Abstract
Learning robot-environment interaction with echo state networks (ESNs) is presented in this paper. ESNs are asked to bootstrap a robot’s control policy from human teacher’s demonstrations on the robot learner, and to generalize beyond the demonstration dataset. Benefits and problems involved in some navigation tasks are discussed, supported by real-world experiments with a small mobile robot.
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
Pfeifer, R., Bongard, J.C.: How the Body Shapes the Way We Think: A New View of Intelligence (Bradford Books). The MIT Press, Cambridge (2006)
Funahashi, K.-i., Nakamura, Y.: Approximation of dynamical systems by continuous time recurrent neural networks. Neural Network 6(6), 801–806 (1993)
Beer, R.D.: A dynamical systems perspective on agent-environment interaction. Artif. Intell. 72(1-2), 173–215 (1995)
Beer, R.D.: The dynamics of active categorical perception in an evolved model agent. Adaptive Behavior 11(4), 209–243 (2003)
Pasemann, F.: Dynamics of a single model neuron. International Journal of Bifurcation and Chaos 3, 271–278 (1993)
Hülse, M., Zahedi, K., Pasemann, F.: Representing robot-environment interactions by dynamical features of neuro-controllers. In: Butz, M.V., Sigaud, O., Gérard, P. (eds.) Anticipatory Behavior in Adaptive Learning Systems. LNCS (LNAI), vol. 2684, pp. 222–242. Springer, Heidelberg (2003)
Tani, J., Yamamoto, J.: On the dynamics of robot exploration learning. Cognitive Systems Research 3(3), 459–470 (2002)
Jaeger, H.: Tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the echo state network approach. Technical Report 159, AIS Fraunhofer, St. Augustin (2002)
Jaeger, H.: The ‘echo state’ approach to analysing and training recurrent neural networks. Technical Report 148, AIS Fraunhofer, St. Augustin, Germany (2001)
Jaeger, H., Haas, H.: Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication. Science (April 2004)
Oubbati, M., Schanz, M., Buchheim, T., Levi, P.: Velocity control of an omnidirectional robocup player with recurrent neural networks. In: Bredenfeld, A., Jacoff, A., Noda, I., Takahashi, Y. (eds.) RoboCup 2005. LNCS (LNAI), vol. 4020, pp. 691–701. Springer, Heidelberg (2006)
Oubbati, M., Schanz, M., Levi, P.: Meta-learning for Adaptive Identification of Non-linear Dynamical Systems. In: Proc. Joint 20th IEEE International Symposium on Intelligent Control and 13th Mediterranean Conference on Control and Automation, Limassol, Cyprus. IEEE, Los Alamitos (June 2005)
Oubbati, M., Palm, G.: A neural framework for adaptive robot control. Journal of Neural Computing and Applications 19(1), 103–114 (2010)
Mondada, et al.: The e-puck, a robot designed for education in engineering. In: Proc. of the 9th Conf. on Autonomous Robot Systems and Competitions, vol. 1, pp. 59–65 (2009)
Hartland, C., Bredèche, N.: Using Echo State Networks for Robot Navigation Behavior Acquisition. In: ROBIO 2007, Sanya Chine (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Oubbati, M., Kord, B., Palm, G. (2010). Learning Robot-Environment Interaction Using Echo State Networks. In: Doncieux, S., Girard, B., Guillot, A., Hallam, J., Meyer, JA., Mouret, JB. (eds) From Animals to Animats 11. SAB 2010. Lecture Notes in Computer Science(), vol 6226. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15193-4_47
Download citation
DOI: https://doi.org/10.1007/978-3-642-15193-4_47
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15192-7
Online ISBN: 978-3-642-15193-4
eBook Packages: Computer ScienceComputer Science (R0)