[en] An autonomous system able to construct its own navigation strategy for mobile robots is proposed. The navigation strategy is molded from navigation experiences (succeeding as the robot navigates) according to a classical reinforcement learning procedure. The autonomous system is based on modular hierarchical neural networks. Initially the navigation performance is poor (many collisions occur). Computer simulations show that after a period of learning the autonomous system generates efficient obstacle avoidance and target seeking behaviors. Experiments also offer support for concluding that the autonomous system develops a variety of object discrimination capability and of spatial concepts.
Disciplines :
Sciences informatiques
Auteur, co-auteur :
ANTONELO, Eric Aislan ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Figueiredo, Mauricio
Baerlvedt, Albert-Jan
Calvo, Rodrigo
Co-auteurs externes :
yes
Langue du document :
Anglais
Titre :
Intelligent autonomous navigation for mobile robots: spatial concept acquisition and object discrimination
Date de publication/diffusion :
2005
Nom de la manifestation :
6th IEEE International Symposium on Computational Intelligence in Robotics and Automation
Date de la manifestation :
27-06-2005 to 30-06-2005
Manifestation à portée :
International
Titre de l'ouvrage principal :
Proceedings of the 6th IEEE International Symposium on Computational Intelligence in Robotics and Automation
Figueiredo, M. (1999) "Autonomous Robot Navigation", Proceedings of VII SBC School for Informatics, Novo Hamburgo (in Portuguese).
Calvo, R., Figueiredo M., Antonelo, E.A. (2005) "Architecture control in constructive neural networks via classifier systems in autonomous navigation systems", 6th IEEE International Symposium on Computational Intelligence in Robotics and Automation, Helsinki, Finland, in press.
Vershure, P. and Voegtlin, T. (1998) "A bottom up approach towards the acquisition and expression of sequential representations applied to behaving real-world device: distributed adaptive control III", Neural Networks, Vol. 11, pp. 1531-1549, 1998.
Crestani, P.R., Figueiredo, M., and Von Zuben, F. (2002) "A hierarchical neuro-fuzzy approach to autonomous navigation", Proceedings of 2002 International Joint Conference on Neural Networks, (cd-rom), Honolulu, USA.
Calvo, R. and Figueiredo M. (2003) "Reinforcement learning for hierarchical and modular neural network in autonomous robot navigation", Proceedings of 2003 International Joint Conference on Neural Networks - IJCNN, Oregon, USA.
Millan, J. (1996) "Rapid, safe, and incremental learning of navigation strategies"; IEEE Transactions on Systems, Man, and Cybernetics, Vol. 26, no 3, pp.408-420, 1996.
Cazangi, R. and Figueiredo, M. (2002) "Simultaneous emergence of conflicting basic behaviors and their coordination in an evolutionary autonomous navigation system", Proceedings of 2002 IEEE Congress on Evolutionary Computation, (cd-rom), Honolulu, EUA.
Kandell, E.; Schwartz, J. and Jessel, T. (1991) "Principles of neural science", Elsevier, New York.
Donahoe, J. W. & Palmer, D. C. (1994) "Learning and complex behavior", Allyn and Bacon, Needham Heights, Massachusetts, EUA.
Edelman, G., (1987) "Neural darwinism: the theory of neuronal group selection", Basic books, New York, USA.
Arkin, R.C. (1998) "Behavior-Based Robotics", The MIT Press.
