Indirect adaptive tracking control of a nonholonomic mobile robot via neural networks

This paper presents the design and implementation of a novel adaptive trajectory tracking controller for a nonholonomic wheeled mobile robot (WMR) with unknown parameters and uncertain dynamics. The learning ability of neural networks is used to design a robust adaptive backstepping controller that does not require the knowledge of the robot dynamics. The kinematic controller gains are tuned on-line to minimize the velocity error and improve the trajectory tracking characteristics. The performance of the proposed control algorithm is verified and compared with the classical backstepping controller through simulation and experiments on a commercial mobile robot platform.