Physics-informed Learning for Identification and State Reconstruction of Traffic Density

Matthieu Barreau, Miguel Aguiar, John Liu, Karl Henrik Johansson

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

12 Scopus citations

Abstract

We consider the problem of traffic density reconstruction using measurements from probe vehicles (PVs) with a low penetration rate. In other words, the number of sensors is small compared to the number of vehicles on the road. The model used assumes noisy measurements and a partially unknown first-order model. All these considerations make the use of machine learning to reconstruct the state the only applicable solution. We first investigate how the identification and reconstruction processes can be merged and how a sparse dataset can still enable a good identification. Secondly, we propose a pre-training procedure that aids the hyperparameter tuning, preventing the gradient descent algorithm from getting stuck at saddle points. Examples using numerical simulations and the SUMO traffic simulator show that the reconstructions are close to the real density in all cases.
Original languageEnglish (US)
Title of host publication2021 60th IEEE Conference on Decision and Control (CDC)
PublisherIEEE
Pages2653-2658
Number of pages6
ISBN (Print)9781665436595
DOIs
StatePublished - Dec 14 2021
Externally publishedYes

Bibliographical note

KAUST Repository Item: Exported on 2022-06-21
Acknowledged KAUST grant number(s): OSR-2019-CRG8-4033
Acknowledgements: This research is partially funded by the KAUST Office of Sponsored Research under Award No. OSR-2019-CRG8-4033, the Swedish Foundation for Strategic Research and Knut and Alice Wallenberg Foundation.
This publication acknowledges KAUST support, but has no KAUST affiliated authors.

Fingerprint

Dive into the research topics of 'Physics-informed Learning for Identification and State Reconstruction of Traffic Density'. Together they form a unique fingerprint.

Cite this