Discrete-time decentralized inverse optimal neural control combined with sliding mode for mobile robots

Many sophisticated analytical procedures for control design are based on the assumption that the full state vector is available for measurement. When this is not the case, is required an observer. In this paper, the super-twisitng second-order sliding-mode algorithm is modified in order to design an observer for the actuators; then a recurrent high order neural network (RHONN) is used to identify the plant model, under the assumption of all the state is available for measurement. The learning algorithm for the RHONN is implemented using an Extended Kalman Filter (EKF) algorithm. On the basis of the identifier a controller which uses inverse optimal control, is designed to avoid solving the Hamilton Jacobi Bellman (HJB) equation. The proposed scheme is implemented in discrete-time to control a KUKA youBot.