Advertisement

Swarm Intelligence

, Volume 2, Issue 2–4, pp 73–95 | Cite as

Evolving coordinated group behaviours through maximisation of mean mutual information

  • Valerio Sperati
  • Vito TrianniEmail author
  • Stefano Nolfi
Article

Abstract

A well known problem in the design of the control system for a swarm of robots concerns the definition of suitable individual rules that result in the desired coordinated behaviour. A possible solution to this problem is given by the automatic synthesis of the individual controllers through evolutionary or learning processes. These processes offer the possibility to freely search the space of the possible solutions for a given task, under the guidance of a user-defined utility function. Nonetheless, there exist no general principles to follow in the definition of such a utility function in order to reward coordinated group behaviours. As a consequence, task dependent functions must be devised each time a new coordination problem is under study. In this paper, we propose the use of measures developed in Information Theory as task-independent, implicit utility functions. We present two experiments in which three robots are trained to produce generic coordinated behaviours. Each robot is provided with rich sensory and motor apparatus, which can be exploited to explore the environment and to communicate with other robots. We show how coordinated behaviours can be synthesised through a simple evolutionary process. The only criteria used to evaluate the performance of the robotic group is the estimate of mutual information between the motor states of the robots.

Keywords

Evolutionary robotics Information theory Mutual information 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Supplementary material

VideoObject

VideoObject

VideoObject

VideoObject

References

  1. Baldassarre, G., Trianni, V., Bonani, M., Mondada, F., Dorigo, M., & Nolfi, S. (2007). Self-organised coordinated motion in groups of physically connected robots. IEEE Transactions on Systems, Man and Cybernetics, Part B: Cybernetics, 37(1), 224–239. CrossRefGoogle Scholar
  2. Brenner, N., Bialek, W., & de Ruyter van Steveninck, R. (2000). Adaptive rescaling maximizes information transmission. Neuron, 26, 695–702. CrossRefGoogle Scholar
  3. Capdepuy, P., Polani, D., & Nehaniv, C. (2007). Maximization of potential information flow as a universal utility for collective behaviour. In Proceedings of the 2007 IEEE symposium on artificial life (CI-ALife 2007) (pp. 207–213). Piscataway: IEEE Press. CrossRefGoogle Scholar
  4. Cianci, C. M., Raemy, C., Pugh, J., & Martinoli, A. (2007). Communication in a swarm of miniature robots: the e-puck as an educational tool for swarm robotics. In E. Şahin, W. M. Spears, & A. F. T. Winfield (Eds.), Lecture notes in computer science: Vol. 4433. Swarm robotics—second SAB 2006 international workshop, revised selected papers (pp. 103–115), Rome, Italy, September 30–October 1, 2006. Berlin: Springer. Google Scholar
  5. Feldman, D. (2002). A brief introduction to: information theory, excess entropy and computational mechanics. (Technical report). College of the Atlantic, Bar Harbor, ME. Google Scholar
  6. Funes, P., Orme, B., & Bonabeau, E. (2003). Evolving emergent group behaviors for simple humans agents. In W. Banzhaf, T. Christaller, P. Dittrich, J. T. Kim, & J. Ziegler (Eds.), Lecture notes in artificial intelligence: Vol. 2801. Advances in artificial life. Proceedings of the 7th European conference on artificial life (ECAL 2003) (pp. 76–89). Berlin: Springer. Google Scholar
  7. Jakobi, N. (1997). Evolutionary robotics and the radical envelope of noise hypothesis. Adaptive Behavior, 6, 325–368. CrossRefGoogle Scholar
  8. Klyubin, A., Polani, D., & Nehaniv, C. (2005a). All else being equal being empowered. In M. Capcarrere, A. A. Freitas, P. J. Bentley, C. G. Johnson, & J. Timmis (Eds.), Lecture notes in artificial intelligence: Vol. 3630. Advances in artificial life. Proceedings of the 8th European conference on artificial life (ECAL 2005) (pp. 744–753). Berlin: Springer. Google Scholar
  9. Klyubin, A., Polani, D., & Nehaniv, C. (2005b). Empowerment: a universal agent-centric measure of control. In Proceedings of the 2005 IEEE congress on evolutionary computation (pp. 128–135). Piscataway: IEEE Press. CrossRefGoogle Scholar
  10. Lungarella, M., & Pfeifer, R. (2001). Robots as cognitive tools: Information theoretic analysis of sensory-motor data. In Proceedings of the 2nd international IEEE/RSJ conference on humanoid robotics (pp. 245–252). Piscataway: IEEE Press. Google Scholar
  11. Lungarella, M., & Sporns, O. (2005). Information self-structuring: key principle for learning and development. In Proceedings of the 4th international conference on development and learning (pp. 25–30). Piscataway: IEEE Press. CrossRefGoogle Scholar
  12. Lungarella, M., Pegors, T., Bulwinkle, D., & Sporns, O. (2005). Methods for quantifying the information structure of sensory and motor data. Neuroinformatics, 3(3), 243–262. CrossRefGoogle Scholar
  13. Matarić, M. J. (1997). Learning social behavior. Robotics and Autonomous Systems, 20, 191–204. CrossRefGoogle Scholar
  14. Miglino, O., Lund, H., & Nolfi, S. (1995). Evolving mobile robots in simulated and real environments. Artificial Life, 2(4), 417–434. CrossRefGoogle Scholar
  15. Mondada, F., & Bonani, M. (2007). The e-puck education robot. http://www.e-puck.org/.
  16. Nolfi, S., & Floreano, D. (2000). Evolutionary robotics: the biology, intelligence, and technology of self-organizing machines. Cambridge: MIT Press/Bradford Books. Google Scholar
  17. Olsson, L., Nehaniv, C., & Polani, D. (2005). Sensor adaptation and development in robots by entropy maximization of sensory data. In Proceedings of the 6th IEEE international symposium on computational intelligence in robotics and automation (CIRA-2005) (pp. 587–592). Piscataway: IEEE Computer Society. CrossRefGoogle Scholar
  18. Prokopenko, M., & Wang, P. (2003). Evaluating team performance at the edge of chaos. In D. Polani, B. Browning, A. Bonarini, & K. Yoshida (Eds.), Lecture notes in computer science: Vol. 3020. RoboCup 2003: robot soccer world cup VII (pp. 89–101). Berlin: Springer. Google Scholar
  19. Prokopenko, M., Gerasimov, V., & Tanev, I. (2006a). Evolving spatiotemporal coordination in a modular robotic system. In S. Nolfi, G. Baldassarre, R. Calabretta, J. C. T. Hallam, D. Marocco, J. A. Meyer, O. Miglino, & D. Parisi (Eds.), From animals to animats 9: 9th international conference on the simulation of adaptive behavior (SAB 2006) (pp. 558–569). Berlin: Springer. Google Scholar
  20. Prokopenko, M., Gerasimov, V., & Tanev, I. (2006b). Measuring spatiotemporal coordination in a modular robotic system. In L. M. Rocha, L. S. Yaeger, M. A. Bedau, D. Floreano, R. L. Goldstone, & A. Vespignani (Eds.), Artificial life X: proceedings of the tenth international conference on the simulation and synthesis of living systems (pp. 185–191). Cambridge: MIT Press. Google Scholar
  21. Quinn, M., Smith, L., Mayley, G., & Husbands, P. (2003). Evolving controllers for a homogeneous system of physical robots: structured cooperation with minimal sensors. Philosophical Transactions of the Royal Society of London, Series A: Mathematical, Physical and Engineering Sciences, 361, 2321–2344. CrossRefMathSciNetGoogle Scholar
  22. Shannon, C. (1948). A mathematical theory of communication. The Bell System Technical Journal, 27, 379–423 and 623–656. Google Scholar
  23. Sporns, O., & Lungarella, M. (2006). Evolving coordinated behavior by maximizing information structure. In L. M. Rocha, L. S. Yaeger, M. A. Bedau, D. Floreano, R. L. Goldstone, & A. Vespignani (Eds.), Artificial life X: proceedings of the tenth international conference on the simulation and synthesis of living systems (pp. 323–329). Cambridge: MIT Press. Google Scholar
  24. Sporns, O., Tononi, G., & Edelman, G. (2000). Connectivity and complexity, the relationship between neuroanatomy and brain dynamics. Neural Networks, 13, 909–922. CrossRefGoogle Scholar
  25. Tarapore, D., Lungarella, M., & Gomez, G. (2004). Fingerprinting agent-environment interaction via information theory. In F. Groen, N. Amato, A. Bonarini, E. Yoshida, & B. Kröse (Eds.), Intelligent autonomous systems 8 (pp. 512–520). Amsterdam: IOS. Google Scholar
  26. Tarapore, D., Lungarella, M., & Gomez, G. (2006). Quantifying patterns of agent-environment interaction. Robotics and Autonomous Systems, 54(2), 150–158. CrossRefGoogle Scholar
  27. Tononi, G., Sporns, O., & Edelman, G. (1994). A measure for brain complexity: relating functional segregation and integration in the nervous system. Proceedings of the National Academy of Sciences, 91, 5033–5037. CrossRefGoogle Scholar
  28. Tononi, G., Sporns, O., & Edelman, G. G. (1996). A complexity measure for selective matching of signals by the brain. Proceedings of the National Academy of Sciences, 93, 3422–3427. CrossRefGoogle Scholar
  29. Tononi, G., Edelman, G., & Sporns, O. (1998). Complexity and coherency: integrating information in the brain. Trends in Cognitive Sciences, 2(12), 474–484. CrossRefGoogle Scholar
  30. Trianni, V., & Nolfi, S. (2007). Minimal communication strategies for self-organising synchronisation behaviours. In Proceedings of the 2007 IEEE symposium on artificial life (CI-ALife 2007) (pp. 199–206). Piscataway: IEEE Press. CrossRefGoogle Scholar
  31. Trianni, V., Nolfi, S., & Dorigo, M. (2008). Evolution, self-organisation and swarm robotics. In C. Blum & D. Merkle (Eds.), Natural computing series. Swarm intelligence. Introduction and applications. Berlin: Springer. Google Scholar
  32. Van Dyke Parunak, H., & Brueckner, S. (2001). Entropy and self-organization in multi-agent systems. In Proceedings of the fifth international conference on autonomous agents (pp. 124–130). New York: ACM. CrossRefGoogle Scholar

Copyright information

© Springer Science + Business Media, LLC 2008

Authors and Affiliations

  1. 1.Laboratory of Autonomous Robotics and Artificial LifeInstitute of Cognitive Sciences and Technologies, CNRRomeItaly

Personalised recommendations