A Bi-Layer Collaborative Planning Framework for Multi-UAV Delivery Tasks in Multi-Depot Urban Logistics

To address the modeling complexity and multi-objective collaborative optimization challenges in multi-depot and multiple Unmanned Aerial Vehicle (UAV) delivery task planning, this paper proposes a bi-layer planning framework, which comprehensively considers resource constraints, multi-depot coordination, and the coupling characteristics of path execution. The upper layer tackles the task assignment problem by formulating a multi-objective optimization model aimed at minimizing economic cost, delivery delay, and the number of UAVs deployed. An Enhanced Non-dominated Sorting Genetic Algorithm II (ENSGA-II) is developed, incorporating heuristic initialization, goal-oriented search operators, an adaptive mutation mechanism, and a staged evolution control strategy to improve solution feasibility and distribution quality. The lower layer addresses the path planning problem by establishing a multi-objective model that considers path length, flight risk, and altitude variation. An improved Particle Swarm Optimization (PSO) algorithm is proposed by integrating chaotic initialization, linearly adjusted acceleration coefficients and maximum velocity, a stochastic disturbance-based position update mechanism, and an adaptively tuned inertia weight to enhance algorithmic performance and path generation quality. Simulation results under typical task scenarios demonstrate that the proposed model achieves an average reduction of 47.8% in economic cost and 71.4% in UAV deployment quantity, while significantly reducing delivery window violations. The framework exhibits excellent capability in multi-objective collaborative optimization. The ENSGA-II algorithm outperforms baseline algorithms significantly across performance metrics, achieving a hypervolume (HV) value of 1.0771 (improving by 72.35% to 109.82%) and an average Inverted Generational Distance (IGD) of 0.0295, markedly better than those of comparison algorithms (ranging from 0.0893 to 0.2714). The algorithm also demonstrates overwhelming superiority in the C-metric, indicating outstanding global optimization capability in terms of distribution, convergence, and diversity of the solution set. Moreover, the proposed framework and algorithm are both effective and feasible, offering a novel approach to low-altitude urban logistics delivery problems.