C++ source code is made available.

Keywords: Biomimetics, Neurorobotics, Motion Control
Abstract: The control of human hands and fingers represents one of the most complex functions of the motor cortex. In order to implement anthropomorphic hands that mimic accurately the motion ability of the human hands, the basic biological mechanisms of the natural muscle control should be modeled. This paper presents the design of a significantly improved control system based on analogue neural networks that can be used to replicate the biological control mechanisms of the natural muscles. In order to demonstrate the proposed concept, experiments were performed using a single-joint robotic arm that can be flexed as the human elbow by an artificial muscle connected as the biceps. To bring more biological plausibility to the robotic arm, the artificial muscle is implemented using a shape memory alloy wire which actuates by contraction as the natural muscles. Moreover, the contraction force of the actuator wire is directly determined by the spiking frequency of the electronic neurons as the motor neurons determines the contraction strength of the natural muscles. The experimental results that validate the control method show that using excitatory neurons and several inhibitory neurons unevenly distributed on the inputs of the artificial motor neurons that drive the shape memory alloy actuator, the spiking neural network is able to control with high precision the rotation of the arm mobile lever to random target positions even if the arm is slightly loaded.

Keywords: Robust/Adaptive Control of Robotic Systems
Abstract: The inverted pendulum is by nature a dynamically unstable system and may be subjected to severe disturbances due to its environmental or loading conditions. This paper formulates a design for a nonlinear controller to balance a two-wheeled mobile robot (TWMR) based on Model Reference Adaptive Control. The proposed solution overcomes the limitations of control systems that rely on fixed parameter controllers. Given the nonlinear single-input multi-output (SIMO) nature of the TWMR platform, the proposed adaptive controller can handle non-linearities without the need for linearization, and inherently dealing with SIMO systems. By studying the influence that hidden dynamic effects can cause, we show the preference of the proposed controller over other designs. Simulation results demonstrate the applicability and efficiency of our proposed design, and experimental results validate the effectiveness of the proposed scheme in guaranteeing asymptotic output tracking, even in the presence of unknown disturbances.

Keywords: Robust/Adaptive Control of Robotic Systems, Dynamics, Industrial Robots
Abstract: This paper presents a robust controller for uncertain robot manipulators subject to disturbances which are composed of sinusoids. The controller employs the disturbance observer based controller which can effectively estimate and compensate the effect of plant uncertainties and the disturbances. Assuming that the frequencies of sinusoids are known, we embed the internal model of disturbances into the proposed controller so that the design parameters of the controller can be chosen without using the magnitude of disturbance or its time derivative. A rigorous stability analysis shows that the closed-loop system under the proposed controller behaves like the nominal closed-loop system free of disturbances. Simulation results for a 2-DOF manipulator show the effectiveness of the proposed controller.

Keywords: Robust/Adaptive Control of Robotic Systems, Optimization and Optimal Control, Wheeled Robots
Abstract: The control of field robots in varying and uncertain terrain conditions presents a challenge for autonomous navigation. Online estimation of the wheel-terrain slip characteristics is essential for generating the accurate control predictions necessary for tracking trajectories in off-road environments. Receding horizon estimation (RHE) provides a powerful framework for constrained estimation, and when combined with receding horizon control (RHC), yields an adaptive optimisation-based control method. Presently, such methods assume slip to be constant over the estimation horizon, while our proposed structured blocking approach relaxes this assumption, resulting in improved state and parameter estimation. We demonstrate and compare the performance of this method in simulation, and propose an overlapping-block strategy to ameliorate some of the limitations encountered in applying noise-blocking in a receding horizon estimation and control (RHEC) context.

Keywords: Tendon/Wire Mechanism, Multifingered Hands
Abstract: In contrast to underactuated robotic hands the DLR AWIWI II hand of the David robot is fully controllable because each finger with 4 joints is actuated by 6 or 8 tendons respectively. For such fingers all joint angles (generalized positions) or joint torques (generalized forces) can be controlled independently. Usually, the specifications in joint space are converted to desired tendon forces or motor torques, which are regulated by an inner loop impedance controller. However, this conversion typically exhibits couplings between the components of the joint angle vector or the joint torque vector respectively, which arise when using the well known equations. Therefore the usual force control and position control schemes are reviewed and a generic computation of the desired tendon forces is presented. This is also done for the control of the Cartesian position and force at the finger endpoint. Thus the main contribution of the paper is the inhibition of couplings in joint space or at the Cartesian endpoint. This is demonstrated in simulations of the index finger of the DLR David hand.

Keywords: Deep Learning in Robotics and Automation, Autonomous Vehicle Navigation, Sensor Fusion
Abstract: We propose a reconfigurable network for efficient inference dedicated to autonomous platforms equipped with multiple perception sensors. The size of the network for steering autonomous platforms grows proportionally to the number of installed sensors eventually preventing the usage of multiple sensors in real-time applications due to an inefficient inference. Our approach hinges on the observation that multiple sensors provide a large stream of data, where only a fraction of the data is relevant for the performed task at any given moment in time. The architecture of the reconfigurable network that we propose contains separate feature extractors, called experts, for each sensor. The decisive block of our model is the gating network, which online decides which sensor provides the data that is most relevant for driving. It then reconfigures the network by activating only the relevant expert corresponding to that sensor and deactivating the remaining ones. As a consequence, the model never extracts features from data that are irrelevant for driving. The gating network takes the data from all inputs and thus to avoid explosion of computation time and memory space it has to be realized as a small and shallow network. We verify our model on the unmanned ground vehicle (UGV) comprising of the 1/6 scale remote control truck equipped with three cameras. We demonstrate that the reconfigurable network correctly chooses experts in real-time allowing the reduction of computations cost for

Keywords: Deep Learning in Robotics and Automation, Autonomous Vehicle Navigation, Object Detection, Segmentation and Categorization
Abstract: This paper is about fast motion estimation with scanning radar. We use weak supervision to train a focus of attention policy which actively down-samples the measurement stream before data association steps are undertaken. At training, we avoid laborious manual labelling by exploiting short-term sensor coherence from multiple poses in the presence of an external ego-motion estimator (for example, wheel odometry). In this way, we generate copious annotated measurements which can be used for training a learning algorithm in a weakly-supervised fashion. We demonstrate the validity of the approach in the context of a Radar Odometry (RO) task, pre-filtering raw data with a popular image segmentation network trained as presented. We evaluate our system against 26km of data collected in Central Oxford and show consistent motion estimation with greatly reduced radar processing times (by a factor of 2.36).

Keywords: Deep Learning in Robotics and Automation, Motion and Path Planning, Autonomous Vehicle Navigation
Abstract: We demonstrate an autonomous ground robot capable of exploring unknown indoor environments for reconstructing their 2D maps. This problem has been traditionally tackled by geometric heuristics and information theory. More recently, deep learning and reinforcement learning based approaches have been proposed to learn exploration behavior in an end-to-end manner. We present a method that combines the strengths of these different approaches. Specifically, we employ a state-of-the-art generative neural network to predict unknown regions of a partially explored map, and use the prediction to enhance the exploration in an information-theoretic manner. We evaluate our system in simulation using floor plans of real buildings. We also present comparisons with traditional methods which demonstrate the advantage of our method in terms of exploration efficiency. We retain an advantage over end-to-end learned exploration methods in that the robot's behavior is easily explicable in terms of the predicted map.

Keywords: Deep Learning in Robotics and Automation, Model Learning for Control, Learning and Adaptive Systems
Abstract: There has been an increasing interest in learning dynamics simulators for model-based control. Compared with off-the-shelf physics engines, a learnable simulator can quickly adapt to unseen objects, scenes, and tasks. However, existing models like interaction networks only work for fully observable systems; they also only consider pairwise interactions within a single time step, both restricting their use in practical systems. We introduce Propagation Networks (PropNet), a differentiable, learnable dynamics model that handles partially observable scenarios and enables instantaneous propagation of signals beyond pairwise interactions. With these innovations, our propagation networks not only outperform current learnable physics engines in forward simulation, but also achieves superior performance on various control tasks. Compared with existing deep reinforcement learning algorithms, model-based control with propagation networks is more accurate, efficient, and generalizable to novel, partially observable scenes and tasks.

Keywords: Deep Learning in Robotics and Automation, Autonomous Vehicle Navigation, Intelligent Transportation Systems
Abstract: Interactive driving is challenging but essential for autonomous cars in dense traffic or urban areas. Proper interaction requires understanding and prediction of future trajectories of all neighboring cars around a target vehicle. Current solutions typically assume a certain distribution or stochastic process to approximate human-driven cars' behaviors. To relax this assumption, a Recurrent Meta Induction Network (RMIN) framework is developed. The original Conditional Neural Process (CNP) on which this is based does not consider the sequence of the conditions, due to the permutation invariance requirements for stochastic processes. However, the sequential information is important for the driving behavior estimation. Therefore, in the proposed method, a recurrent neural cell replaces the original demonstration sub-net. The behavior estimation is conditioned on the historical observations for all related cars, including the target car and its surrounding cars. The method is applied to predict the lane change trajectory of a target car in dense traffic areas. The proposed method achieves better results than previous methods and thanks to the meta-learning framework, it can use a smaller dataset, putting fewer demands on autonomous driving data collection.

Keywords: Deep Learning in Robotics and Automation, Autonomous Agents, Perception for Grasping and Manipulation
Abstract: Enabling autonomous robots to interact in unstructured environments with dynamic objects requires manipulation capabilities that can deal with clutter, changes, and objects’ variability. This paper presents a comparison of different reinforcement learning-based approaches for object picking with a robotic manipulator. We learn closed-loop policies mapping depth camera inputs to motion commands and compare different approaches to keep the problem tractable, including reward shaping, curriculum learning and using a policy pre-trained on a task with a reduced action set to warm-start the full problem. For efficient and more flexible data collection, we train in simulation and transfer the policies to a real robot. We show that using curriculum learning, policies learned with a sparse reward formulation can be trained at similar rates as with a shaped reward. These policies result in success rates comparable to the policy initialized on the simplified task. We could successfully transfer these policies to the real robot with only minor modifications of the depth image filtering. We found that using a heuristic to warm-start the training was useful to enforce desired behavior, while the policies trained from scratch using a curriculum learned better to cope with unseen scenarios where objects are removed.

Keywords: Mechanism Design, Motion Control of Manipulators
Abstract: Fluidic transmission mechanisms use fluids to transmit force through conduits. We previously presented a transmission mechanism called solid-media transmission (SMT), which uses conduits filled with spheres and spacers for push-only bidirectional transmission. In this paper, we present new designs of SMT-actuated one-degree-of-freedom (DoF) and two-degree-of-freedom positioning manipulators, and report experimental studies to assess their performance. In these studies, closed-loop position control was performed with a PI controller and/or master-slave control. With braided PTFE tubing, SMT exhibited sub-millimeter accuracy, with a tolerance of ±0.05mm for the tested transmission lines with lengths up to 4m.

Keywords: Tendon/Wire Mechanism, Mechanism Design, Redundant Robots
Abstract: The decommissioning of the Fukushima Daiichi Nuclear Power Plants is a national urgent problem in Japan. The distribution and characteristics of the fuel debris inside the nuclear reactor must be investigated to safely retrieve them. This study describes a 10 m-long articulated manipulator for investigation inside the primary container vessel. We employed a coupled tendon-driven mechanism and a gravity compensation mechanism using synthetic fiber ropes to design a lightweight and slender articulated manipulator. After discussing the basic principle and control algorithm, we focus on the detailed mechanical design of a prototype model. We confirmed its feasibility through basic motion experiments.

Keywords: Mechanism Design, Mobile Manipulation, Compliant Joint/Mechanism
Abstract: Robotic grasping can enable mobile vehicles to physically interact with objects for delivery, repositioning, or landing. However, the requirements for grippers on mobile vehicles differ substantially from those used for conventional manipulation. Specifically, grippers for dynamic mobile robots should provide rapid activation, high force density, low power consumption, and minimal computation. In this work, we present a biologically-inspired robotic gripper designed specifically for mobile platforms. This design exploits a bistable shell to achieve “reflexive” activation based on contact with the environment. The mechanism can close its grasp within 0.12s without any sensing or control. Electrical input power is not required for grasping or holding load. The reflexive gripper utilizes a novel pneumatic design to open its grasp with low power, and the gripper can carry slung loads up to 28 times its weight. This new mechanism, including the kinematics, static behavior, control structure, and fabrication, is described in detail. A proof of concept prototype is designed, built, and tested. Experimental results are used to characterize performance and demonstrate the potential of this new approach.

Keywords: Mechanism Design, Biologically-Inspired Robots, Compliant Joint/Mechanism
Abstract: Small aerial robots usually face a common challenge that they can only fly for a short time due to their limited onboard energy supply. To tackle this issue, one promising solution is to endow flying robots with perching capability so that they can perch or land on walls, trees, or power lines to rest or recharge. Such perching capability is especially useful for monitoring-related tasks since the robot can maintain a desired height for monitoring without flying. One of the major challenges for perching is to design a light-weight and energy-efficient perching mechanism. In this paper, we propose a 3D-printed compliant bistable gripper which is easy to close, stable to hold, and easy to adjust for a palm-size quadcopter to perch on cylindrical objects. If installed on the bottom of aerial robots, it can also be used for aerial grasping. The proposed gripper can be directly activated by the contact velocity to switch from open state to closed state. With a required force to open the gripper larger than the robot weight, the gripper can hold the quadcopter safely. We analyze the required forces for closing and opening to provide design guidelines for the mechanism. Experimental results show that the designed gripper can successfully make the quadcopter to perch on cylinders as well as grasp objects.

Keywords: Hydraulic/Pneumatic Actuators, Compliant Joint/Mechanism, Force Control
Abstract: This paper describes our novel hydraulic circuit, referred to as the Hydraulic Hybrid Servo Booster (H2SB), and its application to hydraulic manipulator. The circuit embeds a servomotor-controlled pump into a valve bridge so that the high-speed position can be achieved in a hybrid, cost-effective, and precise manner. This paper focuses on the precise manipulation of heavy-load and the compliant joint torque control using the boost mode. The main obstacles includes: (1) pressure difference caused by area differences of the single rod cylinder, (2) quick changes of the inertial load due to the manipulator and load dynamics, (3) limited response and precision of the low-cost cartridge valves, (4) limited output flow of the small servo-pump. All these factors lead to overpressure. We propose a model-based compensation scheme to mitigate the overpressure. This method comprises: (1) nonlinear flow map of the valves, (2) relief control based on the estimated flow and pressure of the servo-pump. The effectiveness is validated through the joint position and torque control experiments on our hydraulic manipulator prototype.

Keywords: Mechanism Design, Kinematics, Surgical Robotics: Steerable Catheters/Needles
Abstract: One of the key design parameters in tendon-driven continuum robots is the number of tendons and the tendon loading distribution. A load model is also helpful for avoiding slack in tendons that causes control inefficiency and inaccuracy. A quasi-static model of n-tendon continuum robots is derived using the Euler-Lagrange formulation. The model is employed to derive an analytical loading model for equidistant tendon tensions for any given beam configuration within workspace. The model accounts for the bending and axial compliance of the manipulator as well as tendon compliance. Features of the proposed model are discussed and some of the potential application are explained. Based on the proposed model, a slack avoidance algorithm with analytical formulation is developed to dynamically optimize the tendon loads while preventing slack in tendons for a given configuration. The proposed model is experimentally validated in a multi-tendon continuum robot system for four case studies of 3- to 6-tendon arrangements in open-loop control architecture. A stereo vision-based 3D reconstruction system measures the beam configuration and properties for each of the 3- to 6-tendon continuum robots. The effect of number of tendons on the tension loads in n-tendon continuum robots is studied. A quantitative dimensionless relationship between the number of tendons, the maximum tendon loads and the bending angles is developed that may be used as a design tool for trade-off among the complexit

Keywords: SLAM, Localization, Mapping
Abstract: A novel nonlinear incremental optimization algorithm MH-iSAM2 is developed to handle ambiguity in simultaneous localization and mapping (SLAM) problems in a multi-hypothesis fashion. It can output multiple possible solutions for each variable according to the ambiguous inputs, which is expected to greatly enhance the robustness of autonomous systems as a whole. The algorithm consists of two data structures: an extension of the original Bayes tree that allows efficient multi-hypothesis inference, and a Hypo-tree that is designed to explicitly track and associate the hypotheses of each variable as well as all the inference processes for optimization. With our proposed hypothesis pruning strategy, MH-iSAM2 enables fast optimization and avoids the exponential growth of hypotheses. We evaluate MH-iSAM2 using both simulated datasets and real-world experiments, demonstrating its improvements on the robustness and accuracy of SLAM systems.

Keywords: SLAM, Localization
Abstract: Motivated by the need to improve the performance of visual loop closure verification via multi-view geometry (MVG) under significant illumination and viewpoint changes, we propose a keypoint matching method that uses landmarks as an intermediate image representation in order to leverage the power for deep learning. In environments with various changes, the traditional verification method via MVG may encounter difficulty because of their inability to generate a sufficient number of correctly matched keypoints. Our method exploits the excellent invariance properties of convolutional neural network (ConvNet) features, which have shown outstanding performance for matching landmarks between images. By generating and matching landmarks first in the images and then matching the keypoints within the matched landmark pairs, we can significantly improve the quality of matched keypoints in terms of precision and recall measures. The proposed method is validated on challenging datasets that involve significant illumination and viewpoint changes, to establish its superior performance to the standard keypoint matching methods.

Keywords: SLAM, Mapping, Localization
Abstract: Visual-inertial SLAM requires a good initial estimation of the initial velocity, orientation with respect to gravity and gyroscope and accelerometer biases. In this paper we build on the initialization method proposed by Martinelli and extended by Kaiser et al., modifying it to be more general and efficient. We improve accuracy with several rounds of visual-inertial bundle adjustment, and robustify the method with novel observability and consensus tests, that discard erroneous solutions. Our results on the EuRoC dataset show that, while the original method produces scale errors up to 156%, our method is able to consistently initialize in less than two seconds with scale errors around 5%, which can be further reduced to less than 1% performing visual-inertial bundle adjustment after ten seconds.

Keywords: SLAM, Localization
Abstract: In this paper, we address the problem of combining 3D laser scanner and camera information to estimate the motion of a mobile platform. We propose a direct laser-visual odometry approach building upon photometric image alignment. Our approach is designed to maximize the information usage of both, the image and the laser scan, to compute an accurate frame-to-frame motion estimate. To deal with the sparsity of the range measurements, our approach identifies planar point sets within individual point clouds and subsequently extract their corresponding pixel patches from the camera image. The extracted planar image patches are used together with the non-planar pixels to estimate the frame-to-frame motion using a homography formulation capable of incorporating both types of pixel alignments. To achieve high estimation accuracy, we explicitly predict possible occlusions caused by observations taken from different locations. We evaluate our proposed approach using the KITTI dataset as well as data recorded with a Clearpath Husky platform. The experiments suggest that our approach can achieve competitive estimation accuracy and produce consistently registered, colored point clouds.