An Iterative Learning Algorithm Based on RBF Neural Network in Upper Limb Rehabilitation Robot

Abstract

Aiming at the non-linearity and uncertainty of patient spastic disturbance in the trajectory tracking control of upper limb rehabilitation robot, an iterative learning control algorithm is proposed based on RBF neural network. This paper considers repetitive nature of the rehabilitation robot system, the algorithm combines a single hidden layer feedforward neural network with iterative learning. In the upper limb rehabilitation process, the algorithm accelerate the convergence speed of the trajectory tracking error, and quickly suppress the interference in the interference environment. The Lyapunov stability theory is used to prove the globally asymptotic stability of the closed-loop system, then simulation proves the feasibility and effectiveness of the proposed algorithm.