Online Indoor Fire Evacuation System

Many methods for indoor fire escape evacuation have been proposed to assist victims in escaping. Greedy approaches focus on finding the closest exit and providing victims with the shortest evacuation path. However, they are time consuming to respond to a dynamic fire spread. Optimal approaches determine evacuation exits and routes based on the characteristics of indoor fires using probabilistic or gravitational algorithms. However, their disadvantage is the excessive amount of computation required. Compared with previous methods, this article provides a lightweight exit decision formulation paired with dynamic path planning. The experimental results indicate that our approach accelerates the computation time by approximately 1.5 times and achieves a victim survival rate higher than 90%.