Adaptive PSO Algorithm for Cooperative Multi-UAV Path Planning in Disaster Relief

Abstract

Efficient path planning for multiple unmanned aerial vehicles (UAVs) is essential in disaster relief operations, where rapid response and improved survival rates are critical. Conventional metaheuristic algorithms frequently experience premature convergence and an imbalance between exploration and exploitation, especially in complex and densely constrained environments. This study introduces an Adaptive Particle Swarm Optimization (APSO) approach for cooperative multi-UAV trajectory planning in hazardous scenarios. The method utilizes a performance-driven adaptation mechanism that dynamically adjusts each particle’s inertia weight according to its fitness relative to the population average and the global best solution. This mechanism enhances exploration for low-performing particles and ensures precise exploitation for high-performing ones. The path planning problem is formulated as a multi-objective optimization task, incorporating trajectory smoothness, altitude stability, hazard avoidance, and path length. Simulation results in diverse and complex disaster environments demonstrate the effectiveness of the proposed approach. Specifically, the method achieves approximately 6% and 12% reductions in total path length compared to standard Particle Swarm Optimization (PSO) and Ant Colony Optimization (ACO), respectively. In more challenging scenarios, it further surpasses conventional PSO, achieving up to an 11% improvement in mission efficiency. These findings indicate that the adaptive strategy substantially enhances trajectory safety and operational performance, establishing it as a robust and reliable solution for autonomous multi-UAV coordination in disaster response applications.