Generating Various and Consistent Behaviors in Simulations

  • Benoit Lacroix
  • Philippe Mathieu
  • Andras Kemeny
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 55)


In multi-agent based simulations, providing various and consistent behaviors for the agents is an important issue to produce realistic and valid results. However, it is difficult for the simulations users to manage simultaneously these two elements, especially when the exact influence of each behaviorial parameter remains unknown. We propose in this paper a generic model designed to deal with this issue: easily generate various and consistent behaviors for the agents. The behaviors are described using a normative approach, which allows increasing the variety by introducing violations. The generation engine controls the determinism of the creation process, and a mechanism based on unsupervised learning allows managing the behaviors consistency. The model has been applied to traffic simulation with the driving simulation software used at Renault, scaner© ii, and experimental results are presented to demonstrate its validity.


Multiagent System Consistent Behavior Generation Engine Drunk Driver Simulation User 
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.
    Boella, G., van der Torre, L.: An architecture of a normative system: count-as conditionals, obligations and permissions. In: Int. Conf. AAMAS, New-York, USA, pp. 229–231 (2006)Google Scholar
  2. 2.
    Bou, E., López-Sánchez, M., Rodríguez-Aguilar, J.A.: Adaptation of autonomic electronic institutions through norms and institutional agents. In: O’Hare, G.M.P., Ricci, A., O’Grady, M.J., Dikenelli, O. (eds.) ESAW 2006. LNCS, vol. 4457, pp. 300–319. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  3. 3.
    Dewar, R.: Individual Differences. In: Human Factors in Traffic Safety, pp. 111–142 (2002)Google Scholar
  4. 4.
    Doniec, A., Espié, S., Mandiau, R., Piechowiak, S.: Non-normative behaviour in multi-agent system: Some experiments in traffic simulation. In: IEEE/WIC/ACM Int. Conf. on Intelligent Agent Technology, Hong Kong, China, pp. 30–36 (2006)Google Scholar
  5. 5.
    Gallant, S.I.: Neural Network Learning and Expert Systems. MIT Press, Cambridge (1993)zbMATHGoogle Scholar
  6. 6.
    Kohonen, T.: Self-Organizing Maps. Springer, Heidelberg (1995)Google Scholar
  7. 7.
    Lacroix, B., Mathieu, P., Kemeny, A.: A normative model for behavioral differentiation. In: IEEE/WIC/ACM Int. Conf. on Intelligent Agent Technology, Sydney, Australia, pp. 96–99 (2008)Google Scholar
  8. 8.
    Lacroix, B., Mathieu, P., Rouelle, V., Chaplier, J., Gallée, G., Kemeny, A.: Towards traffic generation with individual driver behavior model based vehicles. In: Driving Simulation Conference North America, Iowa City, USA, pp. 144–154 (2007)Google Scholar
  9. 9.
    Maim, J., Yersin, B., Thalmann, D.: Unique instances for crowds. In: Computer Graphics and Applications (2008)Google Scholar
  10. 10.
    Noriega, P.: Agent mediated auctions: The Fishmarket Metaphor. PhD thesis, Univ. de Barcelona (1997)Google Scholar
  11. 11.
    Olstam, J.: Simulation of rural road traffic for driving simulators. In: Transportation Research Board, Whashigton, USA (2005)Google Scholar
  12. 12.
    Pavón, R., Díaz, F., Luzón, V.: A model for parameter setting based on bayesian networks. Engineering Applications of Artificial Intelligence 21, 14–25 (2008)CrossRefGoogle Scholar
  13. 13.
    Reynolds, C.W.: Steering behaviors for autonomous characters. In: Game Developers Conference, San Francisco, California, pp. 763–782 (1999)Google Scholar
  14. 14.
    Vázuez-Salceda, J., Dignum, V., Dignum, F.: Organizing multiagent systems. J. of Autonomous Agents and Multi-Agents Systems 11, 307–360 (2005)CrossRefGoogle Scholar
  15. 15.
    Wright, S., Ward, N.J., Cohn, A.G.: Enhanced presence in driving simulators using autonomous traffic with virtual personalities. Presence 11, 578–590 (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Benoit Lacroix
    • 1
  • Philippe Mathieu
    • 2
  • Andras Kemeny
    • 3
  1. 1.Renault, Technical Center for Simulation and LIFLUniversity of LilleFrance
  2. 2.LIFLUniversity of Lille, Cite Scientifique Bat M3Villeneuve d’AscqFrance
  3. 3.Renault, Technical Center for SimulationGuyancourtFrance

Personalised recommendations