In a survey of Belgian logistics service providers, the efficiency of first-mile pickup operations was identified as a key area for improvement, given the increasing number of returns in e-commerce, which has a significant impact on traffic congestion, carbon emissions, energy consumption and operational costs. However, the complexity of first-mile pickup operations, resulting from the small number of parcels to be collected at each pickup location, customer time windows, and the need to efficiently accommodate the highly heterogeneous cargo inside the vans, has hindered the development of real-world solution approaches. This article tackles this operational problem as a vehicle routing problem with time windows, time-dependent travel durations, and split pickups and integrates practical 3D container loading constraints such as vertical and horizontal stability as well as a more realistic reachability constraint to replace the classical “Last In First Out” (LIFO) constraint. To solve it, we propose a three-phase heuristic based on a savings constructive heuristic, an extreme point concept for the loading aspect and a General Variable Neighborhood Search as an improvement phase for both routing and packing. Numerical experiments are conducted to assess the performance of the algorithm on benchmark instances and new instances are tested to validate the positive managerial impacts on cost when allowing split pickups and on driver working duration when extending customer time windows. In addition, we show the impacts of considering the reachability constraint on cost and of the variation of speed during peak hours on schedule feasibility.

中文翻译：

---

具有分离皮卡和时间窗的三维加载车辆路径问题的三阶段算法


在对比利时物流服务提供商的调查中，鉴于电子商务退货数量不断增加，第一英里取货操作的效率被确定为需要改进的关键领域，这对交通拥堵、碳排放、能源消耗和运营成本有重大影响。然而，由于每个取货地点需要收集的包裹数量较少、客户时间窗口以及需要有效容纳货车内高度异构的货物，导致第一英里取件操作的复杂性阻碍了实际解决方案的开发。本文将这个操作问题作为具有时间窗口、时间相关行驶持续时间和分体式皮卡的车辆路径问题来解决，并集成了实用的 3D 集装箱装载约束，例如垂直和水平稳定性，以及更现实的可达性约束，以取代经典的“后进先出”（LIFO） 约束。为了解决这个问题，我们提出了一个基于节省建设性启发式的三阶段启发式方法，一个用于加载方面的极端点概念和一个通用变量邻域搜索作为布线和包装的改进阶段。进行了数值实验以评估算法在基准实例上的性能，并测试了新实例，以验证在允许分车时对成本的积极管理影响，以及在延长客户时间窗口时对驾驶员工作持续时间的积极影响。此外，我们还展示了考虑可达性约束对成本的影响，以及高峰时段速度变化对计划可行性的影响。