A recurrent neural network model for predicting two-leader car-following behavior

Unlike lane-based traffic where each driver has a distinct leader, the subject driver in disorderly traffic may interact with multiple vehicles in-front. The existence of lateral interactions among the vehicles in-front adds even more complexity to modeling the human-driving process. Utilizing traje...

Full description

Saved in:
Bibliographic Details
Published inTransportation letters Vol. ahead-of-print; no. ahead-of-print; pp. 1 - 15
Main Authors Das, Sanhita, Maurya, Akhilesh Kumar, Dey, Arka
Format Journal Article
LanguageEnglish
Published Taylor & Francis 27.05.2024
Subjects
Online AccessGet full text
ISSN1942-7867
1942-7875
DOI10.1080/19427867.2023.2205190

Cover

Abstract Unlike lane-based traffic where each driver has a distinct leader, the subject driver in disorderly traffic may interact with multiple vehicles in-front. The existence of lateral interactions among the vehicles in-front adds even more complexity to modeling the human-driving process. Utilizing trajectory data extracted from an instrumented vehicle study, this research attempts to propose a gated recurrent unit neural network model to predict responses of vehicles interacting with two leading vehicles simultaneously. The recurrent neural network model can illustrate realistic human-like following behavior of drivers, much better than the classical optimal velocity-based models in terms of trajectory reproducing accuracy. The model can also explain the closing-in, shying-away behavior and local stability properties. Results of the study provide insights into the driving behavioral phenomena of disorderly traffic flows and can contribute to the development of a realistic microsimulation model, smarter autonomous systems, and in-traffic safety evaluation as well.
AbstractList Unlike lane-based traffic where each driver has a distinct leader, the subject driver in disorderly traffic may interact with multiple vehicles in-front. The existence of lateral interactions among the vehicles in-front adds even more complexity to modeling the human-driving process. Utilizing trajectory data extracted from an instrumented vehicle study, this research attempts to propose a gated recurrent unit neural network model to predict responses of vehicles interacting with two leading vehicles simultaneously. The recurrent neural network model can illustrate realistic human-like following behavior of drivers, much better than the classical optimal velocity-based models in terms of trajectory reproducing accuracy. The model can also explain the closing-in, shying-away behavior and local stability properties. Results of the study provide insights into the driving behavioral phenomena of disorderly traffic flows and can contribute to the development of a realistic microsimulation model, smarter autonomous systems, and in-traffic safety evaluation as well.
Author Das, Sanhita
Maurya, Akhilesh Kumar
Dey, Arka
Author_xml – sequence: 1
  givenname: Sanhita
  orcidid: 0000-0002-1199-6398
  surname: Das
  fullname: Das, Sanhita
  email: sanhita.das@ce.iitr.ac.in
  organization: Indian Institute of Technology Roorkee
– sequence: 2
  givenname: Akhilesh Kumar
  surname: Maurya
  fullname: Maurya, Akhilesh Kumar
  organization: Indian Institute of Technology Guwahati
– sequence: 3
  givenname: Arka
  surname: Dey
  fullname: Dey, Arka
  organization: Indian Institute of Technology Roorkee
BookMark eNqFkM1KAzEUhYNUsK0-gjAvMDXJTH6KG0vxDwoi6DpkMolG06TcSS19e2eounChq3O5h-8svgkaxRQtQucEzwiW-ILMayokFzOKaTWjFDMyx0doPPxLIQUb_dxcnKBJ171hzLnEZIweFwVYswWwMRfRbkGHPvIuwXuxTq0NhUtQbMC23mQfX4q-KoPVrYXCaChdCiHthqKxr_rDJzhFx06Hzp595RQ931w_Le_K1cPt_XKxKk1FcC4JqzFtKHW8aWre1vW8YlgSQanVtKn0HLfWGsOdc7RhTBimpdYtlVZwWRFXTRE77BpIXQfWqQ34tYa9IlgNXtS3FzV4UV9eeu7yF2d81tmnmEH78C99daB97MWsdS8qtCrrfUjgQEfjO1X9PfEJSvR-_w
CitedBy_id crossref_primary_10_3390_electronics13061133
crossref_primary_10_1016_j_energy_2024_131333
crossref_primary_10_2478_amns_2024_1672
crossref_primary_10_1080_23307706_2024_2349632
crossref_primary_10_1680_jtran_23_00112
Cites_doi 10.1016/j.trc.2018.07.022
10.1016/j.envsoft.2015.01.004
10.1109/TITS.2006.874716
10.1016/j.physa.2010.06.014
10.1016/j.trc.2018.10.024
10.1016/j.trb.2016.04.012
10.1016/j.simpat.2004.04.002
10.1016/j.trb.2018.12.016
10.1080/15472450.2013.801717
10.1016/j.trc.2020.102785
10.1016/j.trc.2013.09.010
10.1109/TITS.2017.2706963
10.1007/s11071-014-1863-6
10.1117/1.1606458
10.1007/s40890-017-0049-6
10.1080/10447318.2015.1070547
10.3141/1857-04
10.1016/j.trc.2016.02.010
10.1016/j.trf.2008.09.003
10.1080/21680566.2015.1055618
10.1016/0004-3702(92)90065-6
10.1016/j.trc.2019.05.021
10.1109/CAC.2018.8623166
10.1287/opre.9.2.209
10.1016/j.trc.2017.08.027
10.1016/0191-2615(95)00009-3
10.1016/j.jesp.2014.01.005
10.1016/j.trc.2021.103144
10.1109/TITS.2006.884616
10.1109/TSMCA.2012.2192262
10.1155/2020/4752651
10.1103/PhysRevE.51.1035
10.1007/s40890-019-0085-5
10.1016/S0377-2217(00)00123-5
10.1007/s11071-016-2803-4
10.1016/S0968-090X(99)00020-0
10.1103/PhysRevE.64.017101
10.1177/1094428103251907
10.1016/S0378-4371(02)01802-2
ContentType Journal Article
Copyright 2023 Informa UK Limited, trading as Taylor & Francis Group 2023
Copyright_xml – notice: 2023 Informa UK Limited, trading as Taylor & Francis Group 2023
DBID AAYXX
CITATION
DOI 10.1080/19427867.2023.2205190
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Economics
EISSN 1942-7875
EndPage 15
ExternalDocumentID 10_1080_19427867_2023_2205190
2205190
Genre Research Article
GroupedDBID 002
0BK
0R~
30N
4.4
AAGDL
AAHIA
AAJMT
AALDU
AAMIU
AAPUL
AAQRR
ABCCY
ABFIM
ABLIJ
ABPAQ
ABPEM
ABXUL
ABXYU
ACGFS
ACTIO
ADCVX
ADGTB
ADMLS
AEISY
AFRVT
AGDLA
AIJEM
AIYEW
AKBVH
AKOOK
ALMA_UNASSIGNED_HOLDINGS
ALQZU
AQRUH
AQTUD
AWYRJ
BLEHA
CCCUG
DGEBU
DKSSO
E01
EBS
H13
HCLVR
HZ~
IPNFZ
KYCEM
LJTGL
M4Z
P75
P7B
RIG
RNANH
ROSJB
RTWRZ
TASJS
TBQAZ
TDBHL
TEN
TFL
TFT
TFW
TTHFI
TUROJ
ZGOLN
AAYXX
CITATION
ID FETCH-LOGICAL-c310t-15402b22f6bb46d44935081722ea2b3a90deecc6fff2b557c5a8aad28e76831f3
ISSN 1942-7867
IngestDate Thu Oct 30 03:45:05 EDT 2025
Thu Apr 24 23:01:15 EDT 2025
Mon Oct 20 23:46:15 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue ahead-of-print
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c310t-15402b22f6bb46d44935081722ea2b3a90deecc6fff2b557c5a8aad28e76831f3
ORCID 0000-0002-1199-6398
PageCount 15
ParticipantIDs informaworld_taylorfrancis_310_1080_19427867_2023_2205190
crossref_citationtrail_10_1080_19427867_2023_2205190
crossref_primary_10_1080_19427867_2023_2205190
PublicationCentury 2000
PublicationDate 2024-05-27
PublicationDateYYYYMMDD 2024-05-27
PublicationDate_xml – month: 05
  year: 2024
  text: 2024-05-27
  day: 27
PublicationDecade 2020
PublicationTitle Transportation letters
PublicationYear 2024
Publisher Taylor & Francis
Publisher_xml – name: Taylor & Francis
References e_1_3_2_28_1
e_1_3_2_49_1
Mathew T. V. (e_1_3_2_31_1) 2012; 52
e_1_3_2_20_1
e_1_3_2_22_1
e_1_3_2_43_1
e_1_3_2_26_1
e_1_3_2_47_1
Lipton Z. C. (e_1_3_2_27_1) 2015
Hongfei J. (e_1_3_2_18_1) 2003; 1
e_1_3_2_16_1
e_1_3_2_7_1
e_1_3_2_54_1
e_1_3_2_33_1
e_1_3_2_52_1
Wasserman P. D. (e_1_3_2_45_1) 1989
e_1_3_2_12_1
e_1_3_2_35_1
e_1_3_2_5_1
e_1_3_2_14_1
e_1_3_2_37_1
Zhang X. (e_1_3_2_48_1) 2007
e_1_3_2_3_1
e_1_3_2_50_1
Ciuffo B. (e_1_3_2_10_1) 2010
e_1_3_2_29_1
e_1_3_2_42_1
e_1_3_2_21_1
e_1_3_2_44_1
e_1_3_2_23_1
e_1_3_2_46_1
e_1_3_2_25_1
e_1_3_2_40_1
Cho H. J. (e_1_3_2_9_1) 2004; 7
e_1_3_2_8_1
e_1_3_2_19_1
e_1_3_2_30_1
Sayer J. R. (e_1_3_2_39_1) 2003
Reiter U. (e_1_3_2_38_1) 1994; 2
e_1_3_2_11_1
e_1_3_2_32_1
e_1_3_2_53_1
e_1_3_2_6_1
e_1_3_2_13_1
e_1_3_2_34_1
e_1_3_2_4_1
e_1_3_2_36_1
Karlik B. (e_1_3_2_24_1) 2011; 1
Fausett L. (e_1_3_2_15_1) 1994
e_1_3_2_51_1
References_xml – volume: 7
  start-page: 6262
  volume-title: International Conference on Systems, Man and Cybernetics, IEEE
  year: 2004
  ident: e_1_3_2_9_1
– ident: e_1_3_2_19_1
  doi: 10.1016/j.trc.2018.07.022
– ident: e_1_3_2_36_1
  doi: 10.1016/j.envsoft.2015.01.004
– ident: e_1_3_2_42_1
  doi: 10.1109/TITS.2006.874716
– volume-title: Fundamentals of Neural Networks
  year: 1994
  ident: e_1_3_2_15_1
– ident: e_1_3_2_22_1
  doi: 10.1016/j.physa.2010.06.014
– start-page: 574
  volume-title: Proceedings of the 18th IASTED international conference
  year: 2007
  ident: e_1_3_2_48_1
– ident: e_1_3_2_54_1
  doi: 10.1016/j.trc.2018.10.024
– ident: e_1_3_2_37_1
  doi: 10.1016/j.trb.2016.04.012
– ident: e_1_3_2_23_1
  doi: 10.1016/j.simpat.2004.04.002
– ident: e_1_3_2_40_1
  doi: 10.1016/j.trb.2018.12.016
– ident: e_1_3_2_11_1
  doi: 10.1080/15472450.2013.801717
– ident: e_1_3_2_30_1
  doi: 10.1016/j.trc.2020.102785
– volume-title: Proceedings of the 2nd international driving symposium on human factors in driver assessment, training and vehicle design
  year: 2003
  ident: e_1_3_2_39_1
– ident: e_1_3_2_51_1
  doi: 10.1016/j.trc.2013.09.010
– volume-title: Neural Computing: Theory and Practice
  year: 1989
  ident: e_1_3_2_45_1
– volume: 52
  start-page: 1
  year: 2012
  ident: e_1_3_2_31_1
  article-title: Neural Network Based Vehicle-Following Model for Mixed Traffic Conditions
  publication-title: European Transport
– ident: e_1_3_2_44_1
  doi: 10.1109/TITS.2017.2706963
– ident: e_1_3_2_28_1
  doi: 10.1007/s11071-014-1863-6
– ident: e_1_3_2_16_1
  doi: 10.1117/1.1606458
– ident: e_1_3_2_6_1
  doi: 10.1007/s40890-017-0049-6
– ident: e_1_3_2_26_1
  doi: 10.1080/10447318.2015.1070547
– ident: e_1_3_2_43_1
  doi: 10.3141/1857-04
– ident: e_1_3_2_8_1
  doi: 10.1016/j.trc.2016.02.010
– ident: e_1_3_2_5_1
  doi: 10.1016/j.trf.2008.09.003
– ident: e_1_3_2_50_1
  doi: 10.1080/21680566.2015.1055618
– ident: e_1_3_2_32_1
  doi: 10.1016/0004-3702(92)90065-6
– ident: e_1_3_2_49_1
  doi: 10.1016/j.trc.2019.05.021
– ident: e_1_3_2_47_1
  doi: 10.1109/CAC.2018.8623166
– ident: e_1_3_2_33_1
  doi: 10.1287/opre.9.2.209
– ident: e_1_3_2_53_1
  doi: 10.1016/j.trc.2017.08.027
– ident: e_1_3_2_13_1
  doi: 10.1016/0191-2615(95)00009-3
– year: 2015
  ident: e_1_3_2_27_1
  article-title: A Critical Review of Recurrent Neural Networks for Sequence Learning
  publication-title: ArXiv Preprint
– volume: 2
  start-page: 493
  volume-title: Proc. of the Second International Symposium on Highway Capacity
  year: 1994
  ident: e_1_3_2_38_1
– ident: e_1_3_2_46_1
  doi: 10.1016/j.jesp.2014.01.005
– ident: e_1_3_2_34_1
  doi: 10.1016/j.trc.2021.103144
– ident: e_1_3_2_35_1
  doi: 10.1109/TITS.2006.884616
– ident: e_1_3_2_25_1
  doi: 10.1109/TSMCA.2012.2192262
– ident: e_1_3_2_52_1
  doi: 10.1155/2020/4752651
– ident: e_1_3_2_3_1
  doi: 10.1103/PhysRevE.51.1035
– ident: e_1_3_2_12_1
  doi: 10.1007/s40890-019-0085-5
– ident: e_1_3_2_4_1
  doi: 10.1016/S0377-2217(00)00123-5
– ident: e_1_3_2_29_1
  doi: 10.1007/s11071-016-2803-4
– volume-title: 89th Annual Meeting of the Transportation Research Record
  year: 2010
  ident: e_1_3_2_10_1
– volume: 1
  start-page: 346
  volume-title: system”.Proceedings of the International Conference on Intelligent Transportation Systems
  year: 2003
  ident: e_1_3_2_18_1
– ident: e_1_3_2_7_1
  doi: 10.1016/S0968-090X(99)00020-0
– ident: e_1_3_2_21_1
  doi: 10.1103/PhysRevE.64.017101
– ident: e_1_3_2_14_1
  doi: 10.1177/1094428103251907
– volume: 1
  start-page: 111
  issue: 4
  year: 2011
  ident: e_1_3_2_24_1
  article-title: Performance Analysis of Various Activation Functions in Generalized MLP Architectures of Neural Networks
  publication-title: International Journal of Artificial Intelligence and Expert Systems
– ident: e_1_3_2_20_1
  doi: 10.1016/S0378-4371(02)01802-2
SSID ssj0066801
Score 2.3292198
Snippet Unlike lane-based traffic where each driver has a distinct leader, the subject driver in disorderly traffic may interact with multiple vehicles in-front. The...
SourceID crossref
informaworld
SourceType Enrichment Source
Index Database
Publisher
StartPage 1
SubjectTerms Car-following
disordered traffic
mixed traffic
neural network
two-leader
Title A recurrent neural network model for predicting two-leader car-following behavior
URI https://www.tandfonline.com/doi/abs/10.1080/19427867.2023.2205190
Volume ahead-of-print
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVEBS
  databaseName: Inspec with Full Text
  customDbUrl:
  eissn: 1942-7875
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0066801
  issn: 1942-7867
  databaseCode: ADMLS
  dateStart: 20120401
  isFulltext: true
  titleUrlDefault: https://www.ebsco.com/products/research-databases/inspec-full-text
  providerName: EBSCOhost
– providerCode: PRVAWR
  databaseName: Taylor & Francis Science and Technology Library-DRAA
  customDbUrl:
  eissn: 1942-7875
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0066801
  issn: 1942-7867
  databaseCode: 30N
  dateStart: 20090101
  isFulltext: true
  titleUrlDefault: http://www.tandfonline.com/page/title-lists
  providerName: Taylor & Francis
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3da9swEBdr9rC-lHYfLP1CD3sr9mxZlu3HUFrKIIFBA3kzli2R0uCUxCXQv74nna04W-navZjgoHOi--l0Ot_dj5AftsGIgkOOLNPK45UovSytMk-KBJZ5kkpmQxfjibiZ8l-zeLaNKtnqkkb65dOLdSX_o1W4B3o1VbLv0KwTCjfgM-gXrqBhuL5Jx6OLlQmX2wZLpjElTHeNad3IcGNzCB9W5l0M8kFslt7C5i6bjtSeBgwsN-aLrli_76q6tucIkYWt--nR0K8xoFzP7xpn2scFqAgjtfdzsDfr-YXN4XajMEA-Wt0X_XAD4-ZNOVbvtxYy4-CSp8ih4av-PaRAcWZV9OAT92wkx-7r7XbLcdRflhxTH41k8zDfsLz7pig4RHbR3c7Zf-xoLs8wbBugdmJyIyZvxeyRjwy2AsP3EQWTbvsWIrWc2e5_dmVfafDzxV-z49DstLvtOSq3h-SgPWHQEcLliHxQ9WfyqStAX38hv0fUwYYibGgLG2phQ0E43cKGbmFDd2BDO9h8JdPrq9vLG69l1vBKcOcbD_zmgEnGtJCSi4rzLAJHHXxZpgomoyILKgVrW2itmYzjpIyLtCgqlio4nUahjr6RQb2s1XdCweU0qXKMRyLgYVLKkCkZJBVTVSSV1kPCu-nJy7btvGE_WeSvKmdIfDfsAfuu_GtA1p_7vLEBL43sNHn06tjj9z7shOxv18YpGTSrR3UGzmkjzy2YngG-vIWU
linkProvider Taylor & Francis
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV07T8MwELagDGXhjShPD6wOieM4yVghqgJtJaRW6hbFjr2A2iqkQuLXc5cHapGAobNzUWyf7e-c774j5LYUGDEQ5CgdZUxkUrM4ymKmZAjLPIwUL68uhiPZn4inaTBdyYVBWiXG0LYSiij3alzceBndUOLuIPDmYSRDB2t_O5gqCsfaNtkJAOxjFQPfHTW7sZRRWQIZTRjaNFk8v71m7XxaUy9dOXd6-0Q3X1zRTV6dZaEc_flDzHGzLh2QvRqW0m7lR4dky8yOSLvJWn4_Ji9dmuPVPIo5URTBhKdnFYWcltV0KHSBLnL874NMagpN7K3kSVOd5syCv80_sKERBjghk97D-L7P6nIMTAMGLBiALZcrzq1USshMiNgHdAcAiJuUKz-N3cyAQ0hrLVdBEOogjdI045GBkMb3rH9KWrP5zJwRCjgF-VVc-NIVXqiVx41yw4ybzFfG2g4RzSQkutYqx5IZb4lXS5o245XgeCX1eHWI8222qMQ6_jOIV2c4KcpbEluVNEn8P23PN7C9Ie3-eDhIBo-j5wuyC00CGQk8vCStIl-aKwA6hbouPfkLsOfuYQ
linkToPdf http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV07T8MwELagSMDCG1GeHlgdUsd1krECqvKqQKISWxTH9kLVVmkqJH49d0mMWiRg6OxclNhn-zv7u-8IuSwFRgwEOSqLNBNaZiyOdMyUDGGah5Hi5dHFU1_2BuL-re3YhNOaVokxtK2EIsq1Gif3RFvHiLuCuJuHkQw9LP3tYaYo7GqrZE3irRhmcfh9txhLGZUVkNGEoY1L4vntNQvb04J46dy2090myn1wxTZ592aF8rLPH1qOS_3RDtmqQSntVF60S1bMaI9suJzl6T556dAcD-ZRyomiBCY8PaoI5LSspUPhD-gkx1sf5FFTaGLDkiVNszRnFrxt_IENThbggAy6t6_XPVYXY2AZIMCCAdTyueLcSqWE1ELEAWA7gD_cpFwFaexrA-4grbVctdth1k6jNNU8MhDQBC0bHJLGaDwyR4QCSkF2FReB9EUrzFSLG-WHmhsdKGNtkwg3BklWK5VjwYxh0qoFTV1_JdhfSd1fTeJ9m00qqY7_DOL5AU6K8ozEVgVNkuBP2-MlbC_I-vNNN3m86z-ckE1oEUhH4OEpaRT5zJwByinUeenHX8Lc7QU
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+recurrent+neural+network+model+for+predicting+two-leader+car-following+behavior&rft.jtitle=Transportation+letters&rft.au=Das%2C+Sanhita&rft.au=Maurya%2C+Akhilesh+Kumar&rft.au=Dey%2C+Arka&rft.date=2024-05-27&rft.issn=1942-7867&rft.eissn=1942-7875&rft.volume=16&rft.issue=5&rft.spage=461&rft.epage=475&rft_id=info:doi/10.1080%2F19427867.2023.2205190&rft.externalDBID=n%2Fa&rft.externalDocID=10_1080_19427867_2023_2205190
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1942-7867&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1942-7867&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1942-7867&client=summon