AN AI-BASED FRAMEWORK FOR ROUTE OPTIMIZATION IN LAST-MILE DELIVERY: IMPLICATIONS FOR E-COMMERCE LOGISTICS IN VIETNAM
DOI:
https://doi.org/10.62985/j.huit_ojs.vol26.no3E.534Từ khóa:
Artificial Intelligence (AI), Green logistics, Last-mile delivery, Route optimization, E-commerce, Vietnam.Tóm tắt
The explosive growth of e-commerce in Vietnam has significantly increased the need for last-mile delivery, which in turn has resulted in problems related to logistics efficiency, costs, and carbon emissions. In alignment with Vietnam’s National Green Growth Strategy and the country’s commitment to attain Net-zero emissions by 2050, the utilization of Artificial Intelligence (AI) for route optimization has become a strategic approach to improve delivery efficiency and cut down fuel consumption. This study examines how AI is currently being used for route optimization in Vietnam’s e-commerce logistics sector and also introduces an AI-based model for last-mile delivery route optimization tailored to the specific context of emerging market like Vietnam, through the use of technologies such as Graph Machine Learning, Federated Learning, and Reinforcement Learning. This model aims to develop a more intelligent, efficient, and sustainable e-commerce logistics ecosystem in Vietnam. Moreover, this research provides practical implications for e-commerce logistics enterprises in Vietnam in adopting AI for route optimization in last-mile delivery.
Tài liệu tham khảo
[1] Avalara, “The State of Global Cross-Border E-Commerce Report 2023-24,” Accessed: Apr. 01, 2026. [Online]. Available: https://www.avalara.com/dam/avalara/public/documents/pdf/state-of-global-cross-border-ecommerce-report-2023-2024.pdf
[2] W. K. Fong and Y. Zhou, “Emerging economies can lead the way on green logistics. Experts explain why,” Accessed: Apr. 01, 2026. [Online]. Available: https://www.weforum.org/stories/2025/07/emerging-economies-global-green-logistics-development/
[3] D. Singh, G. Higgs, and P. Lam, “Cost of Convenience: Revealing the hidden climate and health impacts of the Global e-commerce-driven parcel delivery industry through 2030,” Accessed: Apr. 01, 2026. [Online]. Available: https://stand.earth/wp-content/uploads/2023/05/CostOfConvenience_Final-Design.pdf
[4] Accenture, “The Sustainable Last Mile. Faster. Cheaper. Greener,” Accessed: Apr. 01, 2026. [Online]. Available: https://www.accenture.com/content/dam/accenture/final/a-com-migration/r3-3/pdf/pdf-148/accenture-sustainable-mile-pov.pdf
[5] Vietnam E-commerce Association, “Vietnam E-Business Report 2025.” Accessed: Apr. 01, 2026. [Online]. Available: https://en.vecom.vn/vietnam-e-business-report-2025
[6] Ministry of Industry and Trade, “Vietnam Logistics Report 2024,” Hanoi, 2024. Accessed: Apr. 01, 2026. [Online]. Available: http://www.spchcmc.vn/FCKeditor/img/file/ThongTinNongNghiep/TinTuc/2024/LOGISTIC/16-12-2024/BAO%20CAO%20LOGISTIC%20VIET%20NAM%202024.pdf
[7] O. I. Dorosh, Yu. V. Oherchuk, and Y. Plish, “Problems and prospects of the development of green logistics,” Management and Entrepreneurship in Ukraine: the stages of formation and problems of development, vol. 6, no. 2, pp. 286–295, 2024, doi: https://doi.org/10.23939/SMEU2024.02.286
[8] I. V. Larina et al., “Green logistics - Modern transportation process technology,” Production Engineering Archives, vol. 27, no. 3, pp. 184–190, 2021, doi: https://doi.org/10.30657/PEA.2021.27.24
[9] A. G. Fareed et al., “Role and applications of advanced digital technologies in achieving sustainability in multimodal logistics operations: A systematic literature review,” Sustainable Futures, vol. 8, Art. no. 100278, 2024, doi: https://doi.org/10.1016/J.SFTR.2024.100278
[10] N. Tsolakis et al., “Towards AI driven environmental sustainability: an application of automated logistics in container port terminals,” International Journal of Production Research, vol. 60, no. 14, pp. 4508–4528, 2022, doi: https://doi.org/10.1080/00207543.2021.1914355
[11] S. Jahagirdar, S. Jahagirdar, A. Apandkar, “Green Logistics and Sustainable Transportation: AI-Based Route Optimization, Carbon Footprint Reduction, And The Future of Eco-Friendly Supply Chains,” Journal of Informatics Education and Research, vol. 5, no. 1, 2025, doi: https://doi.org/10.52783/JIER.V5I1.2323
[12] K. M. Hussain, “Revolutionizing Route Optimization Systems with Artificial Intelligence for a Smarter, Sustainable Logistics Ecosystem,” International Journal of Computer Science and Mobile Computing, vol. 14, no. 2, pp. 66–68, 2025, doi: https://doi.org/10.47760/ijcsmc.2025.v14i02.008
[13] L. Abualigah et al., “Salp swarm algorithm: a comprehensive survey,” Neural Computing and Applications, vol. 32, no. 15, pp. 11195–11215, 2019, doi: https://doi.org/10.1007/s00521-019-04629-4
[14] J. J. Q. Yu, W. Yu, and J. Gu, “Online Vehicle Routing with Neural Combinatorial Optimization and Deep Reinforcement Learning,” IEEE Transactions on Intelligent Transportation Systems, vol. 20, no. 10, pp. 3806–3817, 2019, doi: https://doi.org/10.1109/TITS.2019.2909109
[15] I. Bello et al., “Neural Combinatorial Optimization with Reinforcement Learning,” 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings, Nov. 2016, doi: https://doi.org/10.48550/arXiv.1611.09940
[16] M. A. El-Shorbagy and I. Nasar, “Salp Swarm Optimization: A Comprehensive Review of Recent Advances, Variants, Applications, and Future Research Directions,” European Journal of Pure and Applied Mathematics, vol. 18, no. 4, pp. 7030–7030, 2025, doi: https://doi.org/10.29020/nybg.ejpam.v18i4.7030
[17] M. Liu, E. Demir, and L. Jian, “Reinforcement Learning for the Vehicle Routing Problem: Methodologies, Applications, and Research Outlook,” Arabian Journal for Science and Engineering, vol. 51, no. 5, pp. 6497–6524, 2025, doi: https://doi.org/10.1007/S13369-025-10744-3
[18] R. Jagirdar and C. Pathak, “AI-driven transportation solutions: Lessons from developed nations for emerging economies,” Journal of Public Transportation System, vol. 4, no. 1, pp. 15–37, 2025, doi: https://doi.org/10.34218/jpts_04_01_002
[19] S. Dikshit et al., “The Use of Artificial Intelligence to Optimize the Routing of Vehicles and Reduce Traffic Congestion in Urban Areas,” EAI Endorsed Transactions on Energy Web, vol. 10, pp. 1–13, 2023, doi: https://doi.org/10.4108/ew.4613
[20] V. Bhat et al., “Last-Mile Delivery in High-Density Emerging Economy Cities Using Crowd-Generated Data and Artificial Intelligence,” Communications in Computer and Information Science, vol. 2557 CCIS, pp. 55–70, 2026, doi: https://doi.org/10.1007/978-3-031-98235-4_5
[21] P. N. Duy et al., “Generative AI in Developing Countries: Adoption Dynamics in Vietnamese Local Government,” Informatics 2026, vol. 13, no. 2, Art. no. 22, 2026, doi: https://doi.org/10.3390/informatics13020022
[22] UNDP Vietnam; IPS. Quick Assessment of Application of Artificial Intelligence (AI) in Vietnam Public Sector: Policy Recommendations. 2025. Available online: https://www.undp.org/vi/vietnam/publications/danh-gia-nhanh-ve-ung-dung-tri-tue-nhan-tao-ai-trong-co-quan-nha-nuoc-tai-viet-nam-khuyen-nghi-chinh-sach (accessed on 01 April 2026).
[23] H. Zhu et al., “AIoT-Enabled Federated Learning for Green Supply Chain Demand Forecasting with Privacy-Preserving Carbon Reference Effects,” IEEE Internet of Things Journal, vol. 12, no. 19, pp. 39543–39555, 2025, doi: https://doi.org/10.1109/JIOT.2025.3590155
[24] E. E. Blanco and Y. Sheffi, "Green Logistics," in Springer Series in Supply Chain Management, vol. 23. Cham, Switzerland: Springer, 2024, pp. 101–141, doi: https://doi.org/10.1007/978-3-031-45565-0_5
[25] G. Nagy and S. Szentesi, “Green logistics: Transforming supply chains for a sustainable future,” Advanced Logistic Systems - Theory and Practice, vol. 18, no. 3, pp. 29–42, Oct. 2024, doi: https://doi.org/10.32971/ALS.2024.026
[26] R. Dekker, J. Bloemhof, and I. Mallidis, “Operations Research for green logistics – An overview of aspects, issues, contributions and challenges,” European Journal of Operational Research, vol. 219, no. 3, pp. 671–679, 2012, doi: https://doi.org/10.1016/j.ejor.2011.11.010
[27] N. Fegde, “Challenges and Solutions in Managing Last-Mile Delivery in Urban Areas,” International Journal of Scientific Research in Engineering and Management, vol. 09, no. 01, pp. 1–9, Jan. 2025, doi: https://doi.org/10.55041/IJSREM40615
[28] S. Kedla, D. B. Meghana, and A. J. Deepashree, “Changing the Landscape of Logistic Sector: Way Towards Green Logistics in Circular Economy,” European Journal of Management, Economics and Business, vol. 2, no. 2, pp. 55–60, 2025, doi: https://doi.org/10.59324/ejmeb.2025.2(2).06
[29] A. McKinnon et al., Green Logistics: Improving the Environmental Sustainability of Logistics. Kogan Page Publishers, 2015.
[30] N. T. C. Loan et al., “Last–Mile Delivery in B2C E-Commerce – Common Practices in Some Countries, But What Do They Mean for Businesses in Vietnam?,” Journal of Hunan University Natural Sciences, vol. 49, no. 5, pp. 21–32, 2022, doi: https://doi.org/10.55463/ISSN.1674-2974.49.5.3
[31] H. C. Pham et al., "Last mile delivery as a competitive logistics service-A case study," in Proceedings of the International Conference on Operations and Supply Chain Management, Saigon, Vietnam, vol. 15, 2019, p. 18.
[32] A. Patil, “Last- mile challenges and recommended solution,” International Journal of Multidisciplinary Research and Growth Evaluation, vol. 6, no. 2, pp. 1814–1818, 2025, doi: https://doi.org/10.54660/.ijmrge.2025.6.2.1814-1818
[33] Decathlon, “How can we decarbonise the last-mile delivery?,” Decathlon Sustainability. Accessed: Apr. 01, 2026. [Online]. Available: https://sustainability.decathlon.com/how-can-we-decarbonise-the-last-mile-delivery
[34] Z. Li, “The Impact of E-commerce Last-mile Delivery on Environmental Sustainability,” Proceedings of the 5th Management Science Informatization and Economic Innovation Development Conference, 2024, doi: https://doi.org/10.4108/EAI.8-12-2023.2344383
[35] Yahoo Finance, “Last-Mile Delivery Market Size to Reach US$ 311.31 Billion by 2031, Growing at 9.62% CAGR - Analysis by DataM Intelligence.” Accessed: Apr. 01, 2026. [Online]. Available: https://finance.yahoo.com/news/last-mile-delivery-market-size-143000798.html
[36] T. Lyons and N. C. McDonald, “Last-Mile Strategies for Urban Freight Delivery: A Systematic Review,” Transportation Research Record, vol. 2677, no. 1, pp. 1141–1156, 2023, doi: https://doi.org/10.1177/03611981221103596
[37] N. Giuffrida et al., “Optimization and Machine Learning Applied to Last-Mile Logistics: A Review,” Sustainability, vol. 14, no. 9, p. 5329, 2022, doi: https://doi.org/10.3390/su14095329
[38] A. Chandramouli, “Optimizing Last-Mile Delivery Operations: Leveraging Predictive Analytics, Technology Integration, and Sustainable Practices,” Journal of Mathematical & Computer Applications, vol. 2, no. 3, pp. 1–7, 2023, doi: https://doi.org/10.47363/JMCA/2023(2)145
[39] M. Choi, H. Cha, and T. Cheong, “Multi-Period Multi-Depot Vehicle Routing Problem for Mobile Center-Based Last Mile Delivery,” IEEE Access, vol. 14, pp. 28957–28973, 2026, doi: https://doi.org/10.1109/ACCESS.2026.3666531
[40] J. F. Cordeau and M. Maischberger, “A parallel iterated tabu search heuristic for vehicle routing problems,” Computers & Operations Research, vol. 39, no. 9, pp. 2033–2050, 2012, doi: https://doi.org/10.1016/j.cor.2011.09.021
[41] J. Luo and M. R. Chen, “Multi-phase modified shuffled frog leaping algorithm with extremal optimization for the MDVRP and the MDVRPTW,” Computers & Industrial Engineering, vol. 72, no. 1, pp. 84–97, 2014, doi: https://doi.org/10.1016/j.cie.2014.03.004
[42] Y. Ma et al., “An improved ACO for the multi-depot vehicle routing problem with time windows,” Advances in Intelligent Systems and Computing, vol. 502, pp. 1181–1189, 2017, doi: https://doi.org/10.1007/978-981-10-1837-4_96
[43] H. Bae and I. Moon, “Multi-depot vehicle routing problem with time windows considering delivery and installation vehicles,” Applied Mathematical Modelling, vol. 40, no. 13–14, pp. 6536–6549, 2016, doi: https://doi.org/10.1016/j.apm.2016.01.059
[44] K. Zhang, X. Lin, and M. Li, “Graph attention reinforcement learning with flexible matching policies for multi-depot vehicle routing problems,” Physica A: Statistical Mechanics and its Applications, vol. 611, p. 128451, 2023, doi: https://doi.org/10.1016/j.physa.2023.128451
[45] Y. Wang and X. Liang, “Application of Reinforcement Learning Methods Combining Graph Neural Networks and Self-Attention Mechanisms in Supply Chain Route Optimization,” Sensors, vol. 25, no. 3, p. 955, 2025, doi: https://doi.org/10.3390/s25030955
[46] A. T. Wasi et al., “Graph Neural Networks in Supply Chain Analytics and Optimization: Concepts, Perspectives, Dataset and Benchmarks,” arXiv:2411.08550, Jun. 2025, doi: https://doi.org/10.48550/arXiv.2411.08550
[47] D. G. S. M. Sai et al., “A Novel Reinforcement Learning Based Optimization Approach for Supply Chain Management,” Proceedings - 4th IEEE 2023 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS), pp. 655–661, 2023, doi: https://doi.org/10.1109/ICCCIS60361.2023.10425106
[48] I. P. P. Astawa and I. M. R. M. Arsha, “Artificial Intelligence and Business Models from the Perspective of Innovation and Operational Efficiency of Companies: Systematic Literature Review,” International Journal of Research and Innovation in Social Science, vol. VIII, no. XI, pp. 1882–1899, 2024, doi: https://doi.org/10.47772/IJRISS.2024.8110147
[49] T. Banker and A. Mesbah, “Model-free Reinforcement Learning for Model-based Control: Towards Safe, Interpretable and Sample-efficient Agents,” 2025, doi: https://doi.org/10.48550/arXiv.2507.13491
[50] A. Russo and A. Proutiere, “Model-Free Active Exploration in Reinforcement Learning,” 2024, doi: https://doi.org/10.48550/arXiv.2407.00801
[51] J. Schulman et al., “Proximal Policy Optimization Algorithms,” 2017, doi: https://doi.org/10.48550/arXiv.1707.06347
[52] E. Deineko and C. Kehrt, “Learn to Solve Vehicle Routing Problems ASAP: A Neural Optimization Approach for Time-Constrained Vehicle Routing Problems with Finite Vehicle Fleet,” 2024, doi: https://doi.org/10.48550/arXiv.2411.04777
[53] K. Zhang, Z. Yang, and T. Başar, “Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms,” Studies in Systems, Decision and Control, vol. 325, pp. 321–384, 2021, doi: https://doi.org/10.1007/978-3-030-60990-0_12
[54] W. Li et al., “Research on GNNs with stable learning,” Scientific Reports, vol. 15, no. 1, p. 29002, 2025, doi: https://doi.org/10.1038/s41598-025-12840-8
[55] Z. Liu and J. Zhou, “Graph Attention Networks,” in Introduction to Graph Neural Networks, Synthesis Lectures on Artificial Intelligence and Machine Learning. Cham, Switzerland: Springer, 2020, pp. 39–41, doi: https://doi.org/10.1007/978-3-031-01587-8_7
[56] J. Liu et al., “Accelerating Decentralized Federated Learning with Probabilistic Communication in Heterogeneous Edge Computing,” IEEE Transactions on Networking, vol. 34, pp. 486–501, 2026, doi: https://doi.org/10.1109/TON.2025.3600015
[57] C. Xu et al., “A Deep Reinforcement Learning Method for Autonomous Driving Integrating Multi-Modal Fusion,” IEEE Transactions on Intelligent Transportation Systems, vol. 26, no. 8, pp. 11850–11863, 2025, doi: https://doi.org/10.1109/TITS.2025.3573781
[58] S. Nghia, “Vietnam’s transport and logistics market is forecasted to reach USD 48.6 billion in 2024,” VTV Times. Accessed: Apr. 01, 2026. [Online]. Available: https://vtv.vn/kinh-te/thi-truong-van-tai-va-logistics-cua-viet-nam-du-bao-cham-moc-486-ty-usd-trong-nam-2024-20241201111202451.htm
[59] Vneconomy, “Global logistics firms have adopted Industry 4.0 technology, while Vietnamese enterprises are still struggling due to lack of capital,” Vietnam Logistics Business Association. Accessed: Apr. 01, 2026. [Online]. Available: https://vla.com.vn/cac-hang-logistics-the-gioi-da-ung-dung-cong-nghe-4-0-doanh-nghiep-viet-van-con-loay-hoay-vi-thieu-von/
[60] V. N. Hanh, “Vietnam E-Commerce Growth: Key Findings from the 2025 E-Business Index,” Vietnam Briefing. Accessed: Apr. 01, 2026. [Online]. Available: https://www.vietnam-briefing.com/news/vietnam-e-commerce-growth-key-findings-from-the-2025-e-business-index.html/
[61] The Prime Minister, “Decision No. 749/QD-TTg dated June 3, 2020, Introducing Program for National Digital Transformation by 2025 with Orientations Towards 2030,”, Hanoi, Vietnam, Jun. 3, 2020. Accessed: Apr. 01, 2026. [Online]. Available: https://thuvienphapluat.vn/van-ban/Cong-nghe-thong-tin/Quyet-dinh-749-QD-TTg-2020-phe-duyet-Chuong-trinh-Chuyen-doi-so-quoc-gia-444136.aspx
[62] The Prime Minister, “Decision No. 221/QD-TTg Amending and Supplementing Decision No. 200/QD-TTg dated February 14, 2017, Approving the Action Plan to Enhance Competitiveness and Develop Vietnam’s Logistics Services until 2025”, Hanoi, Vietnam, Feb. 22, 2021. Accessed: Apr. 01, 2026. [Online]. Available: https://thuvienphapluat.vn/van-ban/Thuong-mai/Quyet-dinh-221-QD-TTg-nam-2021-sua-doi-Quyet-dinh-200-QD-TTg-phat-trien-dich-vu-logistics-465626.aspx
[63] Ministry of Industry and Trade of Vietnam, “Decision 1568/QD-BCT dated June 3, 2025, Approving Master Plan for National Electronic commerce Development 2026-2030 period,” Hanoi, Vietnam, 2025. Accessed: Apr. 01, 2026. [Online]. Available: https://thuvienphapluat.vn/van-ban/Thuong-mai/Decision-1568-QD-BCT-2025-Master-Plan-for-National-Electronic-commerce-Development-2026-2030-662064.aspx
[64] Ministry of Industry and Trade, “Logistics service businesses in Vietnam transform digitally to reduce costs,” Vietnam Logistics Portal, 2024. Accessed: Apr. 01, 2026. [Online]. Available: https://logistics.gov.vn/logistics-service-businesses-in-vietnam-transform-digitally-to-reduce-costs
[65] T. Phuong, “Logistics businesses transform digitally to optimize costs,” Vietnam Logistics Portal, 2023. Accessed: Apr. 01, 2026. [Online]. Available: https://logistics.gov.vn/logistics-businesses-transform-digitally-to-optimize-costs
[66] VOV, “Policies needed to support logistics businesses in digital and green transformation,” 2024. Accessed: Apr. 01, 2026. [Online]. Available: https://vov.vn/kinh-te/can-chinh-sach-de-ho-tro-doanh-nghiep-logistics-chuyen-doi-so-chuyen-doi-xanh-post1128625.vov
[67] M. Prates et al., “Learning to solve NP-complete problems: A graph neural network for decision TSP,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, no. 01, 2019, pp. 4731–4738.
