Neural Network Robust Control for a Nonholonomic Mobile Robot including Actuator Dynamics

In this paper, a control strategy that integrates a kinematic controller and an adaptive wavelet neural network (AWNN) controller for nonholonomic mobile robots including actuator dynamics is presented. The AWNN control system adopts a wavelet neural network (WNN) with accurate approximation capability to represent the unknown dynamics of the robotic system. It also uses a robust term to confront the inevitable approximation errors due to the finite number of wavelet bases functions and to disturbances. Based on the Lyapunov stability theorem, an adaptive learning algorithm learns the parameters of weight, dilation, and translation of the WNN on line. The tracking stability of the closed loop system, the convergence of the WNN weight-updating process and boundedness of WNN weight estimation errors are all guaranteed. The effectiveness and superiority of the proposed controller are demonstrated by simulation and experiment studies.