电商背景下的农村地区卡车–无人机协同配送的路径优化研究

Path Optimization of Truck-Drone Collaborative Delivery in Rural Areas under E-Commerce Context

摘要: 在乡村振兴战略的持续推动下，中国农村电子商务展现出强劲活力，2025年1~7月农产品网络零售额同比增长7.4%，农村网络零售额同比增长6.4%。尽管全国行政村快递服务覆盖率已高达95%，但仍面临客户分布分散、路网条件薄弱、末端配送成本高等挑战。本文提出一种卡车–无人机协同配送模式，以卡车作为主干运输工具与移动调度基站，无人机负责末端小批量、高时效的灵活配送，从而提升整体效率、降低运营成本，并规避传统路网修缮与配送中心建设等重资产投入风险。针对农村电商物流的货物特征与配送难点，构建以总成本最小为目标的混合整数规划模型，并设计两阶段启发式算法进行求解：第一阶段采用聚类方法对客户进行区域划分与任务预分配；第二阶段融合遗传算法与贪心策略，协同优化卡车路径与无人机任务序列，同时引入变邻域搜索进行动态调整，增强算法鲁棒性与求解质量。

Abstract: Under the continuous promotion of the rural revitalization strategy, China’s rural e-commerce has demonstrated strong vitality. From January to July 2025, the online retail sales of agricultural products increased by 7.4% year-on-year, while the rural online retail sales grew by 6.4%. Although the coverage rate of express delivery services in administrative villages nationwide has reached 95%, challenges such as scattered customer distribution, weak road network conditions, and high terminal delivery costs still exist. This paper proposes a truck-drone collaborative delivery model, where trucks serve as the main transportation tools and mobile dispatching base stations, while drones handle flexible small-batch, high-precision terminal deliveries. This approach enhances overall efficiency, reduces operational costs, and avoids the risks of heavy asset investments such as traditional road network repairs and distribution center construction. To address the cargo characteristics and delivery challenges in rural e-commerce logistics, a hybrid integer programming model with the objective of minimizing total cost is constructed, and a two-stage heuristic algorithm is designed for solving: the first stage uses clustering methods to divide customers into regions and pre-allocate tasks; the second stage integrates genetic algorithms and greedy strategies to collaboratively optimize truck routes and drone task sequences. At the same time, variable neighborhood search is introduced for dynamic adjustment, enhancing the algorithm’s robustness and solution quality.