Learning-based Traffic State Reconstruction using Probe Vehicles

John Liu; Matthieu Barreau; Mladen Čičić; Karl H. Johansson

doi:10.1016/j.ifacol.2021.06.013

Learning-based Traffic State Reconstruction using Probe Vehicles

John Liu, Matthieu Barreau, Mladen Čičić, Karl H. Johansson

Research output: Contribution to journal › Article › peer-review

9 Scopus citations

Abstract

This article investigates the use of a model-based neural network for the traffic reconstruction problem using noisy measurements coming from Probe Vehicles (PV). The traffic state is assumed to be the density only, modeled by a partial differential equation. There exist various methods for reconstructing the density in that case. However, none of them perform well with noise and very few deal with lagrangian measurements. This paper introduces a method that can reduce the processes of identification, reconstruction, prediction, and noise rejection into a single optimization problem. Numerical simulations, based either on a macroscopic or a microscopic model, show good performance for a moderate computational burden.

Original language	English (US)
Pages (from-to)	87-92
Number of pages	6
Journal	IFAC-PapersOnLine
Volume	54
Issue number	2
DOIs	https://doi.org/10.1016/j.ifacol.2021.06.013
State	Published - 2021
Externally published	Yes

Bibliographical note

KAUST Repository Item: Exported on 2021-08-25
Acknowledged KAUST grant number(s): CRG, OSR
Acknowledgements: This research is partially funded by the KAUST Office of Sponsored Research under Award No. OSR-20f 9-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.

Access to Document

10.1016/j.ifacol.2021.06.013

https://repository.kaust.edu.sa/bitstream/10754/666000/1/Preprintfile1.pdf

Cite this

@article{cabb1db098ae4f87b56192310e6e18fb,

title = "Learning-based Traffic State Reconstruction using Probe Vehicles",

abstract = "This article investigates the use of a model-based neural network for the traffic reconstruction problem using noisy measurements coming from Probe Vehicles (PV). The traffic state is assumed to be the density only, modeled by a partial differential equation. There exist various methods for reconstructing the density in that case. However, none of them perform well with noise and very few deal with lagrangian measurements. This paper introduces a method that can reduce the processes of identification, reconstruction, prediction, and noise rejection into a single optimization problem. Numerical simulations, based either on a macroscopic or a microscopic model, show good performance for a moderate computational burden.",

author = "John Liu and Matthieu Barreau and Mladen {\v C}i{\v c}i{\'c} and Johansson, {Karl H.}",

note = "KAUST Repository Item: Exported on 2021-08-25 Acknowledged KAUST grant number(s): CRG, OSR Acknowledgements: This research is partially funded by the KAUST Office of Sponsored Research under Award No. OSR-20f 9-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.",

year = "2021",

doi = "10.1016/j.ifacol.2021.06.013",

language = "English (US)",

volume = "54",

pages = "87--92",

journal = "IFAC-PapersOnLine",

issn = "2405-8963",

publisher = "Elsevier",

number = "2",

}

TY - JOUR

T1 - Learning-based Traffic State Reconstruction using Probe Vehicles

AU - Liu, John

AU - Barreau, Matthieu

AU - Čičić, Mladen

AU - Johansson, Karl H.

N1 - KAUST Repository Item: Exported on 2021-08-25 Acknowledged KAUST grant number(s): CRG, OSR Acknowledgements: This research is partially funded by the KAUST Office of Sponsored Research under Award No. OSR-20f 9-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.

PY - 2021

Y1 - 2021

N2 - This article investigates the use of a model-based neural network for the traffic reconstruction problem using noisy measurements coming from Probe Vehicles (PV). The traffic state is assumed to be the density only, modeled by a partial differential equation. There exist various methods for reconstructing the density in that case. However, none of them perform well with noise and very few deal with lagrangian measurements. This paper introduces a method that can reduce the processes of identification, reconstruction, prediction, and noise rejection into a single optimization problem. Numerical simulations, based either on a macroscopic or a microscopic model, show good performance for a moderate computational burden.

AB - This article investigates the use of a model-based neural network for the traffic reconstruction problem using noisy measurements coming from Probe Vehicles (PV). The traffic state is assumed to be the density only, modeled by a partial differential equation. There exist various methods for reconstructing the density in that case. However, none of them perform well with noise and very few deal with lagrangian measurements. This paper introduces a method that can reduce the processes of identification, reconstruction, prediction, and noise rejection into a single optimization problem. Numerical simulations, based either on a macroscopic or a microscopic model, show good performance for a moderate computational burden.

UR - http://hdl.handle.net/10754/666000

UR - https://linkinghub.elsevier.com/retrieve/pii/S2405896321004420

UR - http://www.scopus.com/inward/record.url?scp=85104198317&partnerID=8YFLogxK

U2 - 10.1016/j.ifacol.2021.06.013

DO - 10.1016/j.ifacol.2021.06.013

M3 - Article

SN - 2405-8963

VL - 54

SP - 87

EP - 92

JO - IFAC-PapersOnLine

JF - IFAC-PapersOnLine

IS - 2

ER -

Learning-based Traffic State Reconstruction using Probe Vehicles

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this