Journal article
Real-time multi-depot urban logistics optimization in megacities via transformer-based deep reinforcement learning
International journal of geographical information science : IJGIS, Vol.40(4), pp.1107-1130
04/03/2026
DOI: 10.1080/13658816.2025.2551723
Abstract
Rising customer demands and the complexities of dynamic urban systems pose significant challenges for logistics distribution, especially since large-scale real-time dynamic traffic information is not always accessible. However, few studies have focused on optimizing logistics in the ever-changing traffic environments of megacities with multiple distribution centers. This study proposes two deep reinforcement learning models with Transformer architectures to optimize logistics distribution time costs across multiple depots in static and dynamic traffic scenarios, respectively. The first model (DTM-MDVRP) incorporates travel times between customers as edge information in the encoder to pre-plan delivery routes. The second model (DTM-DMDVRP) introduces a feature embedding module to extract real-time traffic information for dynamic route optimization. Wuhan city was selected for logistics optimization experiments. Results indicate that DTM-MDVRP surpasses heuristic methods and other deep reinforcement learning methods in optimization effectiveness and computation time. In dynamic urban traffic environments, DTM-DMDVRP further improves distribution efficiency. Compared to the traditional attention model, DTM-DMDVRP reduces time costs by 7.77, 3.51, and 3.58% across three problem scales and can optimize delivery routes for 100 customer points within 0.30 seconds. The proposed DTM-DMDVRP enables the real-time dynamic scheduling of logistics vehicles for logistics enterprises.
Details
- Title: Subtitle
- Real-time multi-depot urban logistics optimization in megacities via transformer-based deep reinforcement learning
- Creators
- Qingfeng Guan - China University of GeosciencesYunpeng Fan - China University of GeosciencesYujia Wang - China University of GeosciencesLin Liang - China University of GeosciencesPeng Luo - MIT Senseable City LabYao Yao - China University of Geosciences
- Resource Type
- Journal article
- Publication Details
- International journal of geographical information science : IJGIS, Vol.40(4), pp.1107-1130
- DOI
- 10.1080/13658816.2025.2551723
- ISSN
- 1365-8816
- eISSN
- 1362-3087
- Publisher
- Taylor & Francis
- Number of pages
- 24
- Grant note
- 2022034 / "CUG Scholar" Scientific Research Funds at China University of Geosciences (Wuhan) 42471491; 42171466 / National Natural Science Foundation of China CCF-DiDi GAIA202516 / CCF-DiDi GAIA Collaborative Research Funds
- Language
- English
- Date published
- 04/03/2026
- Academic Unit
- School of Earth, Environment, and Sustainability
- Record Identifier
- 9985219866302771
Metrics
1 Record Views