Adaptive Learning-based Predictor for Enhanced Control of Assistive Soft Robots

Soft robots are increasingly used in healthcare, especially for assistive care, due to their inherent safety and adaptability. Controlling soft robots is challenging due to their nonlinear dynamics and the presence of time delays, especially in applications like a soft robotic arm for patient care. We propose a novel learning-based Smith Predictor (SP) for enhanced delay compensation in soft robots. We use Kernel Recursive Least Squares Tracker (KRLST) to approximate online the SP correction term without needing an explicit dynamic model, coupled with Legendre Delay Network (LDN) for efficient and scalable input history encoding. This learning-based predictor is modularly integrated with a baseline robust model-based nonlinear controller. Experimental results demonstrate significant improvement in tracking performance compared to the baseline. The method is computationally efficient and adaptable online, making it suitable for real-world scenarios and highlighting its potential for enabling safer and more accurate control of soft robots in assistive care applications.