Risk-based autonomous vehicle motion control with considering human driver’s behaviour

Chongfeng Wei, Richard Romano, Natasha Merat, Yafei Wang, Chuan Hu, Hamid Taghavifar, Foroogh Hajiseyedjavadi, Erwin R. Boer

Research output: Contribution to journalArticle

Abstract

The selected motions of autonomous vehicles (AVs) are subject to the constraints from the surrounding traffic environment, infrastructure and the vehicle’s dynamic capabilities. Normally, the motion control of the vehicle is composed of trajectory planning and trajectory following according to the surrounding risk factors, the vehicles’ capabilities as well as tyre/road interaction situations. However, pure trajectory following with a unique path may make the motion control of the vehicle be too careful and cautious with a large amount of steering effort. To follow a planned trajectory, the AVs with the traditional path-following control algorithms will correct their states even if the vehicles have only a slight deviation from the desired path or the vehicle detects static infrastructure like roadside trees. In this case, the safety of the AVs can be guaranteed to some degree, but the comfort and sense of hazards for the drivers are ignored, and sometimes the AVs have unusual motion behaviours which may not be acceptable to other road users. To solve this problem, this study aims to develop a safety corridor-based vehicle motion control approach by investigating human-driven vehicle behaviour and the vehicle’s dynamic capabilities. The safety corridor is derived by the manoeuvring action feedback of actual drivers as collected in a driving simulator when presented with surrounding risk elements and enables the AVs to have safe trajectories within it. A corridor-based Nonlinear Model Predictive Control (NMPC) has been developed which controls the vehicle state to achieve a smooth and comfortable trajectory while applying trajectory constraints using the safety corridor. The safety corridor and motion controller are assessed using four typical scenarios to show that the vehicle has a human-like or human-oriented behaviour which is expected to be more acceptable for both drivers and other road users.

Original languageEnglish
Pages (from-to)1-14
Number of pages14
JournalTransportation Research Part C: Emerging Technologies
Volume107
Early online date13 Aug 2019
DOIs
Publication statusPublished - Oct 2019
Externally publishedYes

Fingerprint

Motion control
driver
road user
Trajectories
infrastructure
non-linear model
road
traffic
scenario
planning
interaction
Roadsides
Model predictive control
Tires

Keywords

  • Autonomous vehicles
  • Human-like
  • Model predictive control
  • Risk-based corridor
  • Trajectory

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Automotive Engineering
  • Transportation
  • Computer Science Applications

Cite this

Risk-based autonomous vehicle motion control with considering human driver’s behaviour. / Wei, Chongfeng ; Romano, Richard ; Merat, Natasha ; Wang, Yafei ; Hu, Chuan; Taghavifar, Hamid; Hajiseyedjavadi, Foroogh ; Boer, Erwin R.

In: Transportation Research Part C: Emerging Technologies, Vol. 107, 10.2019, p. 1-14.

Research output: Contribution to journalArticle

Wei, Chongfeng ; Romano, Richard ; Merat, Natasha ; Wang, Yafei ; Hu, Chuan ; Taghavifar, Hamid ; Hajiseyedjavadi, Foroogh ; Boer, Erwin R. / Risk-based autonomous vehicle motion control with considering human driver’s behaviour. In: Transportation Research Part C: Emerging Technologies. 2019 ; Vol. 107. pp. 1-14.
@article{86af207710f74cd98cd0384dc22e9008,
title = "Risk-based autonomous vehicle motion control with considering human driver’s behaviour",
abstract = "The selected motions of autonomous vehicles (AVs) are subject to the constraints from the surrounding traffic environment, infrastructure and the vehicle’s dynamic capabilities. Normally, the motion control of the vehicle is composed of trajectory planning and trajectory following according to the surrounding risk factors, the vehicles’ capabilities as well as tyre/road interaction situations. However, pure trajectory following with a unique path may make the motion control of the vehicle be too careful and cautious with a large amount of steering effort. To follow a planned trajectory, the AVs with the traditional path-following control algorithms will correct their states even if the vehicles have only a slight deviation from the desired path or the vehicle detects static infrastructure like roadside trees. In this case, the safety of the AVs can be guaranteed to some degree, but the comfort and sense of hazards for the drivers are ignored, and sometimes the AVs have unusual motion behaviours which may not be acceptable to other road users. To solve this problem, this study aims to develop a safety corridor-based vehicle motion control approach by investigating human-driven vehicle behaviour and the vehicle’s dynamic capabilities. The safety corridor is derived by the manoeuvring action feedback of actual drivers as collected in a driving simulator when presented with surrounding risk elements and enables the AVs to have safe trajectories within it. A corridor-based Nonlinear Model Predictive Control (NMPC) has been developed which controls the vehicle state to achieve a smooth and comfortable trajectory while applying trajectory constraints using the safety corridor. The safety corridor and motion controller are assessed using four typical scenarios to show that the vehicle has a human-like or human-oriented behaviour which is expected to be more acceptable for both drivers and other road users.",
keywords = "Autonomous vehicles, Human-like, Model predictive control, Risk-based corridor, Trajectory",
author = "Chongfeng Wei and Richard Romano and Natasha Merat and Yafei Wang and Chuan Hu and Hamid Taghavifar and Foroogh Hajiseyedjavadi and Boer, {Erwin R.}",
year = "2019",
month = "10",
doi = "10.1016/j.trc.2019.08.003",
language = "English",
volume = "107",
pages = "1--14",
journal = "Transportation Research Part C: Emerging Technologies",
issn = "0968-090X",
publisher = "Elsevier",

}

TY - JOUR

T1 - Risk-based autonomous vehicle motion control with considering human driver’s behaviour

AU - Wei, Chongfeng

AU - Romano, Richard

AU - Merat, Natasha

AU - Wang, Yafei

AU - Hu, Chuan

AU - Taghavifar, Hamid

AU - Hajiseyedjavadi, Foroogh

AU - Boer, Erwin R.

PY - 2019/10

Y1 - 2019/10

N2 - The selected motions of autonomous vehicles (AVs) are subject to the constraints from the surrounding traffic environment, infrastructure and the vehicle’s dynamic capabilities. Normally, the motion control of the vehicle is composed of trajectory planning and trajectory following according to the surrounding risk factors, the vehicles’ capabilities as well as tyre/road interaction situations. However, pure trajectory following with a unique path may make the motion control of the vehicle be too careful and cautious with a large amount of steering effort. To follow a planned trajectory, the AVs with the traditional path-following control algorithms will correct their states even if the vehicles have only a slight deviation from the desired path or the vehicle detects static infrastructure like roadside trees. In this case, the safety of the AVs can be guaranteed to some degree, but the comfort and sense of hazards for the drivers are ignored, and sometimes the AVs have unusual motion behaviours which may not be acceptable to other road users. To solve this problem, this study aims to develop a safety corridor-based vehicle motion control approach by investigating human-driven vehicle behaviour and the vehicle’s dynamic capabilities. The safety corridor is derived by the manoeuvring action feedback of actual drivers as collected in a driving simulator when presented with surrounding risk elements and enables the AVs to have safe trajectories within it. A corridor-based Nonlinear Model Predictive Control (NMPC) has been developed which controls the vehicle state to achieve a smooth and comfortable trajectory while applying trajectory constraints using the safety corridor. The safety corridor and motion controller are assessed using four typical scenarios to show that the vehicle has a human-like or human-oriented behaviour which is expected to be more acceptable for both drivers and other road users.

AB - The selected motions of autonomous vehicles (AVs) are subject to the constraints from the surrounding traffic environment, infrastructure and the vehicle’s dynamic capabilities. Normally, the motion control of the vehicle is composed of trajectory planning and trajectory following according to the surrounding risk factors, the vehicles’ capabilities as well as tyre/road interaction situations. However, pure trajectory following with a unique path may make the motion control of the vehicle be too careful and cautious with a large amount of steering effort. To follow a planned trajectory, the AVs with the traditional path-following control algorithms will correct their states even if the vehicles have only a slight deviation from the desired path or the vehicle detects static infrastructure like roadside trees. In this case, the safety of the AVs can be guaranteed to some degree, but the comfort and sense of hazards for the drivers are ignored, and sometimes the AVs have unusual motion behaviours which may not be acceptable to other road users. To solve this problem, this study aims to develop a safety corridor-based vehicle motion control approach by investigating human-driven vehicle behaviour and the vehicle’s dynamic capabilities. The safety corridor is derived by the manoeuvring action feedback of actual drivers as collected in a driving simulator when presented with surrounding risk elements and enables the AVs to have safe trajectories within it. A corridor-based Nonlinear Model Predictive Control (NMPC) has been developed which controls the vehicle state to achieve a smooth and comfortable trajectory while applying trajectory constraints using the safety corridor. The safety corridor and motion controller are assessed using four typical scenarios to show that the vehicle has a human-like or human-oriented behaviour which is expected to be more acceptable for both drivers and other road users.

KW - Autonomous vehicles

KW - Human-like

KW - Model predictive control

KW - Risk-based corridor

KW - Trajectory

UR - http://www.scopus.com/inward/record.url?scp=85070489250&partnerID=8YFLogxK

U2 - 10.1016/j.trc.2019.08.003

DO - 10.1016/j.trc.2019.08.003

M3 - Article

VL - 107

SP - 1

EP - 14

JO - Transportation Research Part C: Emerging Technologies

JF - Transportation Research Part C: Emerging Technologies

SN - 0968-090X

ER -