Abstract
This paper deals with the problem of identifying and controlling nonlinear time varying plants. The algorithm is defined to reach the following objectives. First, to achieve a quick and efficient identification, the plant is represented by a linear model defined with hyperplanes. They are found by minimizing errors between the last measures and their estimations. Secondly, to obtain a smooth control and a good accuracy, control law is derived from the optimization of a quadratic criteria defined to minimize outputs errors and the successive derivatives of the control. This identification and control law overcome the problems met in adaptive control based on neural networks, for which learning is often long, and where an important number of neurons and weights is required to get accurate results. Finally the proposed approach is applied to control a two-link planar robot manipulator and a PUMA 560 robot.
Similar content being viewed by others
References
Bolourchi, F. and Hess, R. A.: Nonlinear model reference adaptive control using tap-delay filters, IEEE Systems, Man and Cybernetics 22(2) (1992).
Chen, D. S. and Jain, R. C.: A robust back propagation learning algorithm for function approximation, IEEE Transactions on Neural Networks 5(3) (1994).
Corke, P. I.: A robotics toolbox for MATLAB, IEEE Robotics and Automation Magazine 3(1) (1996), 24–32.
Gautier, M.: Dynamic identification and control of robot manipulator, in: Proceedings of the Second International Symposium on Methods and Models in Automation and Robotics, MMAR 95, vol. 2 p. 517, 30 August–2 September, Miedzyzdroje, Poland.
Hunt, K., Shrbaro, D., Zbikowski, R. and Gauthrop, P. J.: Neural networks for control systems, A survey, Automatica 28(6) (1992), 1083–1112.
Morris, A. S. and Khemaissia, S.: A neural network based adaptive robot controller, Journal of Intelligent and Robotic Systems 15(1996), 3–10.
Narendra, K. S. and Parthasarathy, K.: Identification and control of dynamical systems using neural networks, IEEE Transactions on Neural Networks 1(1) (1990).
Polycarpou, M. and Ioannou, P. A.: Identification and control of nonlinear systems using neural networks models: Design and stability analysis, Tech. Rep. 91-09-01, Dpt of Elet. Eng. Systems, University of Southern California, Los Angeles, CA, 1991.
9. Rovithakis, G. A. and Christodoulou, M. A.: Adaptive control of unknown plants using dynamical neural networks, IEEE SMC 24(3) (1994).
Rovithakis, G. A. and Christodoulou, M. A.: Direct adaptive regulation of unknown nonlinear systems via dynamic neural networks, IEEE Trans. Systems Man and Cybernetics 25(12) (1995), 1578–1594.
Sadegh, N.: A nodal link perceptron network with applications to control of a nonholonomic system, IEEE Transactions on Neural Networks 6(6) (1995).
Tzafestas, S. G.: Adaptive, robust and rule-based control of robotic manipulators, in S. G. Tzafestas (ed.), Intelligent Robotic Systems, Marcel Dekker, 1991, pp. 3–42.
Tzafestas, S. G.: Neural networks in robot control, in S. G. Tzafestas and H. B. Verbruggen (eds), Artificial Intelligence in Industrial Decision Making, Control and Automation, Kluwer, 1995, pp. 327–387.
Yang, H. W. and Choi, J. S.: A design of a hybrid control system using neural networks, in Proc. IEEE Internat. Conf. on Systems, Man and Cybernetics, vol. 2, 1995, pp. 1255–1260.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Canart, R., Borne, P. Implementation of Adaptive Hyperplanes for the Determination of Robust Control. Journal of Intelligent and Robotic Systems 18, 289–308 (1997). https://doi.org/10.1023/A:1007952315886
Issue Date:
DOI: https://doi.org/10.1023/A:1007952315886