A stable neural network-based adaptive controller for robot manipulators

Abstract

A stable neural network-based adaptive controller design for integrating a neural network (NN) approach with an adaptive implementation of the sliding mode control with the sector is presented in this paper for the trajectory tracking control of a robot with unknown nonlinear dynamics. The sliding mode control with the sector serves two purposes, one is to provide the global stability of the closed loop system when the system goes out of the control, the other is to improve the tracking performance within the NN approximation region. The system stability and tracking error convergence are proved using Lyapunov techniques that yield a NN weight tuning algorithm. Finally, the effectiveness of the proposed control approach is illustrated through simulation studies.