Continuous learning in a behavioral animation

  • J. D. Fouks
  • L. Signac
Conference paper
Part of the Eurographics book series (EUROGRAPH)


To model both individual behaviors and their effects upon an eco-system appears as extremely difficult. However, our first results [5] prove that an adaptation strategy cannot be chosen without taking into account the evolution of the environment. Therefore, we create a virtual world simulating resources disappearing as soon as they are exploited too efficiently. Consequently, this world becomes more unstable as species adapt themselves to it. Based on our new concepts, autonomous robots succeed in surviving there and hence reproduce the continuous learning ability of a hen.


Virtual World Autonomous Robot Artificial Life Computer Animation Continuous Learning 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    K.J. Aström & B. Wittenmark, Adaptive control, Addison-Wesley Publishing Comp., 1989MATHGoogle Scholar
  2. 2.
    L.B. Booker, Intelligent behavior as an adaptation to the ask environment, Phd Thesis, Ann Arbor, University of Michigan Press 1982Google Scholar
  3. 3.
    R. Boulic, R. Mas & D. Thalmann, Position Control of the Center of Mass for Articulated Figures in Multiple Support, Computer Animation and Simulation ’95 D. Terzopoulos & D. Thalmann (eds), Springer Verlag 1995 pp. 130–143.CrossRefGoogle Scholar
  4. 4.
    R.A. Brooks, Artificial Life and Real Robots, toward a practice of Autonomous Systems in: F.J. Varela, P. Bourgine (eds), Proc. of the 1st European Conf. on Artificial Life, MIT Press/Bradford Books, Cambridge MA, 1992.Google Scholar
  5. 5.
    J.D. Fouks, Towards an algorithmic theory of adaptation, To appear in Theoretical Computer Science.Google Scholar
  6. 6.
    J.C. Heudin, La vie artificielle, Collection systèmes complexes, Hermès, Paris 1994.Google Scholar
  7. 7.
    J.H. Holland, Outline for a Logical Theory of Adaptive System, JACM 9(3):297–314, July 1962.MathSciNetMATHCrossRefGoogle Scholar
  8. 8.
    M.I. Jordan & R.A. Jacobs, Learning to control an unstable system with forwarded modeling, in Advances in Neural Information Processing II, Touretzky (Ed), Morgan Kaufmann, pp324–331, 1990.Google Scholar
  9. 9.
    J.R. Koza, Genetic evolution and co-evolution of computer programs, in: CG. Langton, C. Taylor, J.D. Farmer, S. Rasmussen (eds), Artificial Life II, SFI studies in the Sciences of Complexity, Addison Wesley, Reading, MA, 1991 pp. 603–629.Google Scholar
  10. 10.
    J.A. Meyer, H. Roitblat and S. Wilson, From animals to animats 2. Proc. 2nd Internat. Conf. on Simulation of Adaptive Behavior. The MIT Press, Cambridge, MA 1993Google Scholar
  11. 11.
    J.M. Renders, Algorithmes génétiques et réseaux de neurones, Collection systèmes complexes, Hermès, Paris 1995.Google Scholar
  12. 12.
    S. Rose, The Making of Memory, Bantam Press, 1992.Google Scholar
  13. 13.
    D. Terzopoulos, X. Tu & R. Grzeszczuk, Artificial Fishes: Autonomous locomotion, Perception, Behavior and Learning in a Simulated Physical World, in: Tutorials of The 3rd Pacific Conf. on Computer Graphics and Applications, Seoul 1995 pp. 186–197.Google Scholar
  14. 14.
    J. Von Neumann (completed by A.W. burks), Theory of self-reproducing automata, University of Illinois Press 1966.Google Scholar
  15. 15.
    S.W. Wilson, Knowledge growth in an artificial animals Proc. of an International Conference on Genetic Algorithms and their applications, 1985Google Scholar

Copyright information

© Springer-Verlag Wien 1999

Authors and Affiliations

  • J. D. Fouks
    • 1
  • L. Signac
    • 1
  1. 1.Ircom/Sic Umr 6615 2bd. du téléport 3Futuroscope CedexFrance

Personalised recommendations