Data Driven VRP: A Neural Network Model to Learn Hidden Preferences for VRP

Jayanta Mandi, Rocsildes Canoy, Victor Bucarey Lopez, Tias Guns

Research output: Chapter in Book/Report/Conference proceedingConference paper

Abstract

The traditional Capacitated Vehicle Routing Problem (CVRP) minimizes the total distance of the routes under the capacity constraints of the vehicles. But more often, the objective involves multiple criteria including not only the total distance of the tour but also other factors such as travel costs, travel time, and fuel consumption. Moreover, in reality, there are numerous implicit preferences ingrained in the minds of the route planners and the drivers. Drivers, for instance, have familiarity with certain neighborhoods and knowledge of the state of roads, and often consider the best places for rest and lunch breaks. This knowledge is difficult to formulate and balance when operational routing decisions have to be made. This motivates us to learn the implicit preferences from past solutions and to incorporate these learned preferences in the optimization process. These preferences are in the form of arc probabilities, i.e., the more preferred a route is, the higher is the joint probability. The novelty of this work is the use of a neural network model to estimate the arc probabilities, which allows for additional features and automatic parameter estimation. This first requires identifying suitable features, neural architectures and loss functions, taking into account that there is typically few data available. We investigate the difference with a prior weighted Markov counting approach, and study the applicability of neural networks in this setting.

Original languageEnglish
Title of host publicationData Driven VRP: A Neural Network Model to Learn Hidden Preferences for VRP
EditorsLaurent D. Michel
PublisherSchloss Dagstuhl - Leibniz-Zentrum für Informatik
Pages42:1-42:17
Number of pages17
Volume210
ISBN (Electronic)9783959772112
ISBN (Print)978-3-95977-211-2
DOIs
Publication statusPublished - 15 Oct 2021
Event27th International Conference on Principles and Practice of Constraint Programming (CP 2021) - Online
Duration: 25 Oct 202129 Oct 2021
https://cp2021.a4cp.org/

Publication series

NameLeibniz International Proceedings in Informatics (LIPIcs)
PublisherSchloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik

Conference

Conference27th International Conference on Principles and Practice of Constraint Programming (CP 2021)
Period25/10/2129/10/21
Internet address

Keywords

  • Vehicle routing problem
  • Preference learning
  • Neural network

Fingerprint

Dive into the research topics of 'Data Driven VRP: A Neural Network Model to Learn Hidden Preferences for VRP'. Together they form a unique fingerprint.

Cite this