Article · IEEE Transactions on Intelligent Transportation Systems · January 2, 2024
Machine Learning to Solve Vehicle Routing Problems: A Survey
Aigerim Bogyrbayeva, Meraryslan Meraliyev, Taukekhan Mustakhov, Bissenbay Dauletbayev
Abstract
This paper provides a systematic overview of machine learning methods applied to solve NP-hard Vehicle Routing Problems (VRPs). Recently, there has been great interest from both the machine learning and operations research communities in solving VRPs either through pure learning methods or by combining them with traditional handcrafted heuristics. We present a taxonomy of studies on learning paradigms, solution structures, underlying models, and algorithms. Detailed results of state-of-the-art methods are presented, demonstrating their competitiveness with traditional approaches. The survey highlights the advantages of the machine learning-based models that aim to exploit the symmetry of VRP solutions. The paper outlines future research directions to incorporate learning-based solutions to address the challenges of modern transportation systems.
More by Aigerim Bogyrbayeva
- Reinforcement Learning for Efficient Drone-Assisted Vehicle RoutingApplied Sciences · 2025 · Citations: 9
- Deep Reinforcement Learning for Stochastic Dynamic Vehicle Routing ProblemInternational Conference on Electronics, Computer and Computation · 2023 · Citations: 5
- A deep reinforcement learning approach for solving the Traveling Salesman Problem with DroneTransportation Research Part C Emerging Technologies · 2023 · Citations: 125
- A Reinforcement Learning Approach for Rebalancing Electric Vehicle Sharing SystemsIEEE Transactions on Intelligent Transportation Systems · 2021 · Citations: 40