Abstract
This research concerns the comparison of three different artificial evolution approaches to the design of cooperative behavior in a group of simulated mobile robots. The first and second approaches, termed: single pool and plasticity, are characterized by robot controllers that share a single genotype, though the plasticity approach includes a learning mechanism. The third approach, termed: multiple pools, is characterized by robot controllers that use different genotypes. The application domain implements a pursuit-evasion game in which a team of robots, termed: pursuers, collectively work to capture one or more robots from a second team, termed: evaders. Results indicate that the multiple pools approach is superior comparative to the other two approaches in terms of measures defined for evader-capture strategy performance. Specifically, this approach facilitates behavioural specialization in the pursuer team allowing it to be effective for several different pursuer team sizes.
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
Benda, M., Jagannanthan, V., and Dodhiawalla, R. An Optimal Cooperation of Knowledge Sources. Technical BCS-G2010-28, Boeing AI Center, Bellevue, WA (1985).
Bull, L., and Holland, O. Evolutionary Computing in Multi-Agent Environments: Eusociality. In: Koza, J. R. Deb, K., Dorigo, M., Fogel, D, B., Garzon, M., Iba, H., and Riolo, R. L. (eds.) Proceedings of the Second Annual Conference on Genetic Programming, Morgan Kaufmann, Stanford (1997) 347–352.
Denzinger, J., and Fuchs, M. Experiments in Learning Prototypical Situations for Variants of the Pursuit Game. In: Durfee, E., and Tokoro, M (eds.) Proceedings of the Second ICMAS conference, AAAI Press, Kyoto, Japan, (1996) 48–55.
Goldberg, D. Genetic Algorithms. Addison Wesley, New York, USA. (1989).
Haynes, T., and Sen, S. Evolving behavioral strategies in pursuers and evader. In: Sen, S (ed.). Adaptation and Learning in Multi-Agent Systems, Morgan Kaufmann, Montreal, Quebec (1996) 32–37.
Korf, R. E. A simple solution to pursuit games. In: Weiβand, G., and Sen, S. (eds.) Working Papers of the Eleventh International Workshop on DAI, Springer Verlag, Berlin (1992) 195–213.
Levy, R., and Rosenschein, J. S. A Game Theoretic Approach to Distributed Artificial Intelligence and the Pursuit Problem. In: Rosenschein, J. S (ed.) Decentralized AI III, Springer-Verlag, Berlin (1992) 129–146.
Mondada, F., Franzi, E., and Ienne, P. Mobile Robot Miniaturization: A tool for Investigation in Control Algorithms. In: Yoshikawa, T. and Miyazaki, F. (eds.) Proceedings of Third International Symposium on Experimental Robotics, IEEE Press, Kyoto (1993) 501–513.
Nishimura, S. I., and Ikegami, T. Emergence of Collective Strategies in a Evader-Pursuer Game Model. Artificial Life. 3 (1997) 243–260.
Nitschke, G., and Nolfi, S. Emergence of Cooperation in a Pursuit-Evasion Scenario. Technical Report CNR02-26. Institute of Cognitive Science and Technologies (2002).
Nolfi S. and Parisi D. Learning to adapt to changing environments in evolving neural networks. Adaptive Behavior. 5 (1997) 75–98.
Rumelhart, D. E., Hinton, G. E., and Williams, R. J. Learning internal representations by error propagation. In: Rumelhart, D. E., and McClelland, J. L. (eds.) Parallel Distributed Processing, Vol. 1: Foundations. MIT Press, Cambridge (1986).
Yong, C. H., and Miikkulainen, R. Cooperative Co-evolution of Multi-Agent Systems. Technical Report AI01-287. Department of Computer Science, University of Texas (2001).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Nitschke, G. (2003). Emergence of Specialized Behavior in a Pursuit-Evasion Game. In: Mařík, V., Pěchouček, M., Müller, J. (eds) Multi-Agent Systems and Applications III. CEEMAS 2003. Lecture Notes in Computer Science(), vol 2691. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45023-8_31
Download citation
DOI: https://doi.org/10.1007/3-540-45023-8_31
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40450-7
Online ISBN: 978-3-540-45023-8
eBook Packages: Springer Book Archive