Adaptive neural network control and learning for uncertain robot

Abstract

This paper investigates the adaptive neural network control and learning for the electrically-driven robot with unknown system dynamics.A stable adaptive neural network(NN) controller is first designed,and the radial basis function(RBF) neural-network is used to approximate the unknown closed-loop system dynamics of electrically-driven robot.The stable adaptive tuning laws of network parameters are derived in the sense of the Lyapunov stability theory.Partial persistent excitation(PE) condition of some internal signals in the closed-loop system is satisfied in the control process of tracking a recurrent reference trajectory.Under the PE condition,the proposed adaptive NN controller is rigorously shown to be capable of accurate identification of the uncertain electrically-driven robot dynamics in the stable control process.Subsequently,a novel NN learning control method which effectively utilizes the learned knowledge without re-adapting to the unknown electrically driven robot dynamics is proposed to achieve the closed-loop stability and improve the control performance.Simulation studies are performed to demonstrate the effectiveness of the proposed method.