Hysteresis-Aware Neural Network Modeling and Whole-Body Reinforcement Learning Control of Soft Robots

Abstract

Soft robots are inherently compliant and safe, making them suitable for human-interactive applications such as surgery. However, their nonlinear and hysteretic behavior, arising from the properties of soft materials, presents substantial challenges for accurate modeling and control. In this study, we present a soft robotic system and propose a hysteresis-aware whole-body neural network model that accurately captures and predicts the soft robot's whole-body motion, including its hysteretic behavior. Building upon the high-precision dynamic model, we construct a highly parallel simulation environment for soft robot control and apply an on-policy reinforcement learning algorithm to efficiently train whole-body motion control policies. The trained policy is deployed on the real soft robot to evaluate its control performance. Furthermore, we develop a soft robotic system for surgical applications and validate it through phantom-based laser ablation experiments. The results demonstrate that the hysteresis-aware modeling reduces the Mean Squared Error (MSE) by 86.07% compared with traditional modeling methods. The deployed control algorithm achieves a trajectory tracking error ranging from 0.147 to 0.307 mm on the real soft robot, highlighting its precision in real-world conditions. The proposed method also shows strong performance in phantom-based surgical experiments, and demonstrates its potential for complex scenarios, including future real-world clinical applications.