Author:
Akira Tsurushima
Affiliation:
Intelligent Systems Laboratory, SECOM CO., LTD., Japan
Keyword(s):
Distributed Problem Solving, Multi-Agent Simulation, Average Value at Risk, Crowd Evacuation, Dynamic Evacuation Guidance.
Abstract:
The dynamics of smoke, fire, and toxic gases inside a building is complex and difficult to predict. Models have been used to analyze and develop efficient evacuation protocols for fire-spread evacuation situations. In this study, an integrated model that includes fire spread, evacuation agent, and evacuation guidance signage models, is developed as an efficient control mechanism for a dynamically distributed evacuation guidance system. This mechanism is based on Tsurushima’s distributed algorithm, which does not assume any central control and only requires local information in providing efficient evacuation guidance, thereby minimizing total evacuation time while directing evacuees away from hazards. The parameters of the mechanism were calibrated to mitigate the occurrence of low-probability catastrophic events, which is crucial in the development of evacuation guidance protocols.