Multi-agent modeling and simulation of human behavior in aircraft evacuations

Abstract

Predicting the collective behavior of people during evacuations from aircraft is a significant challenge, complicated by human behavioral factors such as stress and panic. This paper presents a multi-agent system for simulating the impact of individual human factors on aircraft evacuations. Based on the model, a prototype system, AvatarSim, was developed to simulate emergency evacuations from aircrafts. The simulator can be used to model situations that are difficult to test in real-life due to safety considerations.