Neural Network-Based Adaptive Sliding Mode Control for Upper Limb Rehabilitation With Disturbance Observer

Abstract

This paper proposes a neural network-based adaptive sliding mode controller combined with a nonlinear disturbance observer to enhance the stability and precision of the upper limb rehabilitation robot in uncertain environments. The upper limb movement intention is initially captured using an optical motion capture system and a surface electromyography acquisition system. An adaptive sliding mode control method, powered by a neural network, dynamically adjusts the controller's parameters to effectively address system uncertainties and external disturbances. The nonlinear disturbance observer in the controller helps identify and mitigate disturbances from the external environment, including Fourier-type, power-type, and mixed disturbances. Furthermore, the stability of the human-machine interaction controller is rigorously verified using the Lyapunov theorem. Simulation results demonstrate that the proposed neural network-based adaptive sliding mode control method significantly improves the performance and robustness of the upper limb rehabilitation robot.