Keywords: Adaptive and learning control, Intelligent systems
Abstract: Learning motion models of a moving object is a challenge for autonomous robots. We address the particular instance of parameter learning when tracking object motions in a switching multi-model system. We present a general algorithm of joint parameter-state estimation based on multi-model particle filter. We apply the approach to a specific ball-tracking problem and extend the algorithm to learn model parameters in a dynamic Bayesian network (DBN). We show empirical results in simulation and in a team robot soccer environment, as a substrate for applying the learned models to object tracking in a team. The learning capability allow the tracker to much more effectively track mobile objects.

Keywords: Adaptive and learning control, Neural networks
Abstract: Reinforcement Learning has been widely used to solve problems with a little feedback from environment. Q learning can solve full observable Markov Decision Processes quite well. For Partially Observable Markov Decision Processes (POMDPs), a Recurrent Neural Network (RNN) can be used to approximate Q values. However, learning time for these problems is typically very long. In this paper, Mixed Reinforcement Learning is presented to find an optimal policy for POMDPs in a shorter learning time. This method uses both a Q value table and a RNN. Q value table stores Q values for full observable states and the RNN approximates Q values for hidden states. An observable degree is calculated for each state while the agent explores the environment. If the observable degree is less than a threshold, the state is considered as a hidden state. Results of experiment in lighting grid world problem show that the proposed method enables an agent to acquire a policy, as good as the policy acquired by using only a RNN, with better learning performance.

Keywords: Adaptive and learning control, Neural networks, Manipulator control
Abstract: Support vector regression (SVR) is a class of machine learning technique that has been successfully applied to low-level learning control in robotics. Because of the large amount of computation required by SVR, however, most studies have used a batch mode. Although a recently developed online form of SVR shows faster learning performance than batch SVR, the amount of computation required by online SVR prevent its use in real-time robot learning control, which requires short sampling time. Here, we present a novel method, Local online SVR for Learning control, or LoSVR, that extends online SVR with a windowing method. We demonstrate the performance of LoSVR in learning the inverse dynamics of both a simulated two-joint robot and a real one-link robot arm. Our results show that, in both cases, LoSVR can learn the inverse dynamics on-line faster and with a better accuracy than batch SVR.

Keywords: Mobile robotics, Adaptive and learning control
Abstract: Recently, localization for mobile robot has been studied a lot. Up to now, most localization systems which are reliable and efficient are equipped with expensive sensors such as laser scanner and high performance CPU with fast computing. But, small and cost effective robot such as service robot for home cleaning cannot be equipped with costly sensor and CPU. This paper proposes localization method which can be implemented with low cost sensors and CPU while tracking robot’s pose quickly and correctly using Self-Organizing Map.

Keywords: Adaptive and learning control, Soft computing, Computer vision
Abstract: The capability of robotic emotion recognition is an important factor for human-robot interaction. In order to facilitate a robot to function in daily live environments, a emotion recognition system needs to accommodate itself to various persons. In this paper, an emotion recognition system that can adapt to new facial data is proposed. The main idea of the proposed learning algorithm is to adjust parameters of SVM hyperplane for learning emotional expressions of a new face. After mapping the input space to Gaussian-kernel space, support vector pursuit learning (SVPL) is applied to retrain the hyperplane in the new feature space. To expedite the retraining procedure, only samples classified incorrectly in previous iteration are combined with critical historical sets to restrain a new SVM classifier. After adjusting hyperplane parameters, the new classifier will recognize previous erroneous facial data. Experimental results show that the proposed system recognize new facial data with high correction rates after fast retraining the hyperplane. Moreover, the proposed method also keeps satisfactory recognition rate of old facial samples.

Keywords: Computer vision
Abstract: This paper describes the development and the application of an object tracking algorithm from a sequence of images. The algorithm is based on window-matching techniques using the sum of squared differences (SSD) as a distance-similarity measure, but adding stochastic filtering. The algorithm is then applied for tracking a vehicle on an urban environment and for tracking the ball on a ping-pong game. It is concluded that incorporating the Kalman filtering greatly improves the tracking performance.

Keywords: Computer vision
Abstract: We present a general framework for vessel segmentation in retinal images with a particular focus on small vessels. The retinal images are first processed by a nonlinear diffusion filter to smooth vessels along their principal direction. The vessels are then enhanced using a compound vessel enhancement filter that combines the eigenvalues of the Hessian matrix, the response of matched filters, and edge constraints on multiple scales. The eigenvectors of the Hessian matrix provide the orientation of vessels and so only one matched filter is necessary at each pixel on a given scale. This makes the enhancement filter is more efficient compared with existing multiscale matched filters. Edge constraints are used to suppress the response of spurious boundary edges. Finally, the center lines of vessels are tracked from seeds obtained using multiple thresholds of the enhanced image. Evaluation of the enhancement filter and the segmentation is performed on the publicly available DRIVE database.

Keywords: Computer vision, Evolutionary computing
Abstract: This paper presents an automatic object detection and tracking algorithm by using particle swarm optimization (PSO) based method, which is a searching algorithm inspired by the behaviors of social insect in the nature. A cascade of boosted classifiers based on Haar-like features is trained and employed to detect objects. To improve the searching efficiency, first the object model is projected into a high-dimensional feature space, and the PSO-based algorithm is applied to search over this high-dimensional space and converge to some global optima, which are well-matched candidates in terms of object features. Then, a Bayes-based filter is used to identify the best match with the highest possibility among these candidates under the constraint of object motion estimation. The proposed algorithm considers not only the object features but also the object motion estimation to speed up the searching procedure. Experimental results of tracking on vehicle and face demonstrate that the proposed method is efficient and robust under dynamic environment.

Keywords: Computer vision, Intelligent systems, Agent technology
Abstract: In classical image classification approaches, low-level features have been used. But the high dimensionality of feature spaces poses a challenge in terms of feature selection and distance measurement during the clustering process. In this paper, we propose an approach to generate visual keyword and combine both visual and text keywords of the image to form a multimodal vector for image classification. This multimodality helps in extracting the image to image, text to text and text to image relations. A visual keyword is derived using vector quantization of image tiles. We arrange the visual keywords in a manner analogous to the term-document matrix in information retrieval. The visual keywords when combined with text keywords result in improvement in the quality of classification. We use a recently proposed nonlinear dimensionality reduction technique, diffusion maps, to reduce the dimensionality of the image representation. Our method is evaluated on two public datasets: LabelMe and Corel. The results support the conclusion that the proposed method of combining visual and text keywords is robust and produces good quality clusters.

Keywords: Computer vision, Intelligent systems, Mobile robotics
Abstract: Small unmanned vehicles (UVs) are seeing more widespread use in military, scientific, and civil sectors in recent years. Because of the limitations inherent in small UVs, including power consumption and payload, the selection of light weight and low power sensors and processors becomes critical. Low power CMOS cameras and real-time vision processing algorithms can provide fast and reliable information to the UVs. These vision algorithms often require computational power that limits their use in traditional general purpose processors using conventional software. The latest developments in field programmable gate arrays (FPGAs) provide an alternative for hardware and software co-design of complicated real-time vision algorithms. Many vision algorithms utilize image features as the main source of information. By tracking features from one frame to another, it becomes possible to perform many different high-level vision tasks. This paper describes a feature tracking algorithm and an FPGA hardware implementation that operates in real-time.

Keywords: Biologically inspired robotics
Abstract: In this paper we present a model designed on the basis of the rat's brain neurophysiology to provide a robot with spatial cognition and goal-oriented navigation capabilities. We describe place representation and recognition processes in rats as the basis for topological map building and exploitation by robots. We experiment with the model by training a robot to find the goal in a maze starting from a fixed location, and by testing it to reach the same target from new different starting locations.

Keywords: Biologically inspired robotics, Intelligent systems, Agent technology
Abstract: This paper discusses an algorithm to realize the autonomous organization of a transportation network system inspired by social insects. As social insects, a group of ants show advanced performance in their activity by using a chemical substance called pheromone. Although the pheromone shows some interesting characteristics, it is difficult to use it in real applications. By introducing artificial pheromone system composed of data carriers and autonomous robots, the robotic system creates a potential field to navigate their group. We have developed a pheromone density model to realize the function of pheromones with the help of data carriers. We intend to show the effectiveness of the proposed system by performing simulations. The pheromone potential field system can be used in a transportation network system.

Keywords: Biologically inspired robotics, Intelligent systems, Mobile robotics
Abstract: This paper describes two experiments with supervised reinforcement learning (RL) on a real, mobile robot. Two types of experiments were preformed. One tests the robot’s reliability in implementing a navigation task it has been taught by a supervisor. The other, in which new obstacles are placed along the previously learned path to the goal, measures the robot’s robustness to changes in environment. Supervision consisted of human-guided, remote-controlled runs through a navigation task during the initial stages of reinforcement learning. The RL algorithms deployed enabled the robot to learn a path to a goal yet retain the ability to explore different solutions when confronted with a new obstacle. Experimental analysis was based on measurements of average time to reach the goal, the number of failed states encountered during an episode, and how closely the RL learner matched the supervisor’s actions.

Keywords: Biologically inspired robotics, Sensor fusion, Intelligent systems
Abstract: This paper presents a method of designing and optimizing a single chemical sensor-based source identification algorithm, derived from moth-inspired chemical plume tracing (CPT) strategies. In doing it, we define a source identification zone (SIZ) using last chemical detection points (LCDPs). Then, we optimize the proposed algorithm using a simulated plume with significant meander and filament intermittency by considering dynamics of a REMUS vehicle. The simulation studies show that for 1000 test runs the optimized algorithm achieves a success rate of over 90% in identifying source locations, an average identification time of 3-4 minutes, and an average error of identified source locations 1~2 meters in an operation area with length scales of 100 meters. In addition, we discuss an extension of the moth-inspired strategies to trace a plume and identify the odor source with static location in a three-dimensional space.

Keywords: Biologically inspired robotics, Soft computing
Abstract: Physics-based animations executing on 3D game engines enabled with physics middleware libraries and coprocessors can be used to explore the suitability of potential robot behaviors in working environments and robot configurations that are ill-defined or difficult and time-consuming to model with traditional quantitative tools. We use an inexpensive game development engine and PC hardware to develop physics-based animations of potential biomimetic subterranean robot burrowing behaviors. Qualitative assessment of energy efficiency, burrowing time, and digging capabilities of several biomimetic robot designs are validated with data from physical prototypes operated in a range of soil types and models of soil using colored particles. Results suggest this methodology is applicable to rapid screening of potential robot designs intended to operate in a variety of domains.

Keywords: Co-operative robotics, Neural networks, Adaptive and learning control
Abstract: In this paper we investigate how neural fields can produce an elegant solution for the problem of moving multiple robots in formation. The objective is to acquire a target, avoid obstacles and keep a geometric configuration at the same time. Several formations for a team of three robots are considered.

Keywords: Mobile robotics, Neural networks, Adaptive and learning control
Abstract: In this paper a nonholonomic mobile robot with completely unknown dynamics is considered. An efficient single layered neural network controller is assumed for the real time path tracking control of the mobile robot. The controller takes advantage of the robot regressor dynamics that express the highly nonlinear robot dynamics in a linear form in terms of the known and unknown robot dynamic parameters. The influence of time delays in the input control torque on the stability of the mobile robot motion has been studied. The present work enables to estimate the maximum admissible time delay in the input control torque with out the loss of stability in robot motion and guaranteed tracking performance.

Keywords: Biologically inspired robotics, Fuzzy logic, Computer vision
Abstract: A mission of chemical plume tracing (CPT) in near-shore and ocean environments is to navigate an autonomous underwater vehicle (AUV) to find a chemical plume, to trace the plume to its source, and to declare the source location. It is necessary to recognize the declared odor source by using a visual system. Color images, which were taken in near-shore ocean environments when the source was declared, are very vague due to dim illumination conditions and fluid advection effects. This paper presents an iterative fuzzy segmentation (IFS) algorithm for extracting color components of the chemical plume and the odor source for visual confirmation of the correct declared odor source. The proposed approach might be of general interest in image processing and computer vision.

Keywords: Sensor fusion, Mobile robotics
Abstract: We present a novel sensor calibration methodology that is suited to an evidence theoretic Unmanned Ground Vehicle (UGV) localization system. The proposed procedure for sensor calibration employs a series of designed experiments with the objective of creating parametric calibration models and forming a mass assignment table for a Dempster-Shafer belief system. Sensors calibrated include custom built magnetic encoders positioned at the rear wheels of the UGV, an accelerometer, a solid-state rate-gyro, a digital compass, and a Global Positioning System (GPS). The estimated parameters together with a mass assignment table are presented. This table is created for the GPS unit based on the factors that significantly impact the accuracy of the readings using an experimental procedure. We conclude with a brief summary of the main results.

Keywords: Sensor fusion, Mobile robotics
Abstract: In this paper, we present a novel evidence theoretic fusion filter, and its application to the Unmanned Ground Vehicle (UGV) localization problem. The various components of the sensor fusion framework such as the adaptive pre-processing unit, the evidence extraction and combination unit, and the extended Kalman filter are described in detail. The crux of this architecture is the evidence extraction and combination unit that employs a two-pronged approach, one to switch between parametric models, and another to adaptively vary the measurement noise covariance matrix. The process of evidence extraction using fuzzy-type or rule-based techniques, and their subsequent combination using the Dempster’s rule for combination are detailed. An experiment is conducted to demonstrate the merits of this UGV localization approach. Finally, we conclude with a brief summary of the results.

Keywords: Computer vision, Intelligent systems, Soft computing
Abstract: An investigation into computer vision techniques is conducted using a procedure from nonlinear dynamics termed “stochastic resonance.” This work involves concepts from detection theory, information theory and nonlinear dynamics. An information distance metric is synthesized which helps define the dependent measure to be used with the stochastic resonance optimization. Monte Carlo simulations show the efficacy of the proposed method. A class of test objects are presented to fairly evaluate the utility of the proposed methods introduced.

Keywords: Computer vision, Mobile robotics
Abstract: A Field Programmable Gate Array (FPGA) system implementation capable of being mounted onboard a Micro Aerial Vehicle (MAV) (less than 5 pounds) that can perform the processing tasks necessary to identify and track a marked target landing site in real-time is presented. This implementation was designed to be an image processing subsystem that is mounted on a MAV to assist an autopilot system with vision-related tasks. This paper describes the FPGA vision system architecture and algorithms implemented to segment and locate a colored cloth target that specifies the exact landing location. Once the target landing site is identified, the exact location of the landing site is transmitted to the autopilot, which then implements the trajectory adjustments required to autonomously land the MAV on the target. Results of two flight test situations are presented. In the first situation, the MAV lands on a static target. The second situation includes a moving target, which in our tests was the back of a moving vehicle. This FPGA system is an application-specific configuration of the Helios Robotic Vision Platform developed at Brigham Young University.

Keywords: Computer vision, Neural networks, Intelligent systems
Abstract: This paper proposes a technique for real-time recognition of facial Identity and expression which uses the active appearance model (AAM) with efficient second order minimization algorithm and neural network, especially the multilayer perceptron. The efficient second order minimization allows AAM to have the ability of correct convergence with a little loss of frame rate. And the correctly extracted facial shape with AAM prevents the recognition of facial identity and expression from undergoing a large error. In addition, high dimensional feature vectors of facial identity and expression, which consist of facial shape and texture, can be dealt by the multilayer perceptron with a very high recognition rate of over 98%.

Keywords: Computer vision, Evolutionary computing, Genetic algorithms
Abstract: Missing abstract

Keywords: Mobile robotics, Computer vision, Intelligent systems
Abstract: Micro Unmanned Air Vehicles are well suited for a wide variety of applications in agriculture, homeland security, military, search and rescue, and surveillance. In response to these opportunities, a quad-rotor micro UAV has been developed at the Robotic Vision Lab at Brigham Young University. The quad-rotor UAV uses a custom, low-power FPGA platform to perform computationally intensive vision processing tasks on board the vehicle, eliminating the need for wireless tethers and computational support on ground stations. Drift stabilization of the UAV has been implemented using Harris feature detection and template matching running in real-time in hardware on the on-board FPGA platform, allowing the quad-rotor to maintain a stable and almost drift-free hover without human intervention.

Keywords: Adaptive and learning control
Abstract: This paper describes the development and testing of control of the OmniTread OT-4 robot by the Seventh Generation (7G) Control System. Control of OT-4 was developed in the Yobotics 3D simulator by an iterative process combining genetic algorithm, learning and analytic programming techniques. The control system developed in simulation was tested by controlling the real OT-4 robot in the laboratory. The performance of the real OT-4 robot under 7G control on stairs, parallel bars, a slalom course, and stairs with obstacles corresponded well to the simulated performance on which development of the control was based.

Keywords: Ambient intelligence, Sensor fusion, Mobile robotics
Abstract: This paper deals with an architecture for knowledge representation suitable for integrated Robotics and Ambient Intelligence applications. The aim of the work is to adopt a common framework to deal with different aspects of an “intelligent space”. The key idea is that an intelligent space is an ecosystem composed by artificial entities which cooperate to perform an intelligent multi-source data fusion of both numerical and symbolic information. This information is used to guide the coordinated behavior of mobile robots and intelligent appliances, thus extending the overall system capabilities. The experimental results discuss the interaction dynamics related to the fulfillment of several service tasks, whose execution would be otherwise very difficult to achieve.

Keywords: Mobile robotics, Computer vision
Abstract: This paper presents a novel design of a robust visual tracking control system, which consists of a visual tracking controller and a visual state estimator. This system facilitates human-robot interaction of a unicycle-modeled mobile robot equipped with a tilt camera. Based on a novel dual-Jacobian visual interaction model, a dynamic motion target can be tracked using a single visual tracking controller without target’s 3D velocity information. The visual state estimator aims to estimate the optimal system state and target image velocity, which is used later by the visual tracking controller. To achieve this, a self-tuning Kalman filter is proposed to estimate interesting parameters online in real-time. Further, because the proposed method is fully working in image space, the computational complexity and the sensor/camera modeling errors can be reduced. Experimental results validate the effectiveness of the proposed method, in terms of tracking performance, system convergence, and robustness.

Keywords: Mobile robotics, Intelligent systems
Abstract: This paper is a report on the initial trial for its kind in the development of the performance index of the autonomous mobile cleaning robot. The unique characteristic features of the cleaning robot have been identified as autonomous mobility, dust collection, and operation noise. Along with the identification of the performance indices the standardized performance-evaluation methods including the corresponding performance evaluation platform for each indices have been developed as well. The validity of the proposed performance evaluation methods has been demonstrated by applying the proposed evaluation methods on two commercial cleaning robots available in market. The proposed performance evaluation methods can be applied to general-purpose autonomous service robots which will be introduced in the consumer market in near future.

Keywords: Mobile robotics, Evolutionary robotics, Robot manipulators
Abstract: This article proposes a new type of suspension for lunar rover. The suspension is mainly constructed by a positive quadrilateral levers mechanism and a negative quadrilateral levers mechanism. The suspension is designed based on following factors: Climbing up obstacles, adapting terrain, traveling smoothly, and distributing equally the load of cab to wheels. In the article, firstly the structure of the new suspension is described, secondly the kinematics of the levers is analyzed, and the relational equations of the suspension levers are established, so the distortion capability of the suspension is known. In order to test the capability of suspension, we design a prototype rover with the new suspension and take a test of climbing obstacles, and the result indicates that the prototype rover with new type of suspension has excellent capability to climb up obstacles with keeping cab smooth. Based on the shortcoming found in test, we optimize the levers mechanism, and then establish the rover models with the new type of suspension and with Rocker-Bogie suspension based on ADAMS, and then the capability compare on simulation is followed. The further researching work for this new developed suspension is being carried out now so as to improve its overall performances. China has been determined to carry out the lunar exploration project in the near future. The proposed new type of suspension would provide a valuable technical support to it.

Keywords: Agent technology
Abstract: In this paper, we describe the concept, design and implementation of a series of autonomous mobile soccer robots,named “Musashi” robot, which have a mechatronics modular architecture, to participate in the RoboCup middle-size league. In this design methodology, we show that the selection of a proper moving mechanism, a suitable vision system and a mechatronics modular architecture design can lead to realize a reliable, simple, and low cost robot comparing with most of car-like robots including many kinds of sensors and a complex design structure.

Keywords: Co-operative robotics, Intelligent systems, Agent technology
Abstract: Recently multi-agent systems have been discussed to realize a large size of distributed autonomous systems. This paper proposes an intelligent control of multiple partner robots as one of multi-agent systems. First of all, we discuss the current state of researches on the multi-agent systems. Next, we propose a multi-objective behavior coordination to realize formation behaviors based on the integration of the intelligent control from the local viewpoint of individual intelligence and the spring model from the global viewpoint of collective intelligence. Finally, we discuss the effectiveness of the proposed method through several computer simulation results.

Keywords: Health-care robotics, Co-operative robotics, Intelligent systems
Abstract: A power-assist exoskeleton robot, which is directly attached to the user’s body and assist the motion in accordance with the user’s intension, is one of the most effective human assist robots for the physically weak persons. Many studies on power-assist robots have been carried out to help the motion of physically weak persons such as disabled, injured, and/or elderly persons. EMG-based control (i.e., control based on the skin surface electromyogram (EMG) signals of the user) is one of the most effective control methods for the power-assist robots, since EMG signals of user’s muscles directly reflect the user’s motion intension. However, the EMG-based control is not easy to be realized because of many reasons. The paper presents an effective human motion prediction method from the EMG signals using a neuro-fuzzy technique for the control of power-assist exoskeleton robots.

Keywords: Intelligent systems, Genetic algorithms, Manipulator control
Abstract: Resolved acceleration control method or computed torque method is used for nonlinear control of industrial manipulators, which is composed of a model base portion and a servo portion. The servo portion is a close loop with respect to the position and velocity. On the other hand, the model base portion has the inertia term, gravity term and centrifugal/Coriolis term, which work for canceling the nonlinearity of manipulator. In order to realize high control stability, the position and velocity gains used in the servo portion should be selected suitably. In this paper, a simple but effective fine tuning method after manual tuning is introduced for the position and velocity feedback gains in the servo portion. At the first step, base values of the gains are roughly selected by a controller designer, e.g., considering the critically damped condition. After that, the base values are finely tuned by genetic algorithms. Genetic algorithms search for the better combination of the position and velocity gains. Simulations are conducted using a dynamic model of PUMA560 manipulator to validate the effectiveness of the proposed method.

Keywords: Intelligent systems, Adaptive and learning control, Soft computing
Abstract: Recently, various learning methods are adapted for experimental robot. We can make movement of a robot by giving teaching signals to a robot. But it is heavy for operator to define how to give teaching signals generally because operator must guess and think of a task and environment and define a function to do that. Here I aim to create teaching signals automatically for each task and environment. In this paper, I suggest a simple rule which is independent of information about any task and environment to create teaching signals for each task and environment. This rule is that a situation which is often happened is good situation. In this paper, I adopt reinforcement learning as learning method and a small-sized humanoid robot as application. I will show creating a reward by adapting a rule and show that a robot can learn and make movement.

Keywords: Co-operative robotics, Biologically inspired robotics, Ambient intelligence
Abstract: We propose a new concept, potentially distributable energy, in the field of autonomous mobile robots. Considering a system of multiple robots powered by batteries, each robot no longer works since its energy capacity is expired. To extend operating time, the robot needs to replenish energy through recharging energy. To date, except research on vaccum cleaning robots that are able to recharge battery when docking with the fixed station has been achieved, there does not exist any research of energy distribution to prolong operating time in a large population of mobile robots. This could be caused by the lack of using rechargeable battery in the fact that the robot has to normally spend the charging-time much longer than the operating time. This paper presents simulation results of mobile robots that are capable of not only self-recharging energy but also exchanging batteries to the other robots. Initially, we describe a simulation of multiple mobile robots, and then issue rules of battery exchange, which is formulated under constraints of workload, distance and remaining capacity. The simulation shows that: (a) a robot is able to be energetically autonomous if its energy can be replenished by the other robots or it is able to come back to the main charging station to replenish itself; (b) energy of a robot is always under constraints of energy distribution of the mother charging station and the other robots; (c) distributed energy balance is the main elements to decide a number of robots in a specific area and an ideal location of the repository when one wants to deploy a large population of autonomous mobile robots. Finally, based on results of the simulation we adjust rules for our real multirobot system.

Keywords: Co-operative robotics, Computer vision, Mobile robotics
Abstract: Behavior coordination among a team of heterogeneous robots to perform a search-and-retrieve task is investigated. In our initial implementation, two robots with different sensing and actuation abilities are commanded to navigate into an unknown environment, to search for different types of plastic bottles, and then to retrieve the bottles. These two robots communicate and coordinate to pick up a lying bottle from the floor, which cannot by be accomplish by either robot. Four different visual servoing behaviors were employed to implement the search-and-retrieve task.

Keywords: Soft computing, Co-operative robotics, Agent technology
Abstract: To enable effective human-agent collaboration, new human-centric computing paradigms are needed. This paper presents a soft constraint representation scheme based on generalized intervals. With logically quantified intervals, semantics and intent can be integrated in numerical computing. The interpretable numerical results allow for better human-agent communication.

Keywords: Co-operative robotics, Mobile robotics
Abstract: This paper discusses the workload distribution problem in an Active Sensor Network, which integrates multiple sensor network-friendly mobile robots into a traditional sensor network and introduces adaptivity, self-healing, responsiveness and longer lifetime to the network. In order to distribute the workload among the service robots, first, a Service Set Partition (SSP) algorithm is developed to disperse the robots so that each robot can attend one subset of the sensors. Second, to service multiple sensors simultaneously, a Contract Network Protocol (CNP) is adopted to assign tasks to multiple service robots. Through CNP, certain performances such as energy efficiency and service time can be optimized. The proposed algorithms are verified through simulations.

Keywords: Co-operative robotics, Mobile robotics
Abstract: In this paper, a communication-efficient dynamic task scheduling algorithm for a heterogeneous multi-robot system is proposed. To make this task scheduling algorithm to be scalable for various robot teams, a distributed communication with shared global unit mechanism is applied to reduce the storage cost as well as communication overhead. Each robot makes its own decision through communicating with others as well as checking a global unit. This algorithm improves its efficiency by broadcasting specific information only to those who are capable and have interest in the current tasks. To improve the system robustness, an auction-based fitness function is applied to dynamically allocate the tasks among the robots if the pre-assigned robot can not handle the task or a robot fails under dynamic environment. The proposed approach is robust against communication failures and robot failures. Simulation results demonstrate the efficiency and robustness of the proposed approach.

Keywords: Mobile robotics
Abstract: In human-robot communication it is often important to relate robot sensor readings to concepts used by humans. We believe that access to semantic maps will make it possible for robots to better communicate information to a human operator and vice versa. The main contribution of this paper is a method that fuses data from different sensor modalities, range sensors and vision sensors are considered, to create a probabilistic semantic map of an outdoor environment. The method combines a learned virtual sensor (understood as one or several physical sensors with a dedicated signal processing unit for recognition of real world concepts) for building detection with a standard occupancy map. The virtual sensor is applied on a mobile robot, combining classifications of sub-images from a panoramic view with spatial information (location and orientation of the robot) giving the likely locations of buildings. This information is combined with an occupancy map to calculate a probabilistic semantic map. Our experiments with an outdoor mobile robot show that the method produces semantic maps with correct labeling and an evident distinction between `building' objects from `nature' objects.

Keywords: Mobile robotics
Abstract: Many researchers have been encouraged to investigate the design, posture and stability of biped robots in order to replicate the anthropoid gait. This paper addresses the design and development of a bipedal robot. It presents a combination of the design considerations and simplicity of design to provide a test bed for autonomous biped robots. Kinematic models of the biped robot are also developed and simulated prior to experimentally verifying the performance of the system. Overall, a low cost, open system biped robot is the underlying objective on which new gait algorithms and controllers will be developed to further the research in the field of humanoid robots.

Keywords: Mobile robotics, Computer vision
Abstract: This paper introduces a novel self-localization algorithm for mobile robots, which recovers the robot position from a single image of identified landmarks taken by an onboard camera. The visual angle between two landmarks can be derived from their projections in the same image. The distances between the optical center and the landmarks can be calculated from the visual angles and the known landmark positions based on the law of cosine. The robot position can then be determined using the principle of trilateration. Extensive simulation has been carried out. A comprehensive error analysis provides the insight on how to improve the localization accuracy.

Keywords: Mobile robotics, Genetic algorithms, Evolutionary computing
Abstract: This paper studies the evolutionary planning strategies for mobile robots to move smoothly along efficient collision-free paths in known static environments. The cost of each candidate path is composed of the path length and a weighted sum of penetration depth to vertices of polygonal obstacles. The path is composed of a pre-specified number of cubic spiral segments with constrained curvature. Comparison of the path planning performance between two Pareto-optimal schemes, the parallel genetic algorithm scheme based on the island method (PGA) and the non-dominated sorting genetic algorithm (NSGA-II), are conducted in terms of success rate in separate runs and path length whenever collision-free paths are found. Numerical simulation results are presented for three types of obstacles: polygons, walls, and combinations of both.

Keywords: Mobile robotics, Intelligent systems
Abstract: The navigation of autonomous ground vehicles (AGVs) through uncertain environments has received substantial research attention. However, the literature contains very few comparisons of the navigation paradigms for AGVs, especially for algorithms using range finders. The fuzzy behavioral approach and vector field histogram (VFH) approach are well known methods that can be implemented using range finders. This paper will focus on comparing their structure, ease of programming and algorithm tuning, and performance. Both approaches are implemented on a Pioneer 2 robot, equipped with a SICK laser range finder.