Uncertain Bound Estimation for Robustness to the Robot Manipulators Using Feedforward Neural Network

In this paper, an intelligent adaptive robust compensator is developed to eliminate the effects of system uncertainties for tracking control of robot manipulators. For controller design, the prior information of the bound of uncertainties is not required but we estimate this bound by using feed forward neural network. Lyapunov approach will be used to show that the filtered tracking error and neural network weight error are uniformly ultimately bounded. Finally, simulation studies are carried out for a two-link robot manipulator to show the effectiveness of the control scheme.