Real-time adaptive control of robot manipulator based on neural network compensator

This paper presents two kinds of adaptive control schemes for robot manipulator which has the parametric uncertainties. In order to compensate these uncertainties, we use the NN (neural network system) that has the capability to approximate any nonlinear function over the compact input space. In the proposed control schemes, we need not derive the linear formulation of robot dynamic equation and tune the parameters. We also suggest the robust adaptive control laws in all proposed schemes for decreasing the effect of approximation error. To reduce the number of neural of network, we consider the properties of robot dynamics and the decomposition of the uncertainty function. The proposed controllers are robust not only to the structured uncertainty such as payload parameter, but also to the unstructured one such as friction model and disturbance. The validity of the control scheme is shown by computer simulations and experiment of dual-arm robot manipulator.

1. Introduction

INTRODUCTION IN the recent decade, increasing attention has been given to the tracking control of robot manipulators. Tracking control is needed to make each joint track a desired trajectory. Robots have to face many uncertainties in their dynamics, in particular structured uncertainty, such as payload parameter, and unstructured one, such as friction and disturbance. It is difficult to obtain the desired control performance when the control algorithm is only based on the robot dynamic model. To overcome these difficulties, in this paper we propose the adaptive control schemes which utilize a neural network as a compensator for any uncertainty. To reduce the error between the real uncertainty function and the compensator, we design simple and robust adaptive laws based on Lyapunov stability theory. In the proposed control schemes, the NN compensator has to see many neural because uncertainties depend on all state variables. To overcome this problem, therefore, we introduce the control schemes in which the number of neural of the NN compensator can be reduced by using the properties of robot dynamics and uncertainties. By computer simulations, it is verified that the NN is capable to compensate the uncertainties of robot manipulator.