Neural network based robust tracking control for nonholonomic mobile robotic system

A hybrid tracking control scheme which combines RBF neural network with nonlinear H-infinity method is proposed. RBF neural network is designed to approximate the system uncertainty terms, and H-infinity control is utilized to achieve a desired robust tracking performance. Based on Lyapunov theory, the tracking errors of the closed-loop system are bounded. Besides, a specified H. tracking performance is obtained by the proposed robust hybrid control even though the disturbances are merely integral bounded. Compared the proposed method with the computed torque control under the uncertainties and external disturbances, simulation experiments show the effectiveness of the proposed control strategy.