Swarm intelligence applications for emergency evacuation planning: state of the art, recent developments, and future research opportunities

Abstract

In the era where natural and human-made disasters are escalating in frequency and impact, the need for advanced emergency evacuation strategies is more critical than ever. This study presents a comprehensive examination of swarm intelligence algorithms and their applications in emergency evacuation planning—a field that has become increasingly important due to the growing complexity and scale of evacuation challenges. We delve into the realm of swarm intelligence—a class of algorithms inspired by self-organized behaviors observed in nature, such as those in ant colonies, bee colonies, bird flocks, and fish schools. Focusing on specific algorithms, including particle swarm optimization (PSO), artificial bee colony (ABC), and ant colony optimization (ACO), this study discusses their applications in simulating and optimizing emergency evacuation scenarios under various constraints, interactions, and objectives. A systematic literature survey forms the backbone of this study, highlighting the diverse applications and innovations in swarm intelligence for emergency evacuation. The findings underscore the novel aspects of these algorithms, including customized objective functions, solution encodings, and effective hybridization techniques. Through case studies, the paper demonstrates the effectiveness of these techniques in critical aspects of emergency management, such as planning egress routes, locating shelters, and organizing disaster response operations. Moreover, the current limitations emphasizing the untapped potential of swarm intelligence in enhancing emergency evacuation operations are critically discussed. This survey concludes by offering a structured overview of the main findings revealed and proposing future research opportunities in applying swarm intelligence for more effective emergency evacuation planning in the following years.