Abstract:

The internal short-distance transportation in railway logistics parks faces efficiency bottlenecks, and drones offer a new solution to break this bottleneck. However, the introduction of drones creates complex air-ground collaborative scheduling challenges. Focusing on this issue, this paper investigates the collaborative scheduling optimization of drones under multiple spatiotemporal constraints. Firstly, this paper systematically analyzes core constraints including task assignment, drone load and endurance, node capacity, and airspace safety. Secondly, this paper establishes a mixed integer programming model aimed at minimizing the maximum completion time. Furthermore, this paper designs a two-stage heuristic algorithm integrating greedy initialization and improved genetic algorithm. Simulation results demonstrate that the proposed algorithm significantly reduces average task turnaround time and improves drone utilization rates, providing a quantitative decision-making basis for intelligent park scheduling.

Key words: unmanned aerial vehicle, railway logistics park, scheduling optimization, spatiotemporal constraints, genetic algorithm, simulation