M. Kurosu (Ed.): Human-Computer Interaction, Part V, HCII 2013, LNCS 8008, pp. 62–71, 2013. © Springer-Verlag Berlin Heidelberg 2013 Perception and BDI Reasoning Based Agent Model for Human Behavior Simulation in Complex System Jaekoo Joo Systems and Management Engineering, Inje University 197 Inje-ro, Gimhae-si 621-749, Republic of Korea jjoo@inje.ac.kr Abstract. Modeling of human behaviors in systems engineering has been regarded as an extremely complex problem due to the ambiguity and difficulty of representing human decision processes. Unlike modeling of traditional physical systems, from which active humans are assumed to be excluded, HECS has some peculiar characteristics which can be summarized as follows: 1) Environments and human itself are nondeterministic and dynamic that there are many different ways in which they dynamically evolve. 2) Human perceives a set of perceptual information taken locally from surrounding environments and other humans in the environment, which will guide human actions toward his or her goal achievement. In order to overcome the challenges due to the above characteristics, we present an human agent model for mimicking perception-based rational human behaviors in complex systems by combining the ecological concepts of affordance- and the Belief-Desire-Intention (BDI) theory. Illustrative models of fire evacuation simulation are developed to show how the proposed framework can be applied. The proposed agent model is expected to realize their potential and enhance the simulation fidelity in analyzing and predicting human behaviors in HECS. Keywords: Human Behavior, Affordance theory, BDI theory, Agent-based Simulation, Social Interaction. 1 Introduction Both cognitive and rational reasoning aspects of human behaviors must be accommodated in developing common framework for modeling and simulation of Human-Environment Complex System (HECS) due to the critical role of humans in systems operation and dynamics. However, modeling of human behaviors in systems engineering has been regarded as an extremely complex problem due to the ambiguity and difficulty of representing the nondeterministic and dynamic nature of human decision processes, which makes the research difficult and slow. Unlike modeling of traditional physical systems, from which active humans are assumed to be excluded, HECS has some peculiar characteristics which can be summarized into two. First, environments and human him/herself are nondeterministic and dynamic that there are many different ways in which they dynamically evolve. The characteristics mainly