When security games hit traffic: A deployed optimal traffic enforcement system

Ariel Rosenfeld; Oleg Maksimov; Sarit Kraus

doi:10.1016/j.artint.2020.103381

When security games hit traffic: A deployed optimal traffic enforcement system

Ariel Rosenfeld, Oleg Maksimov, Sarit Kraus

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

1 Scopus citations

Abstract

Road accidents are the leading causes of death among youths and young adults worldwide. Efficient traffic enforcement is an essential, yet complex, component in preventing road accidents. In this article, we present a novel model, an optimizing algorithm and a deployed system which together mitigate many of the computational and real-world challenges of traffic enforcement allocation in large road networks. Our approach allows for scalable, coupled and non-Markovian optimization of multiple police units and guarantees optimality. Our deployed system, which utilizes the proposed approach, is used by the Israeli traffic police and is shown to provide meaningful benefits compared to existing standard traffic police enforcement practices.

Original language	English
Article number	103381
Journal	Artificial Intelligence
Volume	289
DOIs	https://doi.org/10.1016/j.artint.2020.103381
State	Published - Dec 2020

Bibliographical note

Funding Information:
This work was supported in part by the LAW-TRAIN project which received funding from the European Union Horizon 2020 research and innovation program under grant agreement 653587 and in part by a grant from the Ministry of Science & Technology, Israel & the Japan Science and Technology Agency (JST), Japan.

Publisher Copyright:
© 2020 Elsevier B.V.

Keywords

Deployed system
Security
Traffic enforcement

Access to Document

10.1016/j.artint.2020.103381

Cite this

@article{f81d1286edd34605930a612eb5e576fb,

title = "When security games hit traffic: A deployed optimal traffic enforcement system",

abstract = "Road accidents are the leading causes of death among youths and young adults worldwide. Efficient traffic enforcement is an essential, yet complex, component in preventing road accidents. In this article, we present a novel model, an optimizing algorithm and a deployed system which together mitigate many of the computational and real-world challenges of traffic enforcement allocation in large road networks. Our approach allows for scalable, coupled and non-Markovian optimization of multiple police units and guarantees optimality. Our deployed system, which utilizes the proposed approach, is used by the Israeli traffic police and is shown to provide meaningful benefits compared to existing standard traffic police enforcement practices.",

keywords = "Deployed system, Security, Traffic enforcement",

author = "Ariel Rosenfeld and Oleg Maksimov and Sarit Kraus",

note = "Publisher Copyright: {\textcopyright} 2020 Elsevier B.V.",

year = "2020",

month = dec,

doi = "10.1016/j.artint.2020.103381",

language = "אנגלית",

volume = "289",

journal = "Artificial Intelligence",

issn = "0004-3702",

publisher = "Elsevier",

}

TY - JOUR

T1 - When security games hit traffic

T2 - A deployed optimal traffic enforcement system

AU - Rosenfeld, Ariel

AU - Maksimov, Oleg

AU - Kraus, Sarit

PY - 2020/12

Y1 - 2020/12

N2 - Road accidents are the leading causes of death among youths and young adults worldwide. Efficient traffic enforcement is an essential, yet complex, component in preventing road accidents. In this article, we present a novel model, an optimizing algorithm and a deployed system which together mitigate many of the computational and real-world challenges of traffic enforcement allocation in large road networks. Our approach allows for scalable, coupled and non-Markovian optimization of multiple police units and guarantees optimality. Our deployed system, which utilizes the proposed approach, is used by the Israeli traffic police and is shown to provide meaningful benefits compared to existing standard traffic police enforcement practices.

AB - Road accidents are the leading causes of death among youths and young adults worldwide. Efficient traffic enforcement is an essential, yet complex, component in preventing road accidents. In this article, we present a novel model, an optimizing algorithm and a deployed system which together mitigate many of the computational and real-world challenges of traffic enforcement allocation in large road networks. Our approach allows for scalable, coupled and non-Markovian optimization of multiple police units and guarantees optimality. Our deployed system, which utilizes the proposed approach, is used by the Israeli traffic police and is shown to provide meaningful benefits compared to existing standard traffic police enforcement practices.

KW - Deployed system

KW - Security

KW - Traffic enforcement

UR - http://www.scopus.com/inward/record.url?scp=85090227385&partnerID=8YFLogxK

U2 - 10.1016/j.artint.2020.103381

DO - 10.1016/j.artint.2020.103381

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:85090227385

SN - 0004-3702

VL - 289

JO - Artificial Intelligence

JF - Artificial Intelligence

M1 - 103381

ER -

When security games hit traffic: A deployed optimal traffic enforcement system

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this