Integrated Order Dispatching and Routing for Last-Mile Pickup via Deep Reinforcement Learning

2026-07-24

AI Summary

This study addresses the inefficiency arising from the decoupled decision-making between order assignment and route planning in last-mile delivery. To overcome this limitation, the authors propose an integrated optimization framework that jointly optimizes both tasks in real time by combining deep reinforcement learning with a graph attention network. The framework features a dynamic residual graph encoder and a personalized decoder, enhanced by a route-planning “oracle”-guided local search strategy. This approach achieves a favorable balance between solution quality and computational efficiency while maintaining scalability. Evaluated on a real-world dataset from Cainiao, the method significantly outperforms existing baselines and demonstrates strong practical applicability for large-scale, real-time delivery scheduling.

Abstract

In recent years, the growing complexity of last-mile pickup operations has increased the need for fast and accurate decision-making on logistics platforms. This challenge is fundamentally driven by two key and tightly coupled decision-making processes: order dispatching and routing. Solving them separately overlooks their interdependence, while fully end-to-end learning can be unstable and costly on large, variable-scale instances due to sparse rewards. To solve this problem, we propose an integrated optimization framework which couples a learned routing oracle with real-time dispatching heuristics. For the routing subproblem, we develop a Dynamic-Residual Graph Attention Network encoder with a Look-Ahead Courier-Personalized decoder. For the dispatching subproblem, we develop a routing-oracle-guided dispatching heuristic with local search, where the oracle provides near-optimal solutions to select candidate couriers while retaining real-time scalability. Extensive experiments on real-world datasets from Cainiao Logistics are used to test the performance of our approach, including an offline evaluation and an online rolling-horizon simulation. The experimental results show that our approach outperforms other benchmarks regarding solution quality and solving time, indicating it can effectively support logistics companies in solving real-time and large-scale last-mile pickup problems.

Problem

• order dispatching
• routing
• last-mile pickup
• deep reinforcement learning
• integrated optimization

Innovation

• integrated optimization
• deep reinforcement learning
• graph attention network
• routing oracle
• last-mile pickup