Learning Drivers’ Preferences in Delivery Route Planning

Learning Drivers’ Preferences in Delivery Route Planning: an Inverse Optimization Approach

van Beek, Piet (TU Delft Mechanical, Maritime and Materials Engineering; TU Delft Delft Center for Systems and Control)

Mohajerin Esfahani, P. (mentor)
Zattoni Scroccaro, P. (mentor)
Atasoy, B. (graduation committee)
Dabiri, A. (graduation committee)
Ren, Ke (graduation committee)

Delft University of Technology

Mechanical Engineering | Systems and Control

2022-11-10

Optimizing delivery routes is a well-researched topic, however, most of the classical approaches do not incorporate preferences of drivers, as those approaches focus on minimizing the time or distance of the routes. As a result, the actual driven route of an experienced driver often deviates from the proposed route since the drivers have tacit knowledge about the real-life conditions of the road network. Amazon proposed a challenge to learn a delivery route planning strategy from historically driven routes and thus incorporate this tacit knowledge.
In this thesis, we will tackle the challenge using data-driven inverse optimization to learn the zone sequencing patterns of drivers. The zone sequences of expert drivers are assumed to be the solutions to a traveling salesman problem (TSP) in which the weights represent the preference of a driver to use a certain edge. The values of the weights will be learned through inverse optimization. Our final approach achieves a score that ranks 4th out of the 48 models that qualified for the final round of the challenge.

Amazon Last Mile Routing Challenge
Inverse Optimization
Traveling Salesman Problem
Weights Optimization

http://resolver.tudelft.nl/uuid:f0d71d50-bc9f-423c-b5eb-f1a3c7e8de4d

Student theses

master thesis

© 2022 Piet van Beek