Adaptive PD Neural Network Tracking Control for the Uncertain Robot Manipulator with Unmatched Disturbance*

This paper addressed the tracking control problem of the robot manipulator with uncertainties and unmatched disturbance by PD control based on adaptive neural network. Adaptive control methods can deal with the control problem of systems with nonlinear and uncertain dynamics, which use measured data of system trajectory in order to learn and compensate the uncertainties and external disturbances. In this work, a nominal PD control law is used to achieve a sub-optimal performance, and a scheme based on a neural network is implemented to act as a nonlinear compensation whose task is to improve the performance of the nominal controller. A two-degree-of-freedom robot manipulator is proposed to validate the proposed scheme.