Adaptive Tracking Control of Mobile Robots based on Neural Network and Sliding Mode Methods

In this paper, an adaptive neural network sliding mode variable structure control strategy is proposed for the motion control of a nonholonomic mobile robot. Firstly, the pose tracking loop is established based on the kinematic model of the mobile robot, and the kinematic controller is designed by the backstepping method to solve the control relationship between pose and tracking velocity. Secondly, considering the dynamic model of the mobile robot, the velocity tracking loop is designed, and a sliding mode variable structure torque controller based on the combined approximation law is constructed. An adaptive neural sliding mode dynamic controller is designed based on the proportional-integral sliding mode control idea. The adaptive radial basis function neural networks (RBFNN) is used to compensate for the external disturbance, which effectively eliminates the influence of system uncertain parameters and external disturbance. Finally, the stability of the proposed system is proved according to Lyapunov’s theory. The simulation results verify the effectiveness and correctness of the control strategy.