Robust neural network/proportional tracking controller with guaranteed global stability

Abstract

A robust neural network is proposed for use with a proportional fixed control scheme for robot control systems. A stability analysis is included based on sector theory. A special normalized learning algorithm is used to train the neural network, which eliminates the need for a bounded regression signal being input to the system. Furthermore, an adaptive dead zone scheme is employed to enhance the robustness of the control system against disturbances. A complete stability and convergence proof is included. The selection of the dead zone does not require knowledge of the upper bound of the disturbance, which is usually unknown for the robot control system. Simulation results are presented to demonstrate the effectiveness of the proposed robust control algorithm.