Decision-making models using artificial intelligence tools in planning intermodal routes
Abstract
Currently, the container transportation industry is undergoing active development due to the implementation of new technologies and modern information systems. These innovations allow for the optimization of supply chain management processes and the automation of transportation and logistics operations, which in turn enhances management efficiency. One of the crucial aspects in planning intermodal transportation is selecting the optimal route, as it directly impacts the cost and speed of cargo delivery. To address this challenge, it is essential to develop a tool that allows for a swift analysis of all transportation options, selection of the best route, and presentation of it to clients. The article discusses the existing machine learning methods used to optimize the route of vehicles. The main purpose of this article is to study the developed solutions for their further application in transport and logistics processes. The introduction of the studied tools will help participants in the transport and logistics market to effectively compare infrastructure opportunities with the emerging demand for transportation.
About the Authors
V. A. Londar
Russian University of Transport
Russian Federation
Russian Federation
Postgraduate student
Moscow
N. Y. Lakhmetkina
Russian University of Transport
Russian Federation
Russian Federation
Candidate of Technical Sciences, Associate Professor
Moscow
References
1. The Transport strategy of the Russian Federation for the period up to 2030 approved by the Decree of the Government of the Russian Federation dated November 22, 2008 No. 1734-R.
2. Bubnova G.V. Digital logistics – an innovative mechanism for the effective development and functioning of transport and logistics systems and complexes / G.V. Bubnova, B.A. Levin // International Journal of Open Information Technologies. - 2017. – No.3. – pp.72-78. EDN XYBPGP.
3. Joe, W., Lau, H.C.: Deep reinforcement learning approach to solve dynamic vehicle routing problem with stochastic customers. In: Proceedings of the International Conference on Automated Planning and Scheduling, vol. 30, pp. 394–402 (2020)
4. Nazari, M. R., Oroojlooy, A., Snyder, L., Takac, M.: Reinforcement learning for solving the vehicle routing problem. In: Advances in Neural Information Processing Systems, pp. 9860–9870 (2018)
5. Nalepa, J.: Wheremachine learning meets smart delivery systems. In: Smart Delivery Systems. pp. 203–226. Elsevier (2020)
6. Kool,W., Van, H.,Welling, M.: Attention, learn to solve routing problems! arXiv:1803.08475 [cs, stat] (2019)
7. Lu, H., Zhang, X., Yang, S.: A learning-based iterative method for solving vehicle routing problems. In: Presented at the International Conference on Learning Representations Sept 25 (2019)
8. Yu, J.J., Yu, W., Gu, J.: Online vehicle routing with neural combinatorial optimization and deep reinforcement learning. In: Presented at the IEEE Transactions on Intelligent Transportation Systems 20, 3806–3817 (2019)
9. Zhao, J., Mao, M., Zhao, X., Zou, J.: A hybrid of deep reinforcement learning and local search for the vehicle routing problems. IEEE Trans. Intell. Transport. Syst. 1–11 (2020)
10. Kalakanti, A.K., Verma, S., Paul, T., Yoshida, T.: RL SolVeR Pro: reinforcement learning for solving vehicle routing problem. In: 2019 1st InternationalConference on Artificial Intelligence and Data Sciences (AiDAS), pp. 94–99. IEEE, Ipoh, Perak, Malaysia (2019)
11. Lin, B., Ghaddar, B., Nathwani, J.: Deep reinforcement learning for electric vehicle routing problem with time windows arXiv:2010.02068 [cs, math, stat] (2021)
12. Tomljenovic, V., Merzifonluoglu, Y. & Spigler, G. Optimizing inland container shipping through reinforcement learning. Annals of Operations Research (2024) https://doi.org/10.1007/s10479-024-05927-4.
Review
For citations:
Londar V.A., Lakhmetkina N.Y. Decision-making models using artificial intelligence tools in planning intermodal routes. Logistics and Supply Chain Management. 2024;21(1):52-61. (In Russ.)
Views:
50
Email this article 