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

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. A lot of research has dealt with the tracking control problem: [1]–[4] were based on VSS (variable structure system) theory, [5]–[10] on adaptive theory, and [11]–[12] on Fuzzy logic. 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. This paper is organized as follows. Section 2 presents NN System. In Section 3, several properties of robot dynamics are introduced. In Section4, the adaptive control scheme is proposed, where the NN is utilized to compensate the uncertainties of the robot manipulator. The robust adaptive law is also designed. The algorithms that reduce the number of neural are proposed based on the properties of robot dynamics and uncertainties in Section 5. The decomposition algorithm of uncertainty function and results of computer simulations for the control scheme and experiment on dual-arm robot are also drawn in Section 6. In Section 7, we obtain the conclusions and discussion.