Every day, millions of trucks and other vehicles perform deliveries or services around the globe. To reduce costs and environmental impact, optimal routing has become increasingly relevant. Efficient transport is often a big puzzle; in jargon formulated as solving 'vehicle routing problems' (VRP's). For many companies, solving vehicle routing problems is an essential daily task, supported by smart algorithms.

Innovative techniques to solve routing problems

The EURO Meets NeurIPS 2022 Vehicle Routing Competition seeks to unite Operations Research and Machine Learning to propose new, innovative techniques to solve routing problems. ORTEC happily organizes this competition as part of the annual NeurIPS conference, supported by renowned academic organizations.

A unique combination: the best of both worlds

The competition bridges the domains of Operations Research and Machine Learning – which is a unique combination. Traditionally, vehicle routing problems have been studied in the field of Operations Research (OR); lately they have been the subject of extensive work in the scientific Machine Learning (ML).

Both methods can come up with a solution separately, but combining them can even lead to better results, believes Wouter Kool, initiator of the competition and Senior OR Engineer at ORTEC. “With this competition, we bring researchers from different disciplines together and provide them with a relevant problem based on realistic data to work on. While both Machine Learning and Operations Research methods can come to a solution, only together will the best solution emerge: the best routes under changing circumstances." Joaquim Gromicho, Science & Education Officer at ORTEC, confirms: “I’m proud that ORTEC initiates this competition as it connects two worlds that normally still exist alongside each other.”

Relevancy of the competition

The world becomes increasingly complex and fast, meaning also algorithms need to become more dynamic: not just solving a problem once, but continuously, under changing circumstances. The best solutions are likely to be a mix of Operations Research and Machine Learning and will emerge from high-quality academic research.

Real data for real relevance

Normally, routing competitions work with limited, often synthetically generated, data. To make the competition more realistic and relevant, ORTEC provides a set of real, anonymized data. Actual road distances are for instance now considered. To encourage actual improvement of the state-of-the-art, ORTEC provides a state-of-the-art Vehicle Routing with Time Windows (VRPTW) as a starting point for participants.

The timeline

Today, on the 1st of August, the code submission platform opens. At the end of October is the deadline for submission, with the results and winner presentations on the 9th of December 2022.

We anticipate that the winning method will significantly advance the state-of-the-art for solving routing problems, therefore providing a strong foundation for further research in both the Operations Research and Machine Learning communities, as well as a practical impact on the real-world solving of vehicle routing problems.

---

About the competition

The EURO Meets NeurIPS 2022 Vehicle Routing Competition is a joint effort of several previous competitions: the 12th DIMACS Implementation Challenge, the series of VeRoLog competitions, and the AI4TSP competition. The competition is hosted at the Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022). Sponsors are the Association of European Operational Research Societies (EURO), the Eindhoven AI Systems Institute (EAISI), and ORTEC.

More details on the competition can be found here or stay up-to-date on Twitter.