A method to accelerate the rescue of fire-stricken victims

Abstract

For individuals trapped in a fire, early detection can significantly increase their chances of survival. Presently, firefighters employ a systematic search method along the walls, ensuring a comprehensive and thorough exploration of the environment to prevent missing any trapped victims. However, this approach has its drawbacks, such as time wastage in areas or rooms without victims. The goal of this study is to propose a search method that can expedite the discovery of trapped victims. Our method relies primarily on prior knowledge, crowd information and the temperature within the fire scene, utilizing fuzzy logic to calculate the probability of the presence and survival of victims in each distinct space. The resulting search sequence not only accelerates victim discovery but also safeguards firefighters from unnecessary risks. We conducted various simulation experiments to validate our approach. In comparison to the sequential search method currently employed by firefighters, the experimental results indicate that our method reduces the time to locate trapped victims by 25 %. Compared to other path planning algorithms based on approximate optimization, our method offers a shorter computation time, making it suitable for integration into fire rescue systems to provide real-time assistance.