Abstract
In this paper, the application of neural networks and neurofuzzy systems to the control of robotic manipulators is examined. Two main control structures are presented in a comparative manner. The first is a Counter Propagation Network-based Fuzzy Controller (CPN-FC) which is able to self-organize and correct on-line its rule base. The self-tuning capability of the fuzzy logic controller is attained by taking advantage of the structural equivalence between the fuzzy logic controller and a counterpropagation network. The second control structure is a more familiar neural adaptive controller based on a feedforward (MLP) network. The neural controller learns the inverse dynamics of the robot joints, and gradually eliminates the model uncertainties and disturbances. Both schemes cooperate with the computed torque control algorithm, and in that way the reduction of their complexity is achieved. The ability of adaptive fuzzy systems to compete with neural networks in difficult control problems is demonstrated. A sufficient set of numerical results is included.
Similar content being viewed by others
References
Kuc, T. Y., Nom, K., and Lee, J. S.: An iterative learning control of robot manipulator, IEEE Trans. Robot. Automat. 7(6) (1991), 835–842.
Kawato, M., Uno, Y., Isobe, M., and Suzuki, R.: Hierarchical neural network model for voluntary movement with application to robots, IEEE Control Systems Mag. 8 (April 1988), 8–16.
Narendra, K. S. and Parthasarathy, K.: Identification and control of dynamical systems using neural networks, IEEE Trans. Neural Networks 1 (1990), 4–27.
Nguyen, D. H. and Widrow, B.: Neural networks for self-learning control systems, IEEE Control Systems Mag. 10 (1990), 18–23.
Chen, F. C.: Back-propagation neural networks for nonlinear self-tuning adaptive control, IEEE Control Systems Mag. 10 (1992), 193–224.
Miller, W. T., Hewes, R. P., Glanz, F. H., and Kraft, L. G.: Real-time dynamic control of an industrial manipulator using a neural-network based learning controller, IEEE Trans. Robot. Automat. 6(1) (1990), 1–9.
Billings, S. A., Jamaluddin, H. B., and Chen, S.: Properties of neural networks with applications to modelling nonlinear dynamical systems, Internat. J. Control 55(1) (1992), 193–224.
Kuschewski, J. G., Hui, S., and Zak, S. H.: Application of feedforward neural networks to dynamical system identification and control, IEEE Trans. Control Systems Technol. 1(1) (1993), 37–49.
Nie, J. and Linkens, D.: Fuzzy-Neural Control: Principles, Algorithms and Applications, Prentice-Hall, Englewood Cliffs, NJ, 1995, pp. 179–194.
Miyamoto, H., Kawato, M., Setoyama, T., and Suzuki, R.: Feedback-error learning neural network for trajectory control of a robot manipulator, IEEE Trans. Neural Networks 1 (1988), 251–265.
Haykin, S.: Neural Networks: A Compehensive Foundation, MacMillan, New York, 1994.
Morris, A. S. and Khemaissia, S.: Artificial neural network based intelligent robot dynamic control, in: A. M. S. Zalzala and A. S. Morris (eds), Neural Networks for Robotic Control: Theory and Applications, Ellis Horwood, 1996, pp. 26–63.
Astrom, K. J. and Wittenmark, B.: Adaptive Control, Addison Wesley, Reading, MA, 1989.
Hecht-Nielsen, R.: Applications of counterpropagation networks, Neural Networks 1 (1988), 131–139.
Kohonen, T.: Self-Organizing and Associative Memory, Springer, Berlin, 1988.
Grossberg, S.: Competitive learning: From interactive activation to adaptive resonance, Cognitive Science 11 (1987), 23–63.
Khemaissia, S. and Morris, A. S.: Neuro-adaptive control of robotic manipulators, Robotica 11 (1993), 465–473.
Tzafestas, S. G. and Tzafestas, C. S.: Fuzzy and neural control: Basic principles and architectures, in: S. G. Tzafestas (ed.), Methods and Applications of Intelligent Control, Kluwer, Dordrecht/Boston, 1997, pp. 25–60.
Wang, L. X.: Adaptive Fuzzy Systems and Control: Design and Stability Analysis, Prentice Hall, Englewood Cliffs, NJ, 1994, pp. 9–28.
Lin, C. T.: Neural Fuzzy Control Systems with Structure and Parameter Learning, World Scientific, Singapore/London, 1994.
Kosko, B.: Neural Networks and Fuzzy Systems: A Dynamical Systems Approach to Machine Intelligence, Prentice-Hall, Englewood Cliffs, NJ, 1992.
Slotine, J. E. and Li, W.: Applied Nonlinear Control, Prentice-Hall, Englewood Cliffs, NJ, 1991.
Lin, C. K. and Wang, S. D.: Robust self-tuning rotated fuzzy basis function controller for robot arms, IEE Proceedings in Control Theory and Applications 144(4) (1997), 293–298.
Su, C. Y. and Stephanenko, Y.: Adaptive fuzzy control of a class of nonlinear systems, IEEE Trans. Fuzzy Systems 2(4) (1994), 285–294.
Yamaguchi, T., Takagi, T., and Mita, T.: Self-organizing control using fuzzy neural networks, Internat. J. Control 56(2) (1992), 415–419.
Watanabe, K. and Tzafestas, S. G.: Mean-value-based functional reasoning techniques in the development of fuzzy-neural network control systems, in: C. T. Leondes (ed.), Fuzzy Logic and Expert Systems Applications: Neural Network Techniques and Applications Series, Vol. 6, Academic Press, San Diego/London, 1988, pp. 243–284.
Watanabe, K., Hara, K., Koga, S., and Tzafestas, S. G.: Fuzzy-neural network controllers using the mean-value-based functional reasoning, Neurocomputing 9 (1995), 39–61.
Watanabe, K. and Tzafestas, S. G.: Learning algorithms for neural networks with the Kalman filters, J. Intell. & Robotic Systems 3 (1990), 305–319.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Tzafestas, S.G., Rigatos, G.G. Neural and Neurofuzzy FELA Adaptive Robot Control Using Feedforward and Counterpropagation Networks. Journal of Intelligent and Robotic Systems 23, 291–330 (1998). https://doi.org/10.1023/A:1008077807191
Issue Date:
DOI: https://doi.org/10.1023/A:1008077807191