Abstract
We investigate the dynamics of agent groups evolved to perform a collective task, and in which the behavioural heterogeneity of the group is under evolutionary control. Two task domains are studied: solutions are evolved for the two tasks using an evolutionary algorithm called the Legion system. A new metric of heterogeneity is also introduced, which measures the heterogeneity of any evolved group behaviour. It was found that the amount of heterogeneity evolved in an agent group is dependent of the given problem domain: for the first task, the Legion system evolved heterogeneous groups; for the second task, primarily homogeneous groups evolved. We conclude that the proposed system, in conjunction with the introduced heterogeneity measure, can be used as a tool for investigating various issues concerning redundancy, robustness and division of labour in the context of evolutionary approaches to collective problem solving.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Arkin, R.C., Hobbs, J.D.: Dimensions of Communication and Social Organization in Multi-agent Robotic Systems. In: Meyer, J.-A., Roitblat, H.L., Wilson, S.W. (eds.) Procs. of the Second Intl. Conf. on Simulation of Adaptive Behavior, pp. 486–493. MIT Press, Cambridge (1992)
Arkin, R.C., Ali, K.S.: Integration of Reactive and Telerobotic Control in Multi-agent Robotic Systems. In: Cliff, D., Husbands, P., Meyer, J.-A., Wilson, S.W. (eds.) Procs. of the Third Intl. Conf. on Simulation of Adaptive Behavior, pp. 473–478. MIT Press, Cambridge (1994)
Balch, T.: Behavioral Diversity in Learning Robot Teams. PhD thesis, College of Computing, Georgia Institute of Technology (1998)
Balch, T.: Reward and Diversity in Multirobot Foraging. In: IJCAI 1999 Workshop on Agents Learning About, From and With other Agents, Sweden, July 31 - August 6 (1999)
Balch, T.: Hierarchic Social Entropy: An Information Theoretic Measure of Robot Group Diversity. Autonomous Robots 8(3) (July 2000) (to appear)
Bennett, F.H.: Automatic Creation of an Efficient Multi-Agent Architecture Using Genetic Programming with Architecture-Altering Operations. In: Koza, J.R., Goldberg, D.E., Fogel, D.B. (eds.) Genetic Programming 1996: Proceedings of the First Annual Conference, pp. 30–38. MIT Press, Cambridge (1996)
Bonabeau, E., Sobkowski, A., Theraulaz, G., Deneubourg, J.-L.: Adaptive Task Allocation Inspired by a Model of Division of Labour in Social Insects. Sante Fe Institute Tech. Rep. 98-01-004 (1998)
Bull, L., Fogarty, C.: Evolutionary Computing in Multi-Agent Environments: Specification and Symbiogenesis. In: Ebeling, W., Rechenberg, I., Voigt, H.-M., Schwefel, H.-P. (eds.) PPSN 1996. LNCS, vol. 1141, pp. 12–21. Springer, Heidelberg (1996)
Fahlman, S., Lebiere, C.: The Cascade-Correlation Learning Architecture. Carnegie Mellon University Tech. Rep. CMU-CS-90-100 (1990)
Fontan, M.S., Mataric, M.J.: A Study of Territoriality: The Role of Critical Mass in Adaptive Task Division. In: Maes, P., Mataric, M., Meyer, J.-A., Pollack, J., Wilson, S.W. (eds.) Procs. of the Fourth Intl. Conf. on Simulation of Adaptive Behavior, pp. 553–561. MIT Press, Cambridge (1996)
Goldberg, D., Mataric, M.J.: Interference as a Tool for Designing and Evaluating Multi-Robot Controllers. In: AAAI 1997: Procs. of the Fourteenth Natl. Conf. on Artificial Intelligence, pp. 637–642. MIT Press, Cambridge (1997)
Haynes, T., Sen, S.: Crossover Operators for Evolving a Team. In: Koza, J.R., Deb, K., Dorigo, M., Fogel, D.B., Gazon, M., Iba, H., Riolo, R.L. (eds.) Genetic Programming 1997: Proceedings of the Second Annual Conference, pp. 162–167. Morgan Kauffman, San Francisco (1997)
Langdon, W.B., Poli, R.: Fitness Causes Bloat. In: Second On-Line World Conference on Soft Computing in Engineering Design and Manufacturing, pp. 13–22. Springer, London (1997)
Luke, S., Spector, L.: Evolving Teamwork and Coordination with Genetic Programming. In: Koza, J.R., Goldberg, D.E., Fogel, D.B., Riolo, R.L. (eds.) Genetic Programming 1996: Proceedings of the First Annual Conference, pp. 141–149. MIT Press, Cambridge (1996)
Mataric, M.J.: Reinforcement Learning in the Multi-Robot Domain. Autonomous Robots 4(1), 73–83 (1997)
Mataric, M.J.: Designing and Understanding Adaptive Group Behavior. Adaptive Behavior 4(1), 51–80 (1995)
McFarland, D.J.: Animals as Cost-Based Robots. In: Boden, M. (ed.) The Philosophy of Artificial Life. Oxford University Press, Oxford (1996)
Ohno, S.: Evolution by Gene Duplication. Springer, New York (1970)
Ohta, T.: Multigene and Supergene Families. Oxford Surv. Evol. Biol. 5, 41–65 (1988)
Parker, L.: Heterogeneous Multi-Robot Cooperation. PhD thesis, Massachussets Institute of Technology (1994)
Potter, M., De Jong, K.: Evolving neural networks with collaborative species. In: Procs. of the 1995 Summer Computer Simulation Conference, Ottawa (1995)
Sims, K.: Evolving 3D Morphology and Behaviour by Competition. In: Brooks, R., Maes, P. (eds.) Artificial Life VI, pp. 28–39. MIT Press, Cambridge (1994)
Sneath, P., Sokal, R.: Numerical Taxonomy. W. H. Freeman and Company, San Francisco (1973)
Theraulaz, G., Goss, S., Gervet, J., Deneubourg, J.-L.: Task Differentiation in Polistes Wasp Colonies: a Model for Self-organizing Groups of Robots. In: Meyer, J.A., Wilson, S.W. (eds.) Procs. of the First Intl. Conf. on the Simulation of Adaptive Behaviour, pp. 346–355. MIT Press, Cambridge (1991)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bongard, J.C. (2000). The Legion System: A Novel Approach to Evolving Heterogeneity for Collective Problem Solving. In: Poli, R., Banzhaf, W., Langdon, W.B., Miller, J., Nordin, P., Fogarty, T.C. (eds) Genetic Programming. EuroGP 2000. Lecture Notes in Computer Science, vol 1802. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-46239-2_2
Download citation
DOI: https://doi.org/10.1007/978-3-540-46239-2_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67339-2
Online ISBN: 978-3-540-46239-2
eBook Packages: Springer Book Archive