Logistics Planning of Intelligent Warehousing System Based on Multi-AGV-UAV Collaborative Delivery and Improved NSGA-II Algorithm

The continuous progress of the social economy has led to problems such as slow allocation speed and insufficient space utilization in traditional warehousing and logistics allocation methods. To overcome the limitations of existing scheduling methods, this study proposes an intelligent warehouse logistics planning method based on the coordinated delivery of multiple automated guided vehicles (AGVs) and unmanned aerial vehicles (UAVs) and an improved non-dominated sorting genetic algorithm. This method uses AGVs and UAVs for integrated air-ground coordinated delivery, innovatively employs a geometric correction method for path correction, uses an individual elimination strategy to improve the algorithm, adopts an individual neighborhood method to retain individuals with higher congestion levels, and improves the algorithm’s crossover and mutation strategies. The experimental results showed that the improved algorithm converged faster, with an optimal function value of 2835.7, which was 23.2, 107.5, and 114.8 lower than the non-dominated sorting genetic algorithm, genetic algorithm, and particle swarm optimization algorithm, respectively. The Pareto boundary distribution of the improved algorithm was more uniform, the transition was smooth, the boundary completeness was high, and the equipment running time was proportional to the total cost. The minimum age distance of the improved algorithm was 0.316, which was 0.008 and 0.014 lower than the compared algorithm. The total time and cost of collaborative delivery were lower than those of single automatic guided vehicle delivery. In operating condition 2, the total time difference reached 815 s, and the total delivery cost was 67 yuan lower than that of single AGV delivery. Therefore, the improved method can effectively enhance the speed of goods delivery in intelligent warehousing systems, improve the space utilization of warehouses, and further reduce the operating costs of enterprises.