Real-time Motion Control of a Nonholonomic Mobile Robot with Unknown Dynamics∗ TIEMIN HU and SIMON

In this paper, real-time fine motion control of a nonholonomic mobile robot is investigated, where the robot dynamics is completely unknown and is subject to significant uncertainties. A novel neural network based real-time controller is developed. The neural network assumes a single layer structure, by taking advantage of the robot regressor dynamics that express the highly nonlinear robot dynamics in a linear form in terms of the known and unknown robot dynamic parameters. The learning algorithm is computationally efficient. The system stability and the converge of tracking errors to zero are rigorously proved using a Lyapunov theory. The real-time fine control of mobile robot is achieved through the on-line learning of the neural network without any off-line learning procedures. In addition, the developed controller is capable of compensating sudden changes of robot dynamics or disturbance. The effectiveness and efficiency of the proposed controller is demonstrated by simulation studies.