Automated Generation of Various and Consistent Populations in Multi-Agent Simulations

  • Benoit Lacroix
  • Philippe Mathieu
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 155)


The variety and consistency of the agents behaviors greatly influences the realism in multi-agent simulations, and designing scenarios that simultaneously take into account both aspects is a complex task. To address this issue, we propose an approach to automatically create populations using sample data. It facilitates the designers tasks, and variety as well as consistency issues are handled by the generation model. The proposed approach is based on a behavioral differentiation model that describes the behaviors of agents using norms. To automatically configure this model, we propose an inference mechanism based on Kohonen networks and estimation distribution functions.We then introduce agents generators that can create a specified population, and are automatically configured by the inferred norms. The approach has been evaluated in traffic simulation, in association with a commercial software. Experimental results show that it allows to accurately reproduce the populations represented in sample data.


Time Slice Model Agent Automate Generation Agent Behavior Inference Mechanism 
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.
    Caillou, P.: Automated multi-agent simulation generation and validation. In: Desai, N., Liu, A., Winikoff, M. (eds.) PRIMA 2010. LNCS, vol. 7057, pp. 398–412. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  2. 2.
    Junges, R., Klugl, F.: Evaluation of Techniques for a Learning-Driven Modeling Methodology in Multiagent Simulation. In: Dix, J., Witteveen, C. (eds.) MATES 2010. LNCS (LNAI), vol. 6251, pp. 185–196. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  3. 3.
    Kemeny, A.: A cooperative driving simulator. In: International Training and Equipment Conference, London, UK, pp. 67–71 (1993)Google Scholar
  4. 4.
    Kohonen, T.: Self-Organizing Maps. Springer, Heidelberg (1995)CrossRefGoogle Scholar
  5. 5.
    Lacroix, B., Mathieu, P., Kemeny, A.: Generating Various and Consistent Behaviors in Simulations. In: Demazeau, Y., Pavón, J., Corchado, J.M., Bajo, J. (eds.) PAAMS 2009. AISC, vol. 55, pp. 110–119. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  6. 6.
    Lacroix, B., Mathieu, P., Kemeny, A.: The Use of Norms Violations to Model Agents Behavioral Variety. In: Hübner, J.F., Matson, E., Boissier, O., Dignum, V. (eds.) COIN@AAMAS 2008. LNCS, vol. 5428, pp. 220–234. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  7. 7.
    Maim, J., Yersin, B., Thalmann, D.: Unique character instances for crowds. IEEE Computer Graphics and Applications 29(6), 82–90 (2009)CrossRefGoogle Scholar
  8. 8.
    Reynolds, C.W.: Steering behaviors for autonomous characters. In: Game Developers Conference, San Francisco, USA, pp. 763–782 (1999)Google Scholar
  9. 9.
    Ulicny, B., de Heras Ciechomski, P., Thalmann, D.: Crowdbrush: Interactive authoring of real-time crowd scenes. In: ACM SIGGRAPH/Eurographics Symposium on Computer Animation, Grenoble, France (2004)Google Scholar
  10. 10.
    Wright, S., Ward, N.J., Cohn, A.G.: Enhanced presence in driving simulators using autonomous traffic with virtual personalities. Presence 11(6), 578–590 (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  1. 1.Computer Science Dept., LIFL (UMR CNRS 8022)University of LilleLilleFrance

Personalised recommendations