Agent modeling with individual human behaviors

ABSTRACT

The challenge presented in this paper is to obtain a human-like individual behavior model by using participatory modeling technology in the traffic domain. We show a methodology that can elicit prior knowledge for explaining human driving behavior in specific environments, and then construct a driving behavior model based on of a set of prior knowledge. Since, in the real world, human drivers often perform unintentional actions, and occasionally they have no logical reason for their driving actions, we are forced to construct a behavior model with an insufficient amount of prior knowledge. To construct an individual driving behavior model with insufficient knowledge, we take the approach of using knowledge from others to complement the lack of knowledge from oneself.

REFERENCES

• 1: Y. Murakami, Y. Sugimoto, and T. Ishida. Modeling human behavior for virtual training systems. In Proceedings of the 20th National Conference on Artificial Intelligence (AAAI-05), pages 127--132, 2005.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
        I.2.11 Distributed Artificial Intelligence

General Terms:
Design

Keywords:
modeling methodology, multiagent simulation, participatory modeling, traffic simulation