Advertisement

Arms Races and Car Races

  • Julian Togelius
  • Simon M. Lucas
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4193)

Abstract

Evolutionary car racing (ECR) is extended to the case of two cars racing on the same track. A sensor representation is devised, and various methods of evolving car controllers for competitive racing are explored. ECR can be combined with co-evolution in a wide variety of ways, and one aspect which is explored here is the relative-absolute fitness continuum. Systematical behavioural differences are found along this continuum; further, a tendency to specialization and the reactive nature of the controller architecture are found to limit evolutionary progress.

Keywords

Sensor Representation Sensor Setup Driving Style Controller Architecture Competitive Racing 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Floreano, D., Kato, T., Marocco, D., Sauser, E.: Coevolution of active vision and feature selection. Biological Cybernetics 90, 218–228 (2004)MATHCrossRefGoogle Scholar
  2. 2.
    Tanev, I., Joachimczak, M., Hemmi, H., Shimohara, K.: Evolution of the driving styles of anticipatory agent remotely operating a scaled model of racing car. In: Proceedings of the IEEE Congress on Evolutionary Computation, pp. 1891–1898 (2005)Google Scholar
  3. 3.
    Togelius, J., Lucas, S.M.: Evolving controllers for simulated car racing. In: Proceedings of the IEEE Congress on Evolutionary Computation, pp. 1906–1913 (2005)Google Scholar
  4. 4.
    Stanley, K.O., Kohl, N., Sherony, R., Miikkulainen, R.: Neuroevolution of an automobile crash warning system. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2005) (2005)Google Scholar
  5. 5.
    Togelius, J., Lucas, S.M.: Evolving robust and specialized car racing skills. In: Proceedings of the IEEE Congress on Evolutionary Computation (to appear, 2006)Google Scholar
  6. 6.
    Hillis, W.D.: Co-evolving parasites improve simulated evolution as an optimization procedure. Physica D 42, 228–234 (1990)CrossRefGoogle Scholar
  7. 7.
    Rosin, C.D., Belew, R.K.: New methods for competitive coevolution. Evolutionary Computation 5(1) (1996)Google Scholar
  8. 8.
    Dawkins, R., Krebs, J.R.: Arms races between and within species. Proceedings of the Royal Society of London, series B 205, 489–511 (1979)CrossRefGoogle Scholar
  9. 9.
    Nolfi, S., Floreano, D.: Co-evolving predator and prey robots: Do ’arm races’ arise in artificial evolution? Artificial Life 4, 311–335 (1998)CrossRefGoogle Scholar
  10. 10.
    Búason, G., Bergfeldt, N., Ziemke, T.: Brains, bodies, and beyond: Competitive co-evolution of robot controllers, morphologies and environments. Genetic Programming and Evolvable Machines 6, 25–51 (2005)CrossRefGoogle Scholar
  11. 11.
    Stanley, K., Miikkulainen, R.: Competitive coevolution through evolutionary complexification. Journal of Artificial Intelligence Research 21, 63–100 (2004)Google Scholar
  12. 12.
    Bourg, D.M.: Physics for Game Developers. O’Reilly, Sebastopol (2002)Google Scholar
  13. 13.
    Monster, M.: Car physics for games (2003), http://home.planet.nl/monstrous/tutcar.html

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Julian Togelius
    • 1
  • Simon M. Lucas
    • 1
  1. 1.Department of Computer ScienceUniversity of EssexColchesterUK

Personalised recommendations