A Neural Network Sliding Mode Controller with Application to Robotic Manipulator

Abstract

A sliding mode control strategy compensated by neural network is proposed, and that is applied to robotic trajectory control. First, a three-layer neural network is used to compensate the uncertainties in the robotic system. Then the structure of sliding mode controller with neural network compensation and the learning algorithm of the neural network are designed based on Lyapunov theorem to guarantee the stability of the system and improve the dynamic performance of the system. The simulation results show that the proposed control strategy can not only reduce the phenomenon of chattering in effect, but also has good robustness and dynamic performance