Learning to Solve Vehicle Routing Problems: A Survey
It addresses the challenge of efficiently solving complex routing problems for transportation and logistics, but is incremental as it synthesizes existing research rather than introducing new methods.
This survey systematically reviews machine learning methods for solving NP-hard Vehicle Routing Problems, showing that state-of-the-art learning-based approaches are competitive with traditional methods.
This paper provides a systematic overview of machine learning methods applied to solve NP-hard Vehicle Routing Problems (VRPs). Recently, there has been a great interest from both machine learning and operations research communities to solve VRPs either by pure learning methods or by combining them with the traditional hand-crafted heuristics. We present the taxonomy of the studies for learning paradigms, solution structures, underlying models, and algorithms. We present in detail the results of the state-of-the-art methods demonstrating their competitiveness with the traditional methods. The paper outlines the future research directions to incorporate learning-based solutions to overcome the challenges of modern transportation systems.