The Visual Computer

, Volume 26, Issue 5, pp 353–366 | Cite as

The Cortexionist architecture: behavioural intelligence of artificial creatures

  • David Panzoli
  • Sara de Freitas
  • Yves Duthen
  • Hervé Luga
Original Article

Abstract

Traditionally, producing intelligent behaviours for artificial creatures involves modelling their cognitive abilities. This approach raises two problems. On the one hand, defining manually the agent’s knowledge is a heavy and error-prone task that implies the intervention of the animator. On the other hand, the relationship between cognition and intelligence has not been theoretically nor experimentally proven so far. The ecological approaches provide a solution for these problems, by exploring the links between the creature, its body and its environment. Using an artificial life approach, we propose an original model of memory based on the synthesis of several neuroscience theories. The Cortexionist controller integrates cortex-like structure into a connectionist architecture in order to enhance the agent’s adaptation in a dynamic environment, ultimately leading to the emergence of intelligent behaviour. Initial experiments presented in this paper prove the validity of the model.

Keywords

Computer animation Autonomous adaptive agents Cognitive modelling Human memory 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Sanchez, S., Balet, O., Luga, H., Duthen, Y.: Autonomous virtual actors. In: 2nd International Conference on Technologies for Interactive Digital Storytelling and Entertainment. LNCS, Darmstadt, Germany, June 2004, pp. 68–78. Springer, Berlin (2004) Google Scholar
  2. 2.
    Pelachaud, C.: Multimodal expressive embodied conversational agents. In: MULTIMEDIA ’05: Proceedings of the 13th Annual ACM International Conference on Multimedia, New York, NY, USA, 2005, pp. 683–689. ACM, New York (2005) CrossRefGoogle Scholar
  3. 3.
    Turing, A.M.: Computing machinery and intelligence. Mind 59, 433–460 (1950) CrossRefMathSciNetGoogle Scholar
  4. 4.
    Pfeifer, R., Bongard, J.C.: How the Body Shapes the Way We Think: A New View of Intelligence. The MIT Press, Cambridge (2006) Google Scholar
  5. 5.
    Hawkins, J., Blakeslee, S.: On Intelligence. Times Books, New York (2004) Google Scholar
  6. 6.
    Lassabe, N., Luga, H., Duthen, Y.: A new step for evolving creatures. In: IEEE-ALife’07, Honolulu, Hawaii, pp. 243–251. IEEE, New York (2007) Google Scholar
  7. 7.
    Shao, W., Terzopoulos, D.: Autonomous pedestrians. Graph. Models 69(5–6), 246–274 (2007) CrossRefGoogle Scholar
  8. 8.
    Conde, T., Thalmann, D.: An integrated perception for autonomous virtual agents: active and predictive perception: research articles. Comput. Animat. Virtual Worlds 17(3–4), 457–468 (2006) CrossRefGoogle Scholar
  9. 9.
    Funge, J., Tu, X., Terzopoulos, D.: Cognitive modeling: knowledge, reasoning and planning for intelligent characters. In: The 26th Annual Conference on Computer Graphics and Interactive Techniques, pp. 29–38. ACM Press/Addison-Wesley, New York (1999) Google Scholar
  10. 10.
    Donikian, S.: HPTS: a behaviour modelling language for autonomous agents. In: Proceedings of the Fifth International Conference on Autonomous Agents, Montreal, Canada, 2001 Google Scholar
  11. 11.
    Brooks, R.A.: A robust layered control system for a mobile robot. IEEE J. Robot. Autom., 14–23 (1986) Google Scholar
  12. 12.
    Minsky, M.: A framework for representing knowledge. Psychol. Comput. Vision, 211–277 (1975) Google Scholar
  13. 13.
    Kallmann, M., Thalmann, D.: A behavioral interface to simulate agent–object interactions in real-time. In: Proceedings of Computer Animation 99, Geneva, 1999, pp. 138–146. IEEE Computer Society Press, Los Alamitos (1999) CrossRefGoogle Scholar
  14. 14.
    Harnad, S.: The symbol grounding problem. Physica 42, 335–346 (1990) Google Scholar
  15. 15.
    Panzoli, D., Luga, H., Duthen, Y.: Beyond reactive systems: An associative memory for sensory-driven intelligent behavior. In: Proceedings of the International Conference on CyberWorlds, Bradford, UK, September 2009, pp. 63–70 Google Scholar
  16. 16.
    Frye, J., Ananthanarayanan, R., Modha, D.S.: Towards real-time, mouse-scale cortical simulations. In: CoSyNe: Computational and Systems Neuroscience, 2007 Google Scholar
  17. 17.
    Meyer, J.-A., Guillot, A., Pirim, P., Berthoz, A.: Psikharpax: An autonomous and adaptive artificial rat. In: Proceedings of ISR2004, the 35th International Symposium on Robotics, Paris, 2004 Google Scholar
  18. 18.
    Filliat, D., Meyer, J.-A.: Active perception and map learning for robot navigation. In: From Animals to Animats 6, Proceedings of the Sixth International Conference on Simulation of Adaptive Behavior, pp. 246–255. The MIT Press, Cambridge (2000) Google Scholar
  19. 19.
    Girard, B., Cuzin, V., Guillot, A., Gurney, K., Prescott, T.J.: A basal ganglia inspired model of action selection evaluated in a robotic survival task. J. Integr. Neurosci. 2(22), 179–200 (2003) CrossRefGoogle Scholar
  20. 20.
    Gibbs, R.W.: A review of ‘how the body shapes the way we think: a new view of intelligence’ from Rolf Pfeifer and Josh Bongard. Pragmat. Cognit. 15(3), 610–614 (2007) Google Scholar
  21. 21.
    McLean, Paul: The Triune Brain in Evolution. Springer, Berlin (1990) Google Scholar
  22. 22.
    George, D., Hawkins, J.: A hierarchical Bayesian model of invariant pattern recognition in the visual cortex. In: Proceedings of the International Joint Conference on Neural Networks (IJCNN’05), 2005 Google Scholar
  23. 23.
    Cliff, D., Miller, G.F.: 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. The MIT Press, Cambridge (1996) Google Scholar
  24. 24.
    Terzopoulos, D., Tu, X.: Artificial fishes: physics, locomotion, perception, behavior. In: SIGGRAPH’94 Computer Graphics, ACM SIGGRAPH, pp. 42–48. ACM Press, New York (1994) Google Scholar
  25. 25.
    Blumberg, B.M., Todd, P.M., Maes, P.: No bad dogs: ethological lessons for learning in Hamsterdam. In: Proceedings of the 4th International Conference on the Simulation of Adaptive Behavior, 1996 Google Scholar
  26. 26.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323, 533–536 (1986) CrossRefGoogle Scholar
  27. 27.
    Anderson, J.R.: The Architecture of Cognition. Harvard University Press, Cambridge (1983) Google Scholar
  28. 28.
    Arbib, M.A. (ed.): The Handbook of Brain Theory and Neural Networks. The MIT Press, Cambridge (2002) Google Scholar
  29. 29.
    Hebb, D.: The Organisation of Behavior. Wiley, New York (1949) Google Scholar
  30. 30.
    Cohen, N.J., Squire, L.R.: Preserved learning and retention of pattern analysing skill in amnesia: dissociation of knowing how and knowing that. Science 210, 207–209 (1980) CrossRefGoogle Scholar
  31. 31.
    Atkinson, R.C., Shiffrin, R.M.: Human memory: a proposed system and its control processes. In: Spence, K.W. (ed.) The Psychology of Learning and Motivation: Advances in Research and Theory, vol. 2, pp. 89–195. Academic Press, New York (1968) CrossRefGoogle Scholar
  32. 32.
    Hall, E.T.: The Hidden Dimension. Anchor Books, Peterborough (1966) Google Scholar
  33. 33.
    Baddeley, A., Hitch, G.: Working memory. In: Recent Advances in Learning and Motivation, vol. 8. Academic Press, New-York (1974) Google Scholar
  34. 34.
    Craik, F.I.M., Lockhart, R.S.: Levels of processing: a framework for memory research. J. Verbal Learn. Verbal Behav. 11, 671–684 (1972) CrossRefGoogle Scholar
  35. 35.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735–1780 (1997) CrossRefGoogle Scholar
  36. 36.
    Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evol. Comput. 10(2), 99–127 (2002) CrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2010

Authors and Affiliations

  • David Panzoli
    • 1
  • Sara de Freitas
    • 2
  • Yves Duthen
    • 1
  • Hervé Luga
    • 1
  1. 1.IRIT-CNRSUniversité de ToulouseToulouseFrance
  2. 2.Serious Games InstituteCoventry UniversityCoventryUK

Personalised recommendations