Abstract
In this article, an approach to improving the performance of robot continuous-path operation is proposed. This approach utilizes a multilayer feedforward neural network to compensate for model uncertainty associated with the robotic operation. Closed-loop stability and performance are analyzed. It is shown that the closed-loop system is stable in the sense that all signals are bounded; it is further proved that the performance of the closed-loop system is improved in the sense that certain erro measure of the closed-loop system decreases as the network learning process is iterated. These analytical results are confirmed by computer simulation. The effectiveness of the proposed approach is demonstrated through a laboratory experiment.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Arai, F., Rong, L. & Fukuda, T. (1993). Asymptotic Convergence of Feedback Error Learning Method and Improvement of Learning Speed. Proceedings of the 1993 IEEE/RSJ International Conference on Intelligent Robots and Systems, Yokohama, Japan, 761–767.
Ciliz, M.K. & Işik, C. (1990). Trajectory Following Control of Robotic Manipulators Using Neural Networks. Proceedings of the 5th IEEE International Symposium on Intelligent Control, Philadelphia, Pennsylvania, 536–540.
Corless, M. & Leitmann, G. (1981). Continuous State Feedback Guaranteeing Uniform Ultimated Boundedness for Uncertain Dynamic Systems. IEEE Transactions on Automatic Control, AC-26, No. 5, 1139–1144.
Craig, J. (1986). Introduction to Robotics: Mechanics and Control. Reading, MA: Addison-Wesley.
Cybenko, G. (1989). Approximation by Superposition of a Sigmoidal Function. Mathematics of Control, Signals, and Systems, Vol. 2, 303–314.
Denker, J., Schwartz, D., Witter, B., Solla, S., Howard, R. & Jackel, L. (1987). Large Automatic Learning, Rule Extraction, and Generalization. Complex Systems, Vol. 1, 877–922.
Dorf, R.C. (1992). Modern Control Systems, Reading, Massachusetts: Addison-Wesley Publishing Company.
Glesner, M. & Pöchmüller, W. (1994). Neurocomputers: An Overview of Neural Networks in VLSI. London: Chapman & Hall.
Gomi, H. & Kawato, M. (1990). Learning Control for a Closed Loop System Using Feedback-Error-Learning. Proceedings of the 29th Conference on Decision and Control, Honolulu, Hawaii, 3289–3294, 1990.
Kuan, A. & Bavarian, B. (1992). Control of Universal 3DOF Robot Manipulator: A Neural Network Approach. Proceedings of the Japan-USA Symposium on Flexible Automation, San Francisco, CA, 249–255.
Lawryshyn, Y.A. (1993). Robot Link and Contact Surface Dynamic Interaction: An Experimental Study of Contact Stability. M.A.Sc. Thesis, Department of Mechanical Engineering, University of Toronto.
Lokhorst, D. M. (1990). An Approach to Force and Position Control of Robots: Theory and Experiments. M.A.Sc. Thesis, Department of Mechanical Engineering, University of Toronto, Toronto, Canada.
McClelland, J.L. & Rumelhart, D.E. (Eds.), (1986). Parallel Distributed Processing. Vol. I, Cambridge, Massachusetts: MIT Press.
Miller, W.T., Sutton, R.S. & Werbos, P.J. (Eds.) (1990). Neural Networks for Control. Cambridge, Massachusetts: MIT Press.
Muller, B. & Reinhardt, J. (1990). Neural Networks: An Introduction. Berlin: Springer-Verlag, 1990.
Okuma, S. & Ishiguro, A. (1990). A Neural Network Compensator for Uncertainties of Robotic Manipulators. Proceedings of the 29th Conference on Decision and Control, Honolulu, Hawaii, 3303–3307.
Ortega, R. & Spong, M.W. (1989). Adaptive Motion Control of Rigid Robots: a Tutorial. Automatica, Vol. 25, No.6, 877–888.
Spong, M.W. & Vidyasagar, M. (1989). Robot Dynamics and Control. New York: John Wiley & Sons.
Spong, M.W. & Vidyasagar, M. (1987). Robust Linear Compensator Design for Nonlinear Robotic Control. IEEE Journal of Robotics and Automation, Vol. RA-3, No. 4, 345–351.
Vidyasagar, M., (1992). Nonlinear Systems Analysis. 2nd ed., New Jersey: Prentice Hall.
Yabuta, T. & Yamada, T. (1991). Learning Control Using Neural Networks. Proceedings of the 1991 IEEE International Conference on Robotics and Automation, Sacramento, California, 740–745.
Yanovski, G., (1991). Experimental Analysis of a Robust Centralized/Decentralized Controller for Robotic Manipulators. M.E. Thesis, Department of Electrical Engineering, University of Toronto.
Zomaya, A.Y. & Nahban, T.M. (1993). Centralized and Decentralized Neuro-Adaptive Robot Controllers. Neural Networks, Vol. 6, 223–244.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Chen, P.C.Y., Mills, J.K. & Smith, K.C. Performance improvement of robot continuous-path operation through iterative learning using neural networks. Mach Learn 23, 191–220 (1996). https://doi.org/10.1007/BF00117444
Issue Date:
DOI: https://doi.org/10.1007/BF00117444