Applying posture identifier in designing an adaptive nonlinear predictive controller for nonholonomic mobile robot

Abstract

This paper presents a trajectory tracking controller for a nonholonomic mobile robot using an optimization algorithm based predictive feedback control and an adaptive posture identifier model while following a continuous and a non-continuous path. The posture identifier model is a modified Elman neural network that describes the kinematics and dynamics of the mobile robot model. The feedforward neural controller is trained off-line and its adaptive weights are adapted on-line to find the reference torques, which controls the steady-state outputs of the mobile robot system. The feedback neural controller is based on the posture neural identifier and quadratic performance index prediction algorithm to find the optimal torque action in the transient state for N-step-ahead prediction. General back propagation algorithm is used to learn the feedforward neural controller and the posture neural identifier. Simulation results and experimental work show the effectiveness of the proposed adaptive nonlinear predictive control algorithm; this is demonstrated by the minimized tracking error and the smoothness of the torque control signal obtained, especially with regards to the external disturbance attenuation problem.