Driving Heterogeneity in Traffic Flow Theory

An Action-based Framework for Identification, Modelling, and Simulation

Doctoral Thesis (2026)
Author(s)

X. Yao (TU Delft - Traffic Systems Engineering)

Contributor(s)

S.P. Hoogendoorn – Promotor (TU Delft - Traffic Systems Engineering)

S.C. Calvert – Copromotor (TU Delft - Traffic Systems Engineering)

Research Group
Traffic Systems Engineering
More Info
expand_more
Publication Year
2026
Language
English
Defense Date
21-01-2026
Awarding Institution
Delft University of Technology
Research Group
Traffic Systems Engineering
ISBN (print)
978-90-5584-378-7
Downloads counter
181
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Human driving behaviour is inherently heterogeneous, shaping traffic dynamics and affecting traffic safety, efficiency and sustainbility. This dissertation develops an interpretable, AI-driven framework to identify, model, and simulate heterogeneous driving behaviour using naturalistic data. By analysing action phases, patterns, and behavioural sequences, it reveals how behavioural variability influences traffic performance and supports improved traffic management, personalised driver assistance, and human-aware autonomous vehicle design.

Files

License info not available