Abstract
This paper shows the results obtained in controlling a mobile robot by means of local recurrent neural networks based on a radial basis function (RBF) type architecture. The model used has a Finite Impulse Response (FIR) filter feeding back each neuron's output to its own input, while using another FIR filter as a synaptic connection. The network parameters (coefficients of both filters) are adjusted by means of the gradient descent technique, thus obtaining the stability conditions of the process. As a practical application the system has been successfully used for controlling a wheelchair, using an architecture made up by a neurocontroller and a neuroidentifier. The role of the latter, connected up in parallel with the wheelchair, is to propagate the control error to the neurocontroller, thus cutting down the control error in each working cycle.
Similar content being viewed by others
References
Campolucci, P., Uncini, A., Piazza, F. and Rao, B. D.: On-line learning algorithms for locally recurrent neural networks, IEEE Transactions on Neural Networks 10(2) (1999), 253–271.
Elman, J. L.: Finding structure in time, Cognitive Science 14 (1990), 179–211.
Narendra, K. S. and Parthasarathy, K.: Identification and control of dynamical systems using neural networks, IEEE Transactions on Neural Networks 1(1) (1990), 4–27.
Tsoi, A. C. and Black, A. D.: Locally recurrent globally feedforward networks: a critical review of architectures, IEEE Transactions on Neural Networks 5(2) (1994), 229–239.
Ciocoiu, I. B.: Radial base function networks with FIR/IIR synapses, Neural Processing Letters 3 (1996), 17–22.
Sastry, P. S., Santharam, G. and Unnikrishnan, K. P.: Memory neuron networks for identification and control of dynamical systems, IEEE Transactions on Neural Networks 5(2) (1994), 30–319.
Sivakumar, S. C., Robertson, W. and Phillips, W. J.: On-line stabilitation of block-diagonal recurrent neural networks, IEEE Transactions on Neural Networks 10(1) (1999), 167–175.
Ku, C. C. and Lee, K. Y.: Diagonal recurrent neural networks for dynamic systems control, IEEE Transactions on Neural Networks 6(1) (1995), 144–156.
Etxebarria, V.: Adaptive control of discrete systems using neural networks, IEE Proc. Control Theory Appl. 141(4) (1994), 209–215.
Zhang, Y., Sen, P. and Hearn, G. E.: An on-line trained adaptive neural controller, IEEE Control Systems 15(5) (1995), 67–75.
Yuan, M., Poo, A.N. and Hong, G. S.: Direct neural control system: nonlinear extension of adaptive control, IEE Proc. Control Theory Appl. 142(6) (1995), 661–667.
Maeda, Y. and Figueiredo, R. J. P.: Learning rules for neuro-controller via simultaneous perturbation, IEEE Transactions on Neural Networks 8(5) (1997), 1119–1130.
Noriega, J. R. and Wang, H.: A direct adaptive neural-network control for unknown nonlinear systems and its application, IEEE Transactions on Neural Networks 9(1) (1998), 27–34.
Boquete, L., García, R., Barea, R. and Mazo, M.: Neural control of the movements of a wheelchair, J. Intelligent Robotic Systems 25 (1999), 213–226.
Boquete, L., Barea, R., García, R., Mazo, M. and Espinosa, F.: Identification and control of a wheelchair using recurrent neural networks, Engineering Applications of Artificial Intelligence 12(4) (1999), 443–452.
Hunt, K. J. and Sbarbaro, D.: Neural networks for non linear internal model control, IEE Proceedings-d 138(5) (1991), 431–438.
Acosta, L., Méndez, J. A., Torres, S., Moreno, L. and Marichal, G. N.: On the design and implementation of a neuromorphic selft-tuning controller, Neural Processing Letters 9(3) (1999), 229–242.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Boquete, L., Bergasa, L.M., Barea, R. et al. Using a New Model of Recurrent Neural Network for Control. Neural Processing Letters 13, 101–113 (2001). https://doi.org/10.1023/A:1011375420498
Issue Date:
DOI: https://doi.org/10.1023/A:1011375420498