Touch-to-Touch Translation -- Learning the Mapping Between Heterogeneous Tactile Sensing Technologies

The use of data-driven techniques for tactile data processing and classification has recently increased. However, collecting tactile data is a time-expensive and sensor-specific procedure. Indeed, due to the lack of hardware standards in tactile sensing, data is required to be collected for each different sensor. This paper considers the problem of learning the mapping between two tactile sensor outputs with respect to the same physical stimulus -- we refer to this problem as touch-to-touch translation. In this respect, we proposed two data-driven approaches to address this task and we compared their performance. The first one exploits a generative model developed for image-to-image translation and adapted for this context. The second one uses a ResNet model trained to perform a regression task. We validated both methods using two completely different tactile sensors -- a camera-based, Digit and a capacitance-based, CySkin. In particular, we used Digit images to generate the corresponding CySkin data. We trained the models on a set of tactile features that can be found in common larger objects and we performed the testing on a previously unseen set of data. Experimental results show the possibility of translating Digit images into the CySkin output by preserving the contact shape and with an error of 15.18% in the magnitude of the sensor responses.

Reinforcement Learning Controllers for Soft Robots using Learned Environments

Soft robotic manipulators offer operational advantage due to their compliant and deformable structures. However, their inherently nonlinear dynamics presents substantial challenges. Traditional analytical methods often depend on simplifying assumptions, while learning-based techniques can be computationally demanding and limit the control policies to existing data. This paper introduces a novel approach to soft robotic control, leveraging state-of-the-art policy gradient methods within parallelizable synthetic environments learned from data. We also propose a safety oriented actuation space exploration protocol via cascaded updates and weighted randomness. Specifically, our recurrent forward dynamics model is learned by generating a training dataset from a physically safe \textit{mean reverting} random walk in actuation space to explore the partially-observed state-space. We demonstrate a reinforcement learning approach towards closed-loop control through state-of-the-art actor-critic methods, which efficiently learn high-performance behaviour over long horizons. This approach removes the need for any knowledge regarding the robot's operation or capabilities and sets the stage for a comprehensive benchmarking tool in soft robotics control.

Towards Reinforcement Learning Controllers for Soft Robots using Learned Environments

Soft robotic manipulators offer operational advantage due to their compliant and deformable structures. However, their inherently nonlinear dynamics presents substantial challenges. Traditional analytical methods often depend on simplifying assumptions, while learning-based techniques can be computationally demanding and limit the control policies to existing data. This paper introduces a novel approach to soft robotic control, leveraging state-of-the-art policy gradient methods within parallelizable synthetic environments learned from data. We also propose a safety oriented actuation space exploration protocol via cascaded updates and weighted randomness. Specifically, our recurrent forward dynamics model is learned by generating a training dataset from a physically safe \textit{mean reverting} random walk in actuation space to explore the partially-observed state-space. We demonstrate a reinforcement learning approach towards closed-loop control through state-of-the-art actor-critic methods, which efficiently learn high-performance behaviour over long horizons. This approach removes the need for any knowledge regarding the robot's operation or capabilities and sets the stage for a comprehensive benchmarking tool in soft robotics control.

SPADA: A Toolbox of Designing Soft Pneumatic Actuators for Shape Matching based on the Surrogate Model

The actuation of a soft robot involves transforming its shape from an initial state to a desired operational state. To achieve task-specific design, it is necessary to map the shape between these two states to the robot's design parameters. This requires both a kinematic model of the soft robot and a shape-matching algorithm. However, existing kinematic models for soft robots are often limited in accuracy and generality due to the robot's flexibility and nonlinearity, and current shape-matching algorithms are not well-suited for 3D cases. To address this challenge, this paper presents a shape-matching design framework for bellow soft pneumatic actuators (SPAs) to expedite the actuator design process. First, a kinematic model of the bellow SPA is developed based on its novel modular design and a surrogate model, which is trained using an Artificial Neural Network and a dataset from Finite Element Method (FEM) simulations. Then, a 3D shape-matching algorithm, composed of a 3D piecewise-constant curvature segmentation and a bi-level Bayesian optimisation algorithm based on the surrogate model, is presented to find the optimal actuator design parameters that match the desired shape. An open-source design toolbox SPADA (Soft Pneumatic Actuator Design frAmework) is also developed to facilitate the use of the proposed design framework, including FEM simulation, shape-matching optimisation based on surrogate modelling, and automatic generation of the ready-to-print CAD file. Experimental results show an averaged root-mean-square error of 2.74 mm, validating the accuracy of the kinematics model. To demonstrate the proposed design framework, actuators are designed to match the predefined shapes in 2D and 3D space.

Design and Characterization of a 3D-printed Pneumatically-driven Bistable Valve with Tunable Characteristics

Although research studies in pneumatic soft robots develop rapidly, most pneumatic actuators are still controlled by rigid valves and conventional electronics. The existence of these rigid, electronic components sacrifices the compliance and adaptability of soft robots.} Current electronics-free valve designs based on soft materials are facing challenges in behaviour consistency, design flexibility, and fabrication complexity. Taking advantages of soft material 3D printing, this paper presents a new design of a bi-stable pneumatic valve, which utilises two soft, pneumatically-driven, and symmetrically-oriented conical shells with structural bistability to stabilise and regulate the airflow. The critical pressure required to operate the valve can be adjusted by changing the design features of the soft bi-stable structure. Multi-material printing simplifies the valve fabrication, enhances the flexibility in design feature optimisations, and improves the system repeatability. In this work, both a theoretical model and physical experiments are introduced to examine the relationships between the critical operating pressure and the key design features. Results with valve characteristic tuning via material stiffness changing show better effectiveness compared to the change of geometry design features (demonstrated largest tunable critical pressure range from 15.3 to 65.2 kPa and fastest response time $\leq$ 1.8 s.

Contact modelling and tactile data processing for robot skin

Tactile sensing is a key enabling technology to develop complex behaviours for robots interacting with humans or the environment. This paper discusses computational aspects playing a significant role when extracting information about contact events. Considering a large-scale, capacitance-based robot skin technology we developed in the past few years, we analyse the classical Boussinesq-Cerruti's solution and the Love's approach for solving a distributed inverse contact problem, both from a qualitative and a computational perspective. Our contribution is the characterisation of algorithms performance using a freely available dataset and data originating from surfaces provided with robot skin.

A Flexible and Robust Large Scale Capacitive Tactile System for Robots

Capacitive technology allows building sensors that are small, compact and have high sensitivity. For this reason it has been widely adopted in robotics. In a previous work we presented a compliant skin system based on capacitive technology consisting of triangular modules interconnected to form a system of sensors that can be deployed on non-flat surfaces. This solution has been successfully adopted to cover various humanoid robots. The main limitation of this and all the approaches based on capacitive technology is that they require to embed a deformable dielectric layer (usually made using an elastomer) covered by a conductive layer. This complicates the production process considerably, introduces hysteresis and limits the durability of the sensors due to ageing and mechanical stress. In this paper we describe a novel solution in which the dielectric is made using a thin layer of 3D fabric which is glued to conductive and protective layers using techniques adopted in the clothing industry. As such, the sensor is easier to produce and has better mechanical properties. Furthermore, the sensor proposed in this paper embeds transducers for thermal compensation of the pressure measurements. We report experimental analysis that demonstrates that the sensor has good properties in terms of sensitivity and resolution. Remarkably we show that the sensor has very low hysteresis and effectively allows compensating drifts due to temperature variations.