Hostname: page-component-78c5997874-xbtfd Total loading time: 0 Render date: 2024-11-10T14:09:48.215Z Has data issue: false hasContentIssue false
  • English
  • Français

A study of neural network control of robot manipulators*

Published online by Cambridge University Press:  09 March 2009

Seul Jung  and
T. C. Hsia
Seul Jung
Affiliation:
Robotics Research Laboratory, Department of Electrical and Computer Engineering, University of California at Davis, Davis, CA 95615 (USA)
T. C. Hsia
Affiliation:
Robotics Research Laboratory, Department of Electrical and Computer Engineering, University of California at Davis, Davis, CA 95615 (USA)
Get access Rights & Permissions [Opens in a new window]

Summary

The basic robot control technique is the model based computer-torque control which is known to suffer performance degradation due to model uncertainties. Adding a neural network (NN) controller in the control system is one effective way to compensate for the ill effects of these uncertainties. In this paper a systematic study of NN controller for a robot manipulator under a unified computed-torque control framework is presented. Both feedforward and feedback NN control schemes are studied and compared using a common back-propagation training algorithm. Effects on system performance for different choices of NN input types, hidden neurons, weight update rates, and initial weight values are also investigated. Extensive simulation studies for trajectory tracking are carried out and compared with other established robot control schemes.

Keywords

Neural networksSimulation studiesRobot control.
Type
Articles
Information
Robotica , Volume 14 , Issue 1 , January 1996 , pp. 7 - 15
Copyright
Copyright © Cambridge University Press 1996

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

1.Chen, F.C., “Back propagation Neural Networks for Nonlinear Self-tuning Adaptive Control” IEEE Control System Magazine 10(3), 44–48 (1990).CrossRefGoogle Scholar
2.Chen, V.C. and Pao, Y.H., “Learning Control with Neural Network” IEEE Magazine 1448–1453 (1989).Google Scholar
3.Fukuda, T. and Shibata, T., “Theory and Applications of Neural Networks for Industrial Control Systems” IEEE Trans, on Industrial Electronics 39, 472–489 (1992).CrossRefGoogle Scholar
4.Kraft III, L.G. and Campagna, D.P., “A Summary Comparison of CMAC Neural Network and Traditional Adaptive Control Systems” Neural Networks for Control (The MIT Press, Cambridge, Mass., 1990) pp. 143–169.Google Scholar
5.Ku, C.C. and Lee, K.Y., “Diagonal Recurrent Neural Networks for Nonlinear System Control” American Control Conference(1992) pp. 545–549.Google Scholar
6.Kuschewski, J.G., Hui, S. and Zak, S.H., “Application of Feedforward Neural Networks to Dynamical System Identification and Control” IEEE Trans, on Control Systems Technology 1, 37–49 (y).CrossRefGoogle Scholar
7.Low, T.S., Lee, T.H. and Lim, H.K., “A Methodology for Neural Network Training for Control of Drives with Nonlinearities” IEEE Trans, on Industrial Electronics 40, No. 2, 243–249 (1993).CrossRefGoogle Scholar
8.Narendra, K. and Parthasarathy, K., “Identification and Control of Dynamical Systems Using Neural Networks” IEEE Trans, on Neural Networks 1, 4–27 (1990).CrossRefGoogle ScholarPubMed
9.Tseng, H.C. and Hwang, V.H., “Neural Network for Nonlinear Servomechanism” Proc. of IEEE International Conference on Robotics and Automation(1991) pp. 2414–2417.Google Scholar
10.Yabuta, T. and Yamada, T., “Possibility of Neural Networks Controller for Robot Manipulator” Proc. of IEEE International Conference on Robotics and Automation(1990) pp. 1686–1691.Google Scholar
11.Horne, B., Jamshidi, M. and Vadiee, N., “Neural Networks in Robotics: A survey” Intelligent and Robotic Systems 3, 61–66(1990).Google Scholar
12.Ishiguro, A., Furuhashii, T., Okuma, S. and Uchikawa, Y., “A Neural Network Compensator for Uncertainties of Robot Manipulator” IEEE Trans, on Industrial Electronics 39, 61–66 (12, 1992).CrossRefGoogle Scholar
13.Katie, D., “Using Neural Network Model for Learning Control of Manipulation Robot” Proc. of Intelligent Autonomous Systems (1989) pp. 424–433.Google Scholar
14.Kwato, M., Kurukkawa, K. and Suzuki, R., “A Hierarchical Neural Network Model for Learning of Voluntary Movement” Biological Cybernetics 169–185 (1987).CrossRefGoogle Scholar
15.Miyamoto, H., Kawato, M., Setoyama, T. and Suzuki, R., “Feedback Error Learning Neural Network for Trajectory Control of a Robotic Manipulator” IEEE Trans, on Neural Networks 1, 251–265 (1988).CrossRefGoogle Scholar
16.Gehlot, N.S. and Alsina, P.J., “A Comparison Control Strategies of Robotic Manipulators Using Neural Networks” International Conference on IECON(1992) pp. 688–693.Google Scholar
17.Ozaky, T., Suzuki, T., Furuhashi, T., Okuma, S. and Uchikawa, Y., “Trajectory Control of Robotic Manipulators Using Neural Networks” IEEE Trans, on Industrial Electronics 38, 195–202 (1991).CrossRefGoogle Scholar
18.Yuh, J. and Lakshmi, R., “An Intelligent Control System for Remotely Operated Vehicles” J. of Ocean Engineering 18, 55–62 (1993).CrossRefGoogle Scholar
19.Lewis, F.L., Liu, K. and Yesildirek, A., “Neural Net Robot Controller with Guaranteed Tracking Performance” Proc. of Intelligent Control (1993) pp. 225–231.Google Scholar
20.Psaltis, D., Sideris, A. and Yamamura, A., “A Multilayered Neural Network Controllers” IEEE Control System Magazine 17–21 (1986).CrossRefGoogle Scholar
21.Jung, S. and Hsia, T.C., “Neural Network Inverse Control of Robot Manipulator” International Conference on Neural Information Processing(Seoul,1994) pp. 603–608.Google Scholar
22.Craig, J.J., Hsu, Ping and Sastry, S.S., “Adaptive Control of Mechanical Manipulators” Proc. of the IEEE International Conference on Robotics and Automation,(1986) 1, pp. 190–195.Google Scholar