Evacuation guidance systems must be adaptive and distributed in the unstable and harsh environment of disaster evacuation. Numerous dynamic evacuation guidance systems have been proposed and studied; however, few of them focus on the unstable evacuation environment that makes computer systems unreliable and malfunctioning. In this study, we introduce a distributed algorithm for a dynamic evacuation guidance system to ensure safe and efficient evacuation, even in the face of system component failures. The system is designed to be resilient, allowing it to continue functioning, providing effective evacuation guidance despite partial system malfunctions. Simulation experiments showed that the distributed system can provide more efficient evacuation guidance than static guidance systems. Furthermore, it correctly guided evacuees in situations where the target exit changed during the evacuation, showcasing the system's adaptability and effectiveness in handling unforeseen challenges, including system failures.

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 Tsurushimaâ\euro™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.