Research on passengers´ evacuation model in ships based on Agent theory

This paper aims to set up a passengers´ evacuation simulation model in ships based on Agent theory. In this model the individual attributes are constituted with gender, age, velocity, response time and position. Besides the process of passengers´ evacuation is conducted by the ship spatial information networks, exit selection is conducted by game theory and obstacle avoidance and conflict selection is conducted by the shortest path planning method. Compared to other cellular automata model the Agent model could simulate passengers´ behavior and thinking process more detailed and predict the evacuation time more accurately. The Agent model also could provide theoretical basis and guidance for passengers´ evacuation scheme design and management in ships.