ADAPTIVE-CONTROL OF A ROBOT USING NEURAL NETWORKS

被引：11

作者：

PHAM, DT

OH, SJ

机构：

[1] Intelligent Systems Laboratory, School of Electrical, Electronic and Systems Engineering, University of Wales College of Cardifff, CF2 1XH, Cardiff, P.O. Box 917, Newport Rd

来源：

ROBOTICA | 1994年 / 12卷

关键词：

MIMO SYSTEM; NEURAL NETWORK; ADAPTIVE CONTROL; ROBOTS;

D O I：

10.1017/S0263574700016891

中图分类号：

TP24 [机器人技术];

学科分类号：

080202 ; 1405 ;

摘要：

This paper describes an adaptive control system for an articulated robot with n joints carrying a variable load. The robot is a complex nonlinear time-varying MIMO plant with dynamic interaction between its inputs and outputs. However, the design of the control system is relatively straightforward and does not require any prior knowledge about the plant. This is because the control system is based on using neural networks which can capture the dynamic characteristics of the plant automatically. Three neural networks are employed in total, the first to learn the dynamics of the robot, the second to model its inverse dynamics and the third, a copy of the second neural network, to control the robot. The paper presents the results obtained for a planar two-joint robot. These results demonstrate the superior adaptive ability of the neural controller compared to a conventional PID controller.

引用

页码：553 / 561

页数：9

共 12 条

[1]

Spong M.W., Vidyasagar M., Robot Dynamics and Control, (1989)

[2]

Tomizuka M., Horowitz R., Anwar G., Jia Y.L., Implementation of adaptive techniques for motion controi of robotic manipulators ASME, J. Dynamical Systems, 110, pp. 62-69, (1988)

[3]

Craig J.J., Hsu P., Sastry S.S., Adaptive control of mechanical manipulators, Int. J. Robotics Research, 6, 2, pp. 16-28, (1987)

[4]

Slotine J.J., Li W., On the adaptive control of robot manipulators, Int. J. Robotics Research, 6, 3, pp. 49-59, (1987)

[5]

Miller W.T., Sutton R.S., Werbos P.J., Neural Networks for Control, (1990)

[6]

Psaltis D., Sideris A., Yamamura A., A multilayered neural network controller, IEEE Control Systems Magazine, pp. 17-21, (1989)

[7]

Kawato M., Uno Y., Isobe M., Suzuki R., Hierarchical neural network model for voluntary movement with application to robotics, IEEE Control Systems Magazine, pp. 8-16, (1999)

[8]

Colombano S.P., Compton M., Goal directed model inversion: adaptation to unexpected model changes, Proc. 4th International Conference on Neural Networks and Their Applications, pp. 271-278, (1991)

[9]

Miller W.T., Glanz F.H., Klaft L.G., Application of a general learning algorithm to the control of robotic manipulators, Int. J. of Robotics Research, 6, 2, pp. 84-98, (1987)

[10]

Makino H., Furuya N., Soma K., Chin E., Research and development of the Scara robot, Proc. 4th Int. Conf. on Production Engineering, pp. 885-890, (1980)

← 1 2 →