Optimizing multi-UAV mission scheduling for army logistics supply chains using metaheuristic algorithms

The increasing integration of Unmanned Aerial Vehicles (UAVs) into US Army logistics operations has introduced complex multi-objective scheduling challenges that conventional optimization methods struggle to address efficiently. This study presents a metaheuristic-based optimization framework for scheduling fleets of military UAVs tasked with last-mile resupply missions in dynamic, contested operational environments. A hybrid approach combining a Genetic Algorithm (GA) and Ant Colony Optimization (ACO) is proposed to minimize total mission completion time, fuel consumption, and operational risk while satisfying strict military delivery constraints. The model incorporates stochastic demand, no-fly-zone avoidance, payload capacity limitations, and UAV endurance parameters derived from US Army field logistics doctrine. Computational experiments were conducted on simulated battlefield scenarios with fleet sizes ranging from 5 to 50 UAVs across terrain grids representing forward operating bases. The proposed GA-ACO hybrid achieved an average improvement of 23.4% in mission completion time and 18.7% in fuel efficiency compared with single-algorithm baselines, while reducing the constraint violation rate to 1.8%. The framework also demonstrated superior adaptability to real-time route re-planning under dynamic threat scenarios and converged within the 10-minute Army tactical planning window for fleets of up to 50 UAVs. These findings suggest that hybrid metaheuristic optimization offers a robust and scalable approach to multi-UAV mission scheduling, with significant implications for enhancing Army supply-chain agility and operational readiness.