Keywords: Soft Sensors and Actuators, Simulation and Animation, Grippers and Other End-Effectors
Abstract: Compliant grippers enable robots to work with humans in unstructured environments. These grippers need tactile sensing to estimate the state of objects around them to precisely manipulate objects. However, co-designing compliant structures with high-resolution tactile sensing is a challenging task. We propose a simulation framework for the end-to-end forward design of Fin Ray GelSight sensors. Our simulation framework consists of mechanical simulation using the finite element method and optical simulation including physically based rendering (PBR). To simulate fluorescent paint, used in Fin Ray grippers, we propose an efficient method that can be directly integrated in PBR. Using the simulation framework, we investigated design choices available in the compliant grippers, namely -- gel pad shapes, illumination conditions, Fin Ray gripper sizes, and Fin Ray stiffness. This enables the design of new Fin Ray sensors within weeks that have a sensing area of 70 mm * 35 mm. We manufacture the best design and show its utility in grasping day-to-day objects.

Keywords: Grippers and Other End-Effectors, Compliant Joint/Mechanism, Soft Sensors and Actuators
Abstract: An origami-inspired bistable gripper, featuring a dual-function custom PET linear solenoid actuator that acts both as an actuator and a sensor, is presented. Movements in the permanent magnet plunger, which is directly mounted to the gripper, create induced electromotive force (emf) in the solenoid, and these induced emf measurements are used to detect snap-through actions and light contacts on the gripper. The fabrication methods for the gripper, actuator, and a gel-free soft wearable EMG electrode are outlined, and the actuator's self-sensing method utilizing the time-integral of the induced emf measurements are explored. Because a self-sensing actuator eliminates the need for extra sensors, it allows for further miniaturization of the robot while maintaining its compactness and lightweight design. The paper also introduces a full human-in-the-loop system, allowing users to open or close the gripper with their biceps via a wearable EMG electrode. This system bridges human intent with robotic action, offering a more intuitive interaction model for robotic control.

Keywords: Soft Sensors and Actuators, Grasping, Grippers and Other End-Effectors
Abstract: Tactile sensing is of utmost importance for accomplishing fine manipulation tasks and extracting crucial physical features in soft grippers. A contact force estimation and localization approach based on sensing modalities using Fiber Bragg Grating (FBG) transducers and artificial intelligence models are proposed for pneumatically actuated soft fingers. The small packaged sensor unit enables modular design, ease of assembly, and high repeatability with negligible effects on the mechanical performance of the soft finger. The proposed neural networks process the output of the sensing modality and mitigate errors from material nonlinearity, fabrication, and assembly of soft fingers. This, in turn, enhances the accuracy and transferability of force and position estimations, leading to proper metrological indicators. These results provide a step forward in the development of smart soft grippers enabling them to attain "transparent" exteroception. As a result, this work contributes to empowering soft grippers with skillful capabilities to acquire precise tactile information for safe manipulation ranging from agricultural to biomedical fields.

Keywords: Soft Sensors and Actuators, Force and Tactile Sensing, Modeling, Control, and Learning for Soft Robots
Abstract: Soft robotic systems necessitate accurate and reliable sensor readings to detect environmental interactions and provide precise feedback for control. To be effective, soft sensors must exhibit sensitivity, reliability, repeatability, and flexibility. A versatile approach to sensing for soft robots uses soft air-filled deformable structures with pressure transducers to detect pressure changes due to applied forces. However, the common approach of employing one pressure transducer per sensing chamber limits the scalability of this sensing approach (e.g., for large arrays able to detect touch at many locations). Here we present an approach to the design of pneumatic sensor arrays that reduces the number of required transducers. We develop mathematical models to analyze the pressure variations within the sensor arrays in response to applied forces at various locations. We also introduce a method of rapidly fabricating sensor arrays by laminating elastomeric sheets patterned with laser-cut sacrificial layers. We then use our model to optimize the geometry of the sensors and evaluate the results experimentally. Finally, we devise an algorithm capable of determining the location of multiple touches anywhere within the sensor array. This work represents a step towards the practical application of soft pneumatic sensors, particularly for robotic sensing and haptic devices, enhancing the safety of human-robot interactions.

Keywords: Soft Sensors and Actuators, Force and Tactile Sensing, Modeling, Control, and Learning for Soft Robots
Abstract: Soft tactile sensors can transform how robots interact with humans and their intricate environments, making such encounters more efficient and safely intimate. However, existing technologies are complex and costly, which has constrained their widespread application. Therefore, there is an urgent need to embrace more straightforward solutions utilizing traditional off-the-shelf sensors. In this context, we integrate fluid-solid interaction with artificial intelligence to develop a soft tactile interface crafted from elastomer-encapsulated fluid. Instead of relying on electronic circuitry, we utilize fluid pressure to transmit tactile information to available pressure sensors. We have devised efficient machine learning algorithms to infer touch position and intensity accurately. In its simplest form, we fabricated a 1D sensor with a linear channel, demonstrating its ability to accurately estimate touch position and force along a straight line using pressure readings solely from its two ends. Additionally, this system served as a test platform to study how geometrical parameters and different fluid mediums (such as air, water, and oil) impact the sensing capabilities of the developed sensor. We envision expanding this simple approach to create a cost-effective, electronics-free sensing front, providing skins for robots designed to be aware of their environment.

Keywords: Soft Sensors and Actuators, Force and Tactile Sensing, Soft Robot Materials and Design
Abstract: Distributed high-density tactile sensing is a challenging problem with numerous commercial applications. Soft sensing technologies appear to be a promising approach to address this challenge. In particular, Electrical Impedance Tomography (EIT)-based soft sensors are desirable because they can offer a large sensing surface without rigid electrodes and provide high sensing resolution. However, their applicability is limited to simple sensor shapes, and they require materials with high conductivity for sensing accuracy. This project introduces a novel multi-layered architecture for EIT-based soft skins. This innovation allows us to develop sensory skins with multiple materials and provides greater flexibility in electrode placement, resulting in higher accuracy. We experimentally tested the method's applicability using soft skins of varying morphology, employing a hydrogel-based tactile skin. The results demonstrate that our multi-layer soft skin improves average accuracy compared to a single-layer EIT-based skin, reducing it from 15.8 mm to 4.4 mm.

Keywords: Soft Sensors and Actuators, Force and Tactile Sensing, Haptics and Haptic Interfaces
Abstract: We present an integrated pneumatic sensor and actuator for soft haptic devices that can estimate contact force, location, and shape using a multi-headed neural network. The sensor uses channels cast into a multi-layer silicone bubble that change flow resistance as the bubble deforms, allowing measurements of strain and external contact at the surface. Changes in flow resistance are measured using pressure transducers in a pneumatic circuit. Arranging the channels in a two-layer array allows localization of the strain with an accuracy of over 80% for contact locations in a 3 x 3 grid and force measurements from 0.9 ~ 4.5N with an RMS error of ~0.39N. This technology can enable closed-loop control for future soft pneumatic devices.