An interpretable prediction model of illegal running into the opposite lane on curve sections of two-lane rural roads from drivers' visual perceptions

Li He; Bo Yu; Yuren Chen; Shan Bao; Kun Gao; You Kong

doi:10.1016/j.aap.2023.107066

An interpretable prediction model of illegal running into the opposite lane on curve sections of two-lane rural roads from drivers' visual perceptions

Accid Anal Prev. 2023 Jun:186:107066. doi: 10.1016/j.aap.2023.107066. Epub 2023 Apr 13.

Authors

Li He¹, Bo Yu², Yuren Chen³, Shan Bao⁴, Kun Gao⁵, You Kong⁶

Affiliations

¹ Key Laboratory of Road and Traffic Engineering of the Ministry of Education, College of Transportation Engineering, Tongji University, 4800 Cao'an Highway, Shanghai 201804, China. Electronic address: 2131290@tongji.edu.cn.
² Key Laboratory of Road and Traffic Engineering of the Ministry of Education, College of Transportation Engineering, Tongji University, 4800 Cao'an Highway, Shanghai 201804, China. Electronic address: boyu@tongji.edu.cn.
³ Key Laboratory of Road and Traffic Engineering of the Ministry of Education, College of Transportation Engineering, Tongji University, 4800 Cao'an Highway, Shanghai 201804, China. Electronic address: chenyr@tongji.edu.cn.
⁴ University of Michigan Transportation Research Institute, 2901 Baxter Rd, Ann Arbor, MI 48109-2150, USA. Electronic address: shanbao@umich.edu.
⁵ Department of Architecture and Civil Engineering, Chalmers University of Technology, Gothenburg SE-412 96, Sweden. Electronic address: gkun@chalmers.se.
⁶ College of Transport and Communications, Shanghai Maritime University, No.1550, Haigang Avenue, Lin'gang Xincheng, Pudong, Shanghai 201303, China. Electronic address: kongyou@shmtu.edu.cn.

PMID: 37058902
DOI: 10.1016/j.aap.2023.107066

Abstract

Illegal running into the opposite lane (IROL) on curve sections of two-lane rural roads is a frequently hazardous behavior and highly prone to fatal crashes. Although driving behaviors are always determined by the information from drivers' visual perceptions, current studies do not consider visual perceptions in predicting the occurrence of IROL. In addition, most machine learning methods belong to black-box algorithms and lack the interpretation of prediction results. Therefore, this study aims to propose an interpretable prediction model of IROL on curve sections of two-lane rural roads from drivers' visual perceptions. A new visual road environment model, consisting of five different visual layers, was established to better quantify drivers' visual perceptions by using deep neural networks. In this study, naturalistic driving data was collected on curve sections of typical two-lane rural roads in Tibet, China. There were 25 input variables extracted from the visual road environment, vehicle kinematics, and driver characteristics. Then, XGBoost (eXtreme Gradient Boosting) and SHAP (SHapley Additive exPlanation) methods were combined to build a prediction model. The results showed that our prediction model performed well, with an accuracy of 86.2% and an AUC value of 0.921. The average lead time of this prediction model was 4.4 s, sufficient for drivers to respond. Due to the advantages of SHAP, this study interpreted the impacting factors on this illegal behavior from three aspects, including relative importance, specific impacts, and variable dependency. After offering more quantitative information on the visual road environment, the findings of this study could improve the current prediction model and optimize road environment design, thereby reducing IROL on curve sections of two-lane rural roads.

Keywords: Curve sections of two-lane rural roads; Deep neural networks; Illegal running into the opposite lane; Interpretable machine learning; Naturalistic driving data; Visual road environment quantification.

MeSH terms

Accidents, Traffic* / prevention & control
Automobile Driving*
Environment Design
Humans
Rural Population
Visual Perception