Data-driven preference-based routing and scheduling for activity-based freight transport modelling

Nadi Najafabadi, A.; Yorke-Smith, N.; Snelder, M.; van Lint, J.W.C.; Tavasszy, Lorant

doi:10.1016/j.trc.2023.104413

Data-driven preference-based routing and scheduling for activity-based freight transport modelling

Title

Data-driven preference-based routing and scheduling for activity-based freight transport modelling

Author

Nadi Najafabadi, A. (TU Delft Transport and Planning)
Yorke-Smith, N. (TU Delft Algorithmics)
Snelder, M. (TU Delft Transport and Planning; TNO)
van Lint, J.W.C. (TU Delft Transport and Planning)
Tavasszy, Lorant (TU Delft Transport and Planning)

Date

2023

Abstract

Understanding preferences and behaviours in road freight transport is valuable for planning and analysis. This paper proposes a data-driven vehicle routing and scheduling approach for use as a descriptive tool to study road freight transport activities. The model developed seeks to capture planners’ or drivers’ preferences in order to reproduce observed road freight activities. The model is based on a parametrized time-dependent vehicle routing problem whose parameters can be estimated from a set of observed planned tours. We propose a Bayesian optimization technique for parameter estimation of the model. Empirical results show that the model can fit real-world data accurately and synthesize tour flows close to reality.

Subject

Activity-based tour modelling
Bayesian optimization
Data-driven routing and scheduling
Freight transport modelling
Preference-based vehicle routing

To reference this document use:

http://resolver.tudelft.nl/uuid:c806cda9-e049-4bb5-822e-52f602c58d74

DOI

https://doi.org/10.1016/j.trc.2023.104413

ISSN

0968-090X

Source

Transportation Research. Part C: Emerging Technologies, 158

Part of collection

Institutional Repository