MOHA: A Multi-Mode Hybrid Automaton Model for Learning Car-Following Behaviors

Qin Lin; Yihuan Zhang; Sicco Verwer; Jun Wang

doi:10.1109/TITS.2018.2823418

MOHA: A Multi-Mode Hybrid Automaton Model for Learning Car-Following Behaviors

Qin Lin, Yihuan Zhang, Sicco Verwer, Jun Wang

Cyber Security

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

25 Citations (Scopus)

355 Downloads (Pure)

Abstract

This paper proposes a novel hybrid model for learning discrete and continuous dynamics of car-following behaviors. Multiple modes representing driving patterns are identified by partitioning the model into groups of states. The model is visualizable and interpretable for car-following behavior recognition, traffic simulation, and human-like cruise control. The experimental results using the next generation simulation datasets demonstrate its superior fitting accuracy over conventional models.

Original language	English
Pages (from-to)	790-796
Number of pages	7
Journal	IEEE Transactions on Intelligent Transportation Systems
Volume	20
Issue number	2
DOIs	https://doi.org/10.1109/TITS.2018.2823418
Publication status	Published - 2019

Bibliographical note

Accepted author manuscript

Keywords

car-following behavior
Computational modeling
Data mining
Data models
Hybrid automaton
Learning automata
Numerical models
simulation and control.
Time series analysis
Vehicles

Access to Document

10.1109/TITS.2018.2823418

45517217 - 08384014Accepted author manuscript, 2.63 MB

Cite this

@article{dc18fedd0b164d10ab7906f977756d02,

title = "MOHA: A Multi-Mode Hybrid Automaton Model for Learning Car-Following Behaviors",

abstract = "This paper proposes a novel hybrid model for learning discrete and continuous dynamics of car-following behaviors. Multiple modes representing driving patterns are identified by partitioning the model into groups of states. The model is visualizable and interpretable for car-following behavior recognition, traffic simulation, and human-like cruise control. The experimental results using the next generation simulation datasets demonstrate its superior fitting accuracy over conventional models.",

keywords = "car-following behavior, Computational modeling, Data mining, Data models, Hybrid automaton, Learning automata, Numerical models, simulation and control., Time series analysis, Vehicles",

author = "Qin Lin and Yihuan Zhang and Sicco Verwer and Jun Wang",

note = "Accepted author manuscript",

year = "2019",

doi = "10.1109/TITS.2018.2823418",

language = "English",

volume = "20",

pages = "790--796",

journal = "IEEE Transactions on Intelligent Transportation Systems",

issn = "1524-9050",

publisher = "IEEE",

number = "2",

}

TY - JOUR

T1 - MOHA

T2 - A Multi-Mode Hybrid Automaton Model for Learning Car-Following Behaviors

AU - Lin, Qin

AU - Zhang, Yihuan

AU - Verwer, Sicco

AU - Wang, Jun

N1 - Accepted author manuscript

PY - 2019

Y1 - 2019

N2 - This paper proposes a novel hybrid model for learning discrete and continuous dynamics of car-following behaviors. Multiple modes representing driving patterns are identified by partitioning the model into groups of states. The model is visualizable and interpretable for car-following behavior recognition, traffic simulation, and human-like cruise control. The experimental results using the next generation simulation datasets demonstrate its superior fitting accuracy over conventional models.

AB - This paper proposes a novel hybrid model for learning discrete and continuous dynamics of car-following behaviors. Multiple modes representing driving patterns are identified by partitioning the model into groups of states. The model is visualizable and interpretable for car-following behavior recognition, traffic simulation, and human-like cruise control. The experimental results using the next generation simulation datasets demonstrate its superior fitting accuracy over conventional models.

KW - car-following behavior

KW - Computational modeling

KW - Data mining

KW - Data models

KW - Hybrid automaton

KW - Learning automata

KW - Numerical models

KW - simulation and control.

KW - Time series analysis

KW - Vehicles

UR - http://www.scopus.com/inward/record.url?scp=85048553144&partnerID=8YFLogxK

U2 - 10.1109/TITS.2018.2823418

DO - 10.1109/TITS.2018.2823418

M3 - Article

AN - SCOPUS:85048553144

SN - 1524-9050

VL - 20

SP - 790

EP - 796

JO - IEEE Transactions on Intelligent Transportation Systems

JF - IEEE Transactions on Intelligent Transportation Systems

IS - 2

ER -

MOHA: A Multi-Mode Hybrid Automaton Model for Learning Car-Following Behaviors

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this