Courier Working Time Aware Vehicle Scheduling for Efficient Urban Logistics

Order Transfer from the transfer center to delivery stations is an essential and expensive part of urban logistics. Vehicles are scheduled to send transferred orders to multiple delivery stations sequentially in one transfer trip. A key problem is to generate the vehicle’s route for efficient order transfer, i.e., minimizing average order transfer time. In this paper, we explore fine-grained delivery station features, i.e., downstream couriers’ remaining working times in last-mile delivery trips and the transferred order distribution to design a Prediction-and-Scheduling framework for efficient Order Transfer called PSOT+ , including three main components: i) a Courier’s Remaining Working Time Prediction component to predict each courier’s working time for conducting heterogeneous tasks with attention-based route generation and multi-task-based working time and workload co-prediction; ii) a Single Vehicle Scheduling component to generate a vehicle’s route to delivery stations with an order-transfer-time-aware heuristic algorithm; and iii) a Capacity-Constrained Vehicle Scheduling component to generate multiple vehicles’ cooperative order transfer routes with a capacity-constrained inter-exchange algorithm. The evaluation results with real-world data from one of the largest logistics companies in China show PSOT+ improves the courier’s remaining working time prediction effectively and reduces the average order transfer time by up to 59% compared to state-of-the-art methods.