Multi-UAVs Path Planning Based on Genetic Algorithm in Campus Emergency Response

University campuses frequently face complex emergencies such as natural disasters, medical emergencies, and safety threats, posing significant challenges to the design of emergency response systems. Given the rapid advancement of drone technology and its efficiency in dynamic environments, this study proposes a genetic algorithm-based multi-Unmanned Aerial Vehicles (UAVs) path planning method to enhance the response efficiency to campus emergencies. Initially, we divide the campus environment into a series of spatial grids, thereby transforming the continuous path planning problem into a discrete optimization problem. By defining time-varying weights for critical areas, an objective function is designed to balance response time and area coverage. The individual encoding is represented by a sequence of path nodes to accommodate the cooperative operation of multi-UAVs systems. The selection, crossover, and mutation operations of genetic algorithms are adapted to suit this specific problem, ensuring global search capability under multiple constraints. Simulation experiments in a real campus environment validate the significant performance enhancement of the algorithm in response time, path optimization, and coverage effectiveness. This study provides a theoretical foundation and practical support for the effective deployment of multi-UAV cooperative systems, improving the intelligence level of campus security management.