Two-timescale learning using idiotypic behaviour mediation for a navigating mobile robot

A combined short-term learning (STL) and long-term learning (LTL) approach to solving mobile-robot navigation problems is presented and tested in both the real and virtual domains. The LTL phase consists of rapid simulations that use a genetic algorithm to derive diverse sets of behaviours, encoded as variable sets of attributes, and the STL phase is an idiotypic artificial immune system. Results from the LTL phase show that sets of behaviours develop very rapidly, and significantly greater diversity is obtained when multiple autonomous populations are used, rather than a single one. The architecture is assessed under various scenarios, including removal of the LTL phase and switching off the idiotypic mechanism in the STL phase. The comparisons provide substantial evidence that the best option is the inclusion of both the LTL phase and the idiotypic system. In addition, this paper shows that structurally different environments can be used for the two phases without compromising transferability.

[1]  Alan S. Perelson,et al.  The immune system, adaptation, and machine learning , 1986 .

[2]  Yoshiki Uchikawa,et al.  Emergent construction of behavior arbitration mechanism based on the immune system , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[3]  Leandro Nunes de Castro,et al.  Artificial Immune Systems: A New Computational Approach , 2002 .

[4]  Robert Weigel,et al.  Hybrid optimization techniques for the design of SAW-filters , 1997, 1997 IEEE Ultrasonics Symposium Proceedings. An International Symposium (Cat. No.97CH36118).

[5]  Guan-Chun Luh,et al.  Reactive Immune Network Based Mobile Robot Navigation , 2004, ICARIS.

[6]  Yoshiki Uchikawa,et al.  Emergent construction of a behavior arbitration mechanism based on the immune system , 1997, Adv. Robotics.

[7]  Olivier Michel,et al.  Cyberbotics Ltd. Webots™: Professional Mobile Robot Simulation , 2004 .

[8]  N K Jerne,et al.  Towards a network theory of the immune system. , 1973, Annales d'immunologie.

[9]  Dario Floreano,et al.  Active vision and feature selection in evolutionary behavioral systems , 2002 .

[10]  Uwe Aickelin,et al.  Idiotypic Immune Networks in Mobile-Robot Control , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[11]  Uwe Aickelin,et al.  Genetic-algorithm Seeding of Idiotypic Networks for Mobile-robot Navigation , 2008, ICINCO-RA.

[12]  Jean-Michel Renders,et al.  Hybrid methods using genetic algorithms for global optimization , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[13]  Yoshiki Uchikawa,et al.  Evolutionary construction of an immune network-based behavior arbitration mechanism for autonomous mobile robots , 1998 .

[14]  Tom Søndergaard Pedersen,et al.  Proceedings of the 5th International Conference on Informatics in Control, Automation and Robotics - ICINCO 2008 , 2008, ICINCO 2008.

[15]  Francesco Mondada,et al.  Evolution of homing navigation in a real mobile robot , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[16]  Kiyonobu Abe,et al.  Simultaneous transmission and reception system by adaptive cancelling , 1998 .

[17]  Jonathan Timmis,et al.  Artificial immune systems - a new computational intelligence paradigm , 2002 .

[18]  Rodney A. Brooks,et al.  Artificial Life and Real Robots , 1992 .

[19]  Piero Mussio,et al.  Toward a Practice of Autonomous Systems , 1994 .

[20]  Peter Ross,et al.  A Role for Immunology in "Next Generation" Robot Controllers , 2003, ICARIS.

[21]  Andrew M. Tyrrell,et al.  Robot error detection using an artificial immune system , 2003, NASA/DoD Conference on Evolvable Hardware, 2003. Proceedings..

[22]  Joanne H. Walker,et al.  The balance between initial training and lifelong adaptation in evolving robot controllers , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[23]  Hod Lipson,et al.  Evolving Dynamic Gaits on a Physical Robot , 2004 .

[24]  Uwe Aickelin,et al.  An Idiotypic Immune Network as a Short-Term Learning Architecture for Mobile Robots , 2008, ICARIS.

[25]  Fernando José Von Zuben,et al.  An Immune Learning Classifier Network for Autonomous Navigation , 2003, ICARIS.

[26]  Werner Dilger,et al.  AIS Based Robot Navigation in a Rescue Scenario , 2004, ICARIS.

[27]  Jon Timmis,et al.  Timidity: A Useful Mechanism for Robot Control? , 2003 .

[28]  Jerne Nk.  Towards a network theory of the immune system. , 1974 .

[29]  F.J. Von Zuben,et al.  Decentralized control system for autonomous navigation based on an evolved artificial immune network , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[30]  Masahiro Fujita,et al.  Evolving robust gaits with AIBO , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[31]  Olivier Michel,et al.  Cyberbotics Ltd. Webots™: Professional Mobile Robot Simulation , 2004, ArXiv.

[32]  F. Varela,et al.  Toward a Practice of Autonomous Systems: Proceedings of the First European Conference on Artificial Life , 1992 .

[33]  Yasuo Kuniyoshi,et al.  Comparison between off-line model-free and on-line model-based evolution applied to a robotics navigation system using evolvable hardware , 1998 .