Skip to main content
SpringerLink
Log in

Exploring Coevolutionary Relations by Alterations in Fitness Function: Experiments with Simulated Robots

  • Published:
Journal of Intelligent and Robotic Systems Aims and scope Submit manuscript

Abstract

This paper focuses on various coevolutionary robotic experiments where all parameters except for the fitness function remain the same. Initially an attempt to categorize coevolutionary experiments is made and subsequently three experiments of competitive coevolution (hunt, battle and mating) are presented. The experiment concerning implicit competition of two species (mating) is given special attention as it shows emergence of compromise and collaboration through a competitive environment. The co-evolution progress monitoring is evaluated through fitness graphs, CIAO and Hamming maps and the results are interpreted for each experimental setup. The paper concludes that despite the alteration of fitness functions, several evasion–pursuit elements emerge. Furthermore, conciliatory strategies can emerge in implicit competitional cases.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Arkin, R.C.: Navigational path planning for a vision-based mobile robot. Robotica 7, 49–63 (1989)

    Article  Google Scholar 

  2. Blair, A.D., Pollack, J.: What makes a good co-evolutionary learning environment? Aust. J. Intell. Inf. Process. Syst. 4(3/4), 166–175 (1997)

    Google Scholar 

  3. Brooks, R.A.: Cambrian Intelligence. MIT Press, Cambridge, MA (1999)

    MATH  Google Scholar 

  4. Buason, G., Ziemke, T.: Explorations of task-dependent visual morphologies in competitive co-evolutionary experiments. In: Banzhaf, W. et al. (eds.) Advances in Artificial Life — The 7th European Conference on Artificial Life, pp. 763–770. Springer, Berlin, Heidelberg, New York (2003)

    Google Scholar 

  5. Carlsson, J., Ziemke, T.: YAKS — Yet Another Khepera Simulator. In: Rückert, Sitte, Witkowski (eds.) Autonomous Minirobots for Research and Entertainment, pp. 235–241. HNI-Verlagsschriftenreihe, Paderborn, Germany (2001)

    Google Scholar 

  6. Cliff, Miller: Co-evolution of pursuit and evasion I: Biological and Game-theoretical foundations, Technical Report CSRP311, University of Sussex, School of Cognitive and Computing Science (1995a)

  7. Cliff, Miller: Tracking the red Queen: Measurements of adaptive progress in co-evolutionary simulations. In: Moran, F., Moreno, A., Merelo, J.J., Chacon, P. (eds.) Advances in Artificial Life, pp. 200–218 (1995b)

  8. Cliff, Miller: Co-evolution of pursuit and evasion II: Simulation methods and results. In: From Animals to Animats 4: Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior, pp. 506–514. MIT Press, Cambridge, USA (1995c)

  9. Ficici, S.G., Pollack, J.B.: A game-theoretic approach to the simple coevolutionary algorithm. In: Schoenauer, et al. (eds.) Parallel Problem Solving from Nature VI, pp. 467–476. Springer (2000)

  10. Floreano, D., Nolfi, S.: God save the red Queen: Competition in evolutionary robotics. In: Koza, J. et al. (eds.) 2nd Conference on Genetic Programming, pp. 398–406. Morgan Kaufmann, San Mateo, CA (1997)

    Google Scholar 

  11. Floreano, D., Nolfi, S., Mondada, F.: Co-evolution and ontogenetic change in competing robots. In: Patel, M., Honavar, V., Balakrishnan, K. (eds.) Advances in the Evolutionary Synthesis of Intelligent Agents, pp. 273–306. MIT Press, Cambridge, MA (2001)

    Google Scholar 

  12. Harvey, P. Husbands, D., Cliff, A., Thompson, N., Jakobi: Evolutionary Robotics: The Sussex approach, Robotics and Autonomous Systems 20 (2–4), pp. 205–224 (1997)

    Google Scholar 

  13. Haynes, T., Sen, S.: Evolving behavioral strategies in predators and prey. In: Weiß, G., Sen, S. (eds.) Adaptation and Learning in Multiagent Systems, pp. 113–126. Springer, Berlin, Heidelberg, New York (1996)

    Google Scholar 

  14. Jakobi, N., Husbands, P., Harvey, I.: Noise and the reality gap: The use of simulation in evolutionary robotics. In: Moran, F., Moreno, A., Merelo, J., Chacon, P. (eds.) Advances in Artificial Life: Proc. 3rd European Conference on Artificial Life, pp. 704–720. Springer, Lecture Notes in Artificial Intelligence 929 (1995)

  15. Kaelbling, L.P., Littman, L.M., Moore, A.W.: Reinforcement learning: a survey. J. Artif. Intell. Res. 4, 237–285 (1996)

    Google Scholar 

  16. Keymeulen, K., Konaka, M., Iwata, Y., Kuniyoshi, Higuchi, T.: “Robot Learning Using Gate–level Evolvable Hardware” Proc. of Sixth European Workshop on Learning Robots (EWLR-6), pp. 173–188. Springer (1998)

  17. K–Team, S.A.: Khepera: User Manual. Switzerland http://ftp.k-team.com/khepera/documentation/KheperaUserManual.pdf (1995)

  18. Michel, O., Clergue, M., Collard, P.: Artificial neurogenesis: applications to the cart-pole problem and to an autonomous mobile robot. Int. J. Artif. Intell. Tools 6(4), 613–634 (1997)

    Article  Google Scholar 

  19. Miglino, O., Lund, H.H., Nolfi, S.: Evolving mobile robots in simulated and real environments. Artif. Life 2, 417–434 (1996)

    Article  Google Scholar 

  20. Nelson, A.L., Grant, E., Henderson, T.C.: Evolution of neural controllers for competitive game playing with teams of mobile robots. Robot. Auton. Syst. 46, 135–150 (2004)

    Article  Google Scholar 

  21. Nolfi, S., Floreano, D.: Co-evolving predator and prey robots: Do ‘arm races’ arise in artificial evolution? Artif. Life 4(4), 311–335 (1998)

    Article  Google Scholar 

  22. Nolfi, S., Floreano, D.: Evolutionary Robotics. MIT Press, Cambridge, MA (2000)

    Google Scholar 

  23. Ostergard, E.H., Lund, H.: Co-evolving Complex Robot Behavior, Proceedings of ICES2003 Trondheim, Norway, pp. 308–319 (2003)

  24. Potter, M., Meeden, L.A., Schultz, A.: Heterogeneity in the coevolved behaviors of mobile robots: The emergence of specialists, Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence, pp. 1337–1343. Morgan Kaufmann (2001)

  25. Quinn, M.: Evolving communication without dedicated communication channels. In: Kelemen, J., Sosνk, P. (eds.) ECAL01, pp. 357–366. Springer, Prague (2001a)

    Google Scholar 

  26. Quinn, M.: A comparison of approaches to the evolution of homogeneous multi-robot teams. In Proceedings of the 2001 Congress on Evolutionary Computation, pp. 128–135 (2001b)

  27. Rosin, C., Belew, R.: New methods for competitive co-evolution. Evol. Comput. 5(1), 1–29 (1996)

    Google Scholar 

  28. Schultz, A.C., Grefenstette, J.J., Adams, W.L.: RoboShepherd: Learning a Complex Behavior. Proc. of the Robots and Learning Workshop (RoboLearn ’96), May 1996, Key West, Florida, pp 105–113. NCARAI Report AIC-96-030 (1996)

  29. Sims, K.: Evolving Virtual Creatures, Computer Graphics (Siggraph ’94 Proceedings), July 1994, pp. 15–22 (1994a)

  30. Sims, K.: Evolving 3D Morphology and Behavior by Competition, Artificial Life IV Proceedings, ed. by Brooks & Maes, 1994, pp. 28–39. MIT Press (1994b)

  31. Stanley, K.O., Miikkulainen, R.: Competitive coevolution through evolutionary complexification. J. Artif. Intell. Res. 21, 63–100 (2004)

    Google Scholar 

  32. Togelius, J.: Evolution of a subsumption architecture neurocontroller. J. Intell. Fuzzy Syst. 15, 15–20 (2004)

    Google Scholar 

  33. Torresenk, J.: Possibilities and Limitations of Applying Evolvable Haxdwaxe to Real-World Applications, Proc. of the 10th Int. Conf on FieM Programmable Logic and Applications, Villach, Austria, pp. 230–239 (2000)

  34. Trianni, V.: Evolution of coordinated motion behaviors in a group of self-assembled robots. Technical Report TR/IRIDIA/2003-25, IRIDIA — Universite Libre de Bruxelles, Belgium, May 2003. DEA Thesis

  35. Watson, R.A., Pollack, J.B. (2001). Coevolutionary Dynamics in a Minimal Substrate. In: Spector, L. et al (eds.) Proceedings of the 2001 Genetic and Evolutionary Computation Conference, pp. 702–709. Morgan Kaufmann, (2001)

  36. Wolff, K., Nordin, P.: An Evolutionary Based Approach for Control Programming of Humanoids. In Proceedings of the 3rd International Conference on Humanoid Robots (Humanoids’03), Karlsruhe, Germany, 2003. VDI/VDE–GMA (2003)

  37. Yamauchi, B.M., Beer, R.D.: Integrating reactive, sequential, and learning behavior using dynamical neural networks. In: Cliff, D., Husbands, P., Meyer, J.-A., Wilson, S.W. (eds.) From Animals to Animats III: Proceedings of the 3rd International Conference on Simulation of Adaptive Behavior, pp. 382–391. MIT Press (1994)

  38. Yao, X., Higuchi, T.: Promises and Challenges of Evolvable Hardware. In Proceedings of First International Conference on Evolvable Systems: from Biology to Hardware, pp. 87–97. Berlin, Heidelberg, New York, Springer (1996)

Download references

Author information

Authors and Affiliations

  1. Faculty of Engineering, Department of Electrical and Computer Engineering, Division of Electronics and Computer Engineering, Aristotle University of Thessaloniki, GR54124, Thessaloniki, Greece

    Ioannis Mermigkis & Loukas Petrou

Authors
  1. Ioannis Mermigkis
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Loukas Petrou
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Loukas Petrou.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Mermigkis, I., Petrou, L. Exploring Coevolutionary Relations by Alterations in Fitness Function: Experiments with Simulated Robots. J Intell Robot Syst 47, 257–284 (2006). https://doi.org/10.1007/s10846-006-9083-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10846-006-9083-z

Key words

Search

Navigation