Robust adaptive control of robotic manipulators using neural networks: Application to a two link planar robot

Abstract

A PD neural network (NN)-based adaptive controller design is presented in this paper for trajectory tracking of robotic manipulators subject to external disturbances and noise measurement. The neural networks are employed to approximate the nonlinearities in dynamic model of the robot to improve the performance of the classical PD controller based on the filtered error approach. The augmented Lyapunov function is used to guarantee the boundedness of the tracking error and derive the adaptation law for the neural network weights. This paper also presents the effect of robust modifications such as σ-modification and e-modification on the performance of adaptation laws in the approximation process and the performance of the controller. The effectiveness of the controller is demonstrated through computer simulation on the two-link planer robot.