Abstract
This paper presents the results of simulation and control experiments using a recently proposed method for real-time switching among a pool of controllers. The switching strategy selects the current controller based on neural network estimates of the future system performance for each controller. This neural-network-based switching controller has been implemented for a simulated inverted pendulum and a level control system for an underwater vehicle in our laboratory. The objectives of the experiments presented here are to demonstrate the feasibility of this approach to switching control for real systems and to identify techniques to deal with practical issues that arise in the training of the neural networks and the real-time switching behavior of the system. This experimental work complements on-going theoretical investigations of the method which will be reported elsewhere.
Research supported by a CONICYT-IBD grant from the government of Uruguay, and the Organization of American States under grant F44395.
Research supported by DARPA under contract F33615-97-C-1012.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
J. Balakrishnan and K.S. Narendra. Adaptation and learning using multiple models, switching, and tuning. IEEE Control Systems Magazine, 15(3):37–51, Jun 1995.
J. Balakrishnan and K.S. Narendra. Adaptive control using multiple models. IEEE Trans. on Automatic Control, 42(2):171–187, Feb 1997.
Dimitri P. Bertsekas and John Tsitsiklis. Neuro-Dynamic Programming. Athena Scientific, Belmont, MA, 1996.
Michael S. Branicky. Stability of switched and hybrid systems. In Proc. 33rd IEEE Conf. Decision Control, volume 4, pages 3498–3503, Lake Buena Vista, FL, Dec 1994.
E.D. Ferreira and B.H. Krogh. Controller scheduling by neural networks. In Proc. 36th Conf. Decision Control, San Diego, CA, Dec 1997.
E.D. Ferreira and B.H. Krogh. Using neural networks to estimate regions of stability. In Proc. of 1997 American Control Conference, volume 3, pages 1989–1993, Albuquerque, NM, Jun 1997.
J. Malmborg, B. Berhardsson, and K.J. Aström. A stabilizing switching scheme for multi-controller systems. In Proc. of the IFAC World Congress, volume F, pages 229–234, San Francisco, California, USA, 1996. IFAC’96, Elsevier Science.
A.S. Morse. Supervisory control of families of linear set-point controllers-Part II: Robustness. In 34th IEEE Conference on Decision and Control, volume 2, pages 1750–1755, New York, USA, Dec 1995.
A.S. Morse. Supervisory control of families of linear set-point controllers-Part I: Exact matching. IEEE Trans. on Automatic Control, 41(10):1413–1431, Oct 1996.
L. Sha. A software architecture for dependable and evolvable industrial computing systems. In Proc. IPC’95, pages 145–156, Detroit, MI, May 1995.
Jean-Jacques. E. Slotine and Weiping Li. Applied Nonlinear Control. Prentice Hall Inc., 1991.
C.J.C.H. Watkins. Learning from Delayed Rewards. PhD thesis, Cambridge University, Cambridge, England, 1989.
P. Werbos. A menu of designs in reinforcement learning over time. In W.T. Miller III, R.S. Sutton, and P. Werbos, editors, Neural Networks for control, chapter 3. MIT Press, 2nd edition, 1991.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ferreira, E.D., Krogh, B.H. (1999). Controller Scheduling Using Neural Networks: Implementation and Experimental Results. In: Antsaklis, P., Lemmon, M., Kohn, W., Nerode, A., Sastry, S. (eds) Hybrid Systems V. HS 1997. Lecture Notes in Computer Science, vol 1567. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-49163-5_5
Download citation
DOI: https://doi.org/10.1007/3-540-49163-5_5
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65643-2
Online ISBN: 978-3-540-49163-7
eBook Packages: Springer Book Archive