Adaptive H∞ Tracking Control Design via Neural Networks of a Constrained Robot System

In this paper, a nonlinear adaptive neural network tracking control with a guaranteed H∞performance is proposed for a constrained robot manipulator with plant uncertainties. The neural network is used to learn the unknown dynamics by an adaptive algorithm. Moreover, a force sensor is built to measure the forces and torques between the experimental robot UArm II end-effector and the environment. Finally, results obtained from the implementation of the proposed controller in the manipulator UArm II, under a constrained movement, are presented.