Discrete-time neural identifier for electrically driven nonholonomic mobile robots

Abstract

A nonlinear discrete-time neural identifier for discrete-time unknown nonlinear systems, in presence of external and internal uncertainties are presented. This identifier is based on a discrete-time recurrent high order neural network (RHONN) trained with an extended Kalman filter (EKF)-based algorithm. Applicability of the scheme is illustrated via simulation for an electrically driven nonholonomic mobile robot.