Abstract
Applications of recurrent neural networks (RNNs) tend to be rare because training is difficult. A recent theoretical breakthrough [Jae01b] called Echo State Networks (ESNs) has made RNN training easy and fast and makes RNNs a versatile tool for many problems. The key idea is training the output weights only of an otherwise topologically unrestricted but contractive network. After outlining the mathematical basics, we apply ESNs to two examples namely to the generation of a dynamical model for a differential drive robot using supervised learning and secondly to the training of a respective motor controller.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Christaller, T., Jaeger, H., Kobialka, H.-U., Schoell, P., Bredenfeld, A.: Robot behavior design using dual dynamics. Tech. GMD Report (2000)
Arkin, R.C.: Behavior-based robotics. The MIT Press, Cambridge (1998)
Bredenfeld, A., Kobialka, H.-U.: Team cooperation using dual dynamics. In: Hannebauer, M. (ed.) Balancing reactivity and social deliberation in multi-agent systems. Lecture notes in computer science, pp. 111–124 (2001)
Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks 5(2), 157–166 (1994) (Special Issue Dynamic and Recurrent Neural Networks)
Gallistel, C.R.: The Organization of Action: a New Synthesis. Lawrence Erlbaum Associates, Inc., Hilldale (1980)
Housseiny, R.: Echo state networks used for the classification and filtering of silicon retina signals. Master’s thesis, RWTH AAchen (2003)
Jaeger, H.: The “echo state” approach to analysing and training recurrent neural networks. GMD Report 148, pp. 1–43 (2001)
Jaeger, H.: The echo state approach to analysing and training recurrent neural networks. Technical report, GMD - Forschungszentrum Informationstechnik GmbH (2001)
Jaeger, H.: Short term memory in echo state networks. Technical report, GMD Forschungszentrum Informationstechnik GmbH (2001)
Jaeger, H.: Tutorial on trainig recurrent neural networks covering bppt, rtrl, ekf and the “echo state network” approach. Technical report, GMD Forschungszentrum Informationstechnik GmbH (2002)
Jordan, M.I., Rumelhart, D.E.: Forward models: Supervised learning with a distal teacher (1992)
Jordan, M.I.: Computational aspects of motor control and motor learning. In: Heuer, H., Keele, S. (eds.) Handbook of Perception and Action: Motor Skills, Academic Press, New York (1995)
Kortenkamp, D., Bonasso, R.P., Murphy, R.: Artificial Intelligence and Mobile Robots. AAAI Press / The MIT Press (1998)
Furawaka, K., Kawato, M., Suzuki, R.: A hierarchical neural network model for the control learning of voluntary movements (1987)
Mead, C.: Analog VLSI and Neural Systems. Addison-Wesley, Reading (1989)
Maass, W., Natschläger, T., Markram, H.: Real-time computing without stable states: A new framework for neural computation based on perturbations. Neural Computation (2002)
Miall, R.C., Wolpert, D.M.: Forward models for phisiological motor control (1996)
Pomerleau, D.A.: Neural Network Perception for Mobile Robot Guidance. Kluwer, Dordrecht (1993)
Press, W.H., Teukolsky, S.A., Vetterling, W.T., Flannery, B.P.: Numerical Recipes in C: The Art of Scientific Computing, 2nd edn. Cambridge University Press, Cambridge (1992)
Sutton, R.S., Barto, A.G.: Toward a modern theory of adaptive networks: expectation and prediction (1981)
Schoenherr, F.: Learning to ground fact symbols in behavior-based robots. In: van Harmelen, F. (ed.) Proceedings of the 15th European Conference on Artificial Intelligence ECAI, pp. 708–712. IOS Press, Amsterdam (2002)
Enhanced Multi-Stream Kalman Filter Training for Recurrent Networks. In: Suykens, J.A.K., Vandewalle, J. (eds.) Nonlinear modeling, Kluwer Academic Publishers, Dordrecht (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Plöger, P.G., Arghir, A., Günther, T., Hosseiny, R. (2004). Echo State Networks for Mobile Robot Modeling and Control. In: Polani, D., Browning, B., Bonarini, A., Yoshida, K. (eds) RoboCup 2003: Robot Soccer World Cup VII. RoboCup 2003. Lecture Notes in Computer Science(), vol 3020. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-25940-4_14
Download citation
DOI: https://doi.org/10.1007/978-3-540-25940-4_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22443-3
Online ISBN: 978-3-540-25940-4
eBook Packages: Springer Book Archive