[en] Reservoir computing (RC) uses a randomly created Recurrent Neural Network as a reservoir of rich dynamics which projects the input to a high dimensional space. These projections are mapped to the desired output using a linear output layer, which is the only part being trained by standard linear regression. In this work, RC is used for imitation learning of multiple behaviors which are generated by different controllers using an intelligent navigation system for mobile robots previously published in literature. Target seeking and exploration behaviors are conflicting behaviors which are modeled with a single RC network. The switching between the learned behaviors is implemented by an extra input which is able to change the dynamics of the reservoir, and in this way, change the behavior of the system. Experiments show the capabilities of Reservoir Computing for modeling multiple behaviors and behavior switching.
Disciplines :
Sciences informatiques
Auteur, co-auteur :
ANTONELO, Eric Aislan ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Schrauwen, Benjamin
Stroobandt, Dirk
Co-auteurs externes :
yes
Langue du document :
Anglais
Titre :
Modeling Multiple Autonomous Robot Behaviors and Behavior Switching with a Single Reservoir Computing Network
Date de publication/diffusion :
2008
Nom de la manifestation :
IEEE International Conference on Systems, Man and Cybernetics
Date de la manifestation :
12-10-2008 to 15-10-2008
Manifestation à portée :
International
Titre de l'ouvrage principal :
Proceedings of the 2008 IEEE International Conference on Systems, Man and Cybernetics
D. Verstraeten, B. Schrauwen, M. D'Haene, and D. Stroobandt, "A unifying comparison of reservoir computing methods," Neural Networks, vol. 20, pp. 391-403, 2007.
H. Jaeger, "The "echo state" approach to analysing and training recurrent neural networks," German National Research Center for Information Technology, Tech. Rep. GMD Report 148, 2001.
W. Maass, T Natschläger, and H. Markram, "Real-time computing without stable states: A new framework for neural computation based on perturbations," Neural Computation, vol. 14, no. 11, pp. 2531-2560, 2002.
J. J. Steil, "Backpropagation-Decorrelation: Online recurrent learning with O(N) complexity," in Proc. Int. Joint Conf. on Neural Networks (IJCNN), vol. 1, 2004, pp. 843-848.
H. Jaeger, "Short term memory in echo state networks," German National Research Center for Information Technology, Tech. Rep. GMD Report 152, 2001.
B. Schrauwen, D. Verstraeten, and J. Van Campenhout, "An overview of reservoir computing: theory, applications and implementations," in Proceedings of the European Symposium on Artifical Neural Networks (ESANN), 2007.
H. Jaeger and H. Haas, "Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless telecommunication," Science, vol. 308, pp. 78-80, April 2 2004.
E. A. Antonelo, B. Schrauwen, and D. Stroobandt, "Event detection and localization for small mobile robots using reservoir computing," Neural Networks, 2008.
E. A. Antonelo, B. Schrauwen, and J. V Campenhout, "Generative modeling of autonomous robots and their environments using reservoir computing," Neural Processing Letters, vol. 26, no. 3, pp. 233-249, 2007.
E. A. Antonelo, B. Schrauwen, and D. Stroobandt, "Mobile robot control in the road sign problem using reservoir computing networks," in IEEE Int. Conf. on Robotics and Automation (ICRA), 2008.
J. Tani, "Learning to generate articulated behavior through the bottom-up and the top-down interaction processes," Neural Networks, vol. 16, pp. 11-23, January 2003.
D. Rumelhart, G. Hinton, and R. Williams, Learning internal representations by error propagation. MIT Press, Cambridge, MA, 1986.
E. A. Antonelo, B. Schrauwen, and D. Stroobandt, "Identification of an intelligent navigation system for mobile robots using reservoir computing," in 10th Brazilian Symp. on Neural Networks (SBRN), 2008, in press.
E. A. Antonelo, A.-J. Baerlvedt, T Rognvaldsson, and M. Figueiredo, "Modular neural network and classical reinforcement learning for autonomous robot navigation: Inhibiting undesirable behaviors," in Proc. Int. Joint Conf. on Neural Networks (IJCNN), Vancouver, 2006, pp. 498-505.
H. Jaeger, "Tutorial on training recurrent neural networks, covering BPTT, RTRL, EKF and the "echo state network" approach," German National Research Center for Information Technology, Tech. Rep. GMD Report 159, 2002.
E. A. Antonelo, M. Figueiredo, A.-J. Baerlvedt, and R. Calvo, "Intelligent autonomous navigation for mobile robots: spatial concept acquisition and object discrimination," in Proc. IEEE Int. Symp. on Computational Intelligence in Robotics and Automation (CIRA), Helsinki, 2005, pp. 553-557.
