Adaptive NN Stabilization of Uncertain Dynamic Nonholonomic Systems

摘要

In this paper, an adaptive neural network (NN) controller is proposed for the stabilization of dynamic nonholonomic systems with unknown inertia parameters and disturbances. Firstly, to facilitate control system design, the nonholonomic kinematic subsystem is transformed into a skew-symmetric form and the properties of the overall systems are discussed. Then, an adaptive NN controller is presented to guarantee the outputs of the dynamic subsystem (the inputs for the kinematic subsystem) to track the given auxiliary signals which are designed for the stabilization of kinematic subsystem. Simulation study on the control of a unicycle wheeled mobile robot has shown the effectiveness of the method.