Discrete time neural control of a nonholonomic mobile robot integrating stereo vision feedback

In this paper, we present a discrete time neural controller for driving a nonholonomic mobile robot integrating stereo camera sensos. The proposed approach is based on a discrete-time high order neural network (RHONN) trained with an extended Kalman filter (EKF). The desired trjectory of the robot is computed during the navigation process using the stereo camera sensor. Simulation result is presented to show the effectiveness of the proposed control scheme.