Learning from output feedback adaptive neural control of robot

Abstract

An adaptive neural control algorithm is proposed for completely unknown robot with only output measurement using RBF networks and high-gain observer.The designed adaptive neural controller not only guarantees uniformly ultimately bounded of all signals in the closed-loop system,but also achieves the deterministic learning of the unknown closed-loop system dynamics along periodic tracking orbit.The learned knowledge can be used to improve control performance,and can also be recalled and reused in the same or similar control task to save time and energy.Simulation results show the effectiveness of the proposed approach.