A neural network and linear feedback based trajectory control method for robot manipulators

Abstract

This paper addresses the issue of trajectory tracking control based on a neural network controller for industrial manipulators. A new control scheme is proposed based on neural network technology and linear feedback approach for tracking a planned trajectory. The control system is established with two parallel subsystems designed separately. One is a linear controller based on state feedback with respect to a manifold that prescribed the desirable trajectory tracking performance, and another one is a learning controller designed with two neural networks. The former ensures trajectory tracking error regulation, the later is for force/torque generation required by the designed dynamic trajectory. A leaning law for online weight updating of the neural networks is derived such that the trajectory tracking accuracy is improved while the system remains in stable. Stability is analyzed using Lyapunov stability theory. Dynamic trajectory tracking control simulations are carried out on an industrial robot AdeptOne arm. The results demonstrate the effectiveness and usefulness of the proposed control scheme.