Takeover quality prediction based on driver physiological state of different cognitive tasks in conditionally automated driving

被引:20
作者
Zhu, Jieyu [1 ,2 ]
Ma, Yanli [1 ]
Zhang, Yiran [2 ]
Zhang, Yaping [1 ]
Lv, Chen [2 ]
机构
[1] Harbin Inst Technol, Sch Transportat Sci & Engn, Harbin 150090, Peoples R China
[2] Nanyang Technol Univ, Sch Mech & Aerosp Engn, Singapore 639798, Singapore
基金
中国国家自然科学基金;
关键词
Conditionally automated driving; Takeover quality prediction; Cognitive tasks; Multimodal physiological features; XGBoost and risk potential field; SITUATION AWARENESS; VEHICLE CONTROL; TIME; PERFORMANCE; REQUESTS; ENGAGEMENT; AGE;
D O I
10.1016/j.aei.2023.102100
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In conditionally automated driving, traffic safety problems would occur if the driver does not properly take over the control authority when the request of automated system arises. Therefore, this study proposes XGBoost learning method considering risk potential field to predict the takeover quality in conditionally automated driving under different levels of cognitive non-driving related tasks (NDRTs). Thirty participants drive on two experimental conditions: manual driving is following an automated driving during which the driver is asked to perform NDRTs. Drivers' physiological features of different cognitive states are exploited to model multi-level takeover quality prediction. This investigation also gives an insight into the main effects of the selected prediction variables on the takeover quality. The proposed model performance within different time windows is assessed using multiple evaluation metrics and compared with other methods. Results show that the prediction accuracy within the time windows of 7-10 s, 5-7 s, 3-5 s and 1-3 s is 0.87, 0.85, 0.85 and 0.90, respectively. The XGBoost model has the best performance of different time windows under each level of takeover quality compared to the other three machine learning models. Our findings can effectively predict the takeover quality and assist automated driving safely in interactions between drivers and automated vehicles.
引用
收藏
页数:15
相关论文
共 45 条
[1]  
Almogbel M., 2019, 2019 21 INT C ADV CO, DOI [10.23919/ICACT.2019.8702048, DOI 10.23919/ICACT.2019.8702048]
[2]   Moving Into the Loop: An Investigation of Drivers' Steering Behavior in Highly Automated Vehicles [J].
Alsaid, Areen ;
Lee, John D. ;
Price, Morgan .
HUMAN FACTORS, 2020, 62 (04) :671-683
[3]  
[Anonymous], 2014, P HUMAN FACTORS ERGO, DOI DOI 10.1177/1541931214581434
[4]   Modeling dispositional and initial learned trust in automated vehicles with predictability and explainability [J].
Ayoub, Jackie ;
Yang, X. Jessie ;
Zhou, Feng .
TRANSPORTATION RESEARCH PART F-TRAFFIC PSYCHOLOGY AND BEHAVIOUR, 2021, 77 :102-116
[5]   Analyzing crowdsourced ratings of speech-based take-over requests for automated driving [J].
Bazilinskyy, P. ;
de Winter, J. C. F. .
APPLIED ERGONOMICS, 2017, 64 :56-64
[6]   Ready for Take-Over? A New Driver Assistance System for an Automated Classification of Driver Take-Over Readiness [J].
Braunagel, Christian ;
Rosenstiel, Wolfgang ;
Kasneci, Enkelejda .
IEEE INTELLIGENT TRANSPORTATION SYSTEMS MAGAZINE, 2017, 9 (04) :10-22
[7]  
Bueno M, 2016, 2016 IEEE 19TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC), P2040, DOI 10.1109/ITSC.2016.7795886
[8]   XGBoost: A Scalable Tree Boosting System [J].
Chen, Tianqi ;
Guestrin, Carlos .
KDD'16: PROCEEDINGS OF THE 22ND ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2016, :785-794
[9]   Age differences in the takeover of vehicle control and engagement in non-driving-related activities in simulated driving with conditional automation [J].
Clark, Hallie ;
Feng, Jing .
ACCIDENT ANALYSIS AND PREVENTION, 2017, 106 :468-479
[10]   Looking at the Driver/Rider in Autonomous Vehicles to Predict Take-Over Readiness [J].
Deo, Nachiket ;
Trivedi, Mohan M. .
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES, 2020, 5 (01) :41-52