Practical point stabilization of a nonholonomic mobile robot using neural networks

Abstract

A control structure that makes possible the integration of a kinematic controller and a neural network (NN) computed-torque controller for nonholonomic mobile robots is presented. This control algorithm is applied to the practical point stabilization problem i.e. stabilization to a small neighborhood of the origin. The NN controller proposed in this work can deal with unmodelled bounded disturbances and/or unstructured unmodelled dynamics in the vehicle. Online NN weight tuning algorithms that do not require off-line learning yet guarantee small tracking errors and bounded control signals are utilized.