A Model-Based Sensor Fusion Approach for Force and Shape Estimation in Soft Robotics

Abstract

In this paper, we address the challenge of sensor fusion in Soft Robotics for estimating forces and deformations. In the context of intrinsic sensing, we propose the use of a soft capacitive sensor to find a contact's location, and the use of pneumatic sensing to estimate the force intensity and the deformation. Using a FEM-based numerical approach, we integrate both sensing streams and model two Soft Robotics devices we have conceived. These devices are a Soft Pad and a Soft Finger. We show in an evaluation that external forces on the Soft Pad can be estimated and that the shape of the Soft Finger can be reconstructed.

Design and Control of Soft Robots Using Differentiable Simulation

“…By leveraging a FEM-driven model in the state estimation, one can solve for the soft body state that best explains a set of observed measurements while minimizing overall energy. This has been recently demonstrated by Navarro et al [55], where a soft body state is reconstructed from a combination of capacitive and pressure sensors, explaining the measurements best.…”

“…Simulation-driven state estimation for soft robots has been demonstrated for liquid-metal strain sensors [14 ••] and also used to combine capacitive and pressure sensing [55]. Similar approaches could be taken for other sensory data such as force/torque, pressure [64], IMU, or optical data [65].…”

Sensor-Based Control for Collaborative Robots: Fundamentals, Challenges, and Opportunities

“…Although vision and touch ( proprioceptive force rather than tact ) emerge nowadays as the most popular senses on collaborative robots, the advent of cheap, precise, and easy to integrate tactile, distance, and audio sensors present great opportunities for the future. Typically, we believe that robot skins (e.g., on arms and hands, Guadarrama-Olvera et al, 2019 ; Navarro et al, 2020 ) will simplify interaction, boosting the opportunities for human-robot collaboration. It is imperative that researchers develop the appropriate tools for this.…”

Proximity Perception in Human-Centered Robotics: A Survey on Sensing Systems and Applications

“…Proximity perception can help in finding and reaching desired contact states. Overall, the support of simulation frameworks for model-based control and sensing, such as SOFA [141], will also be relevant. Therefore, regarding the major challenges in this domain, we can say that:…”

“…A significant crosstalk between the global deformation and the detection of tactile and proximity events has to be expected. As stated in the previous section, appropriate models for proximity sensors are needed for sim-to-real learning or for interpreting their signals correctly under deformation using interactive simulations [142], [141].…”