Proprioceptive and Exteroceptive Information Perception in a Fabric Soft Robotic Arm via Physical Reservoir Computing with minimal training data

TL;DR

This paper demonstrates that a soft robotic arm can accurately perceive its posture and payload using only internal pressure sensors combined with physical reservoir computing, reducing reliance on traditional sensors.

Contribution

It introduces a novel approach using physical reservoir computing with minimal training data for soft robot perception tasks, avoiding specialized external sensors.

Findings

Accurate prediction of bending angle and payload mass from pressure data.

Bending angle prediction requires less training data than payload prediction.

Balanced dynamics are essential for complex perception tasks.

Abstract

Over the past decades, we have witnessed a rapid emergence of soft and reconfigurable robots thanks to their capability to interact safely with humans and adapt to complex environments. However, their softness makes accurate control very challenging. High-fidelity sensing is critical in improving control performance, especially posture and contact estimation. To this end, traditional camera-based sensors and load cells have limited portability and accuracy, and they will inevitably increase the robot's cost and weight. In this study, instead of using specialized sensors, we only collect distributed pressure data inside a pneumatics-driven soft arm and apply the physical reservoir computing principle to simultaneously predict its kinematic posture (i.e., bending angle) and payload status (i.e., payload mass). Our results show that, with careful readout training, one can obtain accurate bending angle and payload mass predictions via simple, weighted linear summations of pressure readings. In addition, our comparative analysis shows that, to guarantee low prediction errors within 10\%, bending angle prediction requires less training data than payload prediction. This result reveals that balanced linear and nonlinear body dynamics are critical for the physical reservoir to accomplish complex proprioceptive and exteroceptive information perception tasks. Finally, the method of exploring the most efficient readout training methods presented in this paper could be extended to other soft robotic systems to maximize their perception capabilities.