Decision Tree-Based Maneuver Prediction for Driver Rear-End Risk-Avoidance Behaviors in Cut-In Scenarios

Decision Tree-Based Maneuver Prediction for Driver Rear-End Risk-Avoidance Behaviors in Cut-In Scenarios

Predicting driver rear-end risk-avoidance maneuvers in cut-in scenarios, especially dangerous precrash scenarios, benefits the customization of automatic driving, particularly automatic steering. This paper studies driver rear-end risk-avoidance behaviors in cut-in scenarios on a straight three-lane...

Full description

Bibliographic Details
Main Authors: Manjiang Hu, Yuan Liao, Wenjun Wang, Guofa Li, Bo Cheng, Fang Chen
Format: Article
Language:English
Published: Hindawi-Wiley 2017-01-01
Series:Journal of Advanced Transportation
Online Access:http://dx.doi.org/10.1155/2017/7170358
id doaj-b59907f5d5044e9fa59f97db2a70e14e
record_format Article
spelling doaj-b59907f5d5044e9fa59f97db2a70e14e2020-11-25T02:37:33ZengHindawi-WileyJournal of Advanced Transportation0197-67292042-31952017-01-01201710.1155/2017/71703587170358Decision Tree-Based Maneuver Prediction for Driver Rear-End Risk-Avoidance Behaviors in Cut-In ScenariosManjiang Hu0Yuan Liao1Wenjun Wang2Guofa Li3Bo Cheng4Fang Chen5Department of Automotive Engineering, Tsinghua University, Beijing 100084, ChinaDepartment of Applied IT, Chalmers University of Technology, 412 96 Gothenburg, SwedenDepartment of Automotive Engineering, Tsinghua University, Beijing 100084, ChinaInstitute of Human Factors and Ergonomics, College of Mechatronics and Control Engineering, Shenzhen University, Shenzhen 518060, ChinaDepartment of Automotive Engineering, Tsinghua University, Beijing 100084, ChinaDepartment of Applied IT, Chalmers University of Technology, 412 96 Gothenburg, SwedenPredicting driver rear-end risk-avoidance maneuvers in cut-in scenarios, especially dangerous precrash scenarios, benefits the customization of automatic driving, particularly automatic steering. This paper studies driver rear-end risk-avoidance behaviors in cut-in scenarios on a straight three-lane highway. Data from 24 participants in 1326 valid trials were collected using a motion-based driving simulator. An Eysenck Personality Questionnaire (revised for Chinese participants) was used to obtain the personality traits of the participants. Based on a statistical analysis, the candidate features used in the driver maneuver prediction were determined as a combination of objective risk indicators and driver characteristics. A decision tree-based model was constructed for maneuver prediction in cut-in scenarios. The prediction accuracy of the extracted classification rules was 79.2% for the training data set and 80.3% for the test data set. The most powerful predictive variables were extracted, and their effects on maneuver decisions were analyzed. The results show that driver characteristics strongly influence the prediction of maneuver decisions.http://dx.doi.org/10.1155/2017/7170358
collection DOAJ
language English
format Article
sources DOAJ
author Manjiang Hu
Yuan Liao
Wenjun Wang
Guofa Li
Bo Cheng
Fang Chen
spellingShingle Manjiang Hu
Yuan Liao
Wenjun Wang
Guofa Li
Bo Cheng
Fang Chen
Decision Tree-Based Maneuver Prediction for Driver Rear-End Risk-Avoidance Behaviors in Cut-In Scenarios
Journal of Advanced Transportation
author_facet Manjiang Hu
Yuan Liao
Wenjun Wang
Guofa Li
Bo Cheng
Fang Chen
author_sort Manjiang Hu
title Decision Tree-Based Maneuver Prediction for Driver Rear-End Risk-Avoidance Behaviors in Cut-In Scenarios
title_short Decision Tree-Based Maneuver Prediction for Driver Rear-End Risk-Avoidance Behaviors in Cut-In Scenarios
title_full Decision Tree-Based Maneuver Prediction for Driver Rear-End Risk-Avoidance Behaviors in Cut-In Scenarios
title_fullStr Decision Tree-Based Maneuver Prediction for Driver Rear-End Risk-Avoidance Behaviors in Cut-In Scenarios
title_full_unstemmed Decision Tree-Based Maneuver Prediction for Driver Rear-End Risk-Avoidance Behaviors in Cut-In Scenarios
title_sort decision tree-based maneuver prediction for driver rear-end risk-avoidance behaviors in cut-in scenarios
publisher Hindawi-Wiley
series Journal of Advanced Transportation
issn 0197-6729
2042-3195
publishDate 2017-01-01
description Predicting driver rear-end risk-avoidance maneuvers in cut-in scenarios, especially dangerous precrash scenarios, benefits the customization of automatic driving, particularly automatic steering. This paper studies driver rear-end risk-avoidance behaviors in cut-in scenarios on a straight three-lane highway. Data from 24 participants in 1326 valid trials were collected using a motion-based driving simulator. An Eysenck Personality Questionnaire (revised for Chinese participants) was used to obtain the personality traits of the participants. Based on a statistical analysis, the candidate features used in the driver maneuver prediction were determined as a combination of objective risk indicators and driver characteristics. A decision tree-based model was constructed for maneuver prediction in cut-in scenarios. The prediction accuracy of the extracted classification rules was 79.2% for the training data set and 80.3% for the test data set. The most powerful predictive variables were extracted, and their effects on maneuver decisions were analyzed. The results show that driver characteristics strongly influence the prediction of maneuver decisions.
url http://dx.doi.org/10.1155/2017/7170358
work_keys_str_mv AT manjianghu decisiontreebasedmaneuverpredictionfordriverrearendriskavoidancebehaviorsincutinscenarios
AT yuanliao decisiontreebasedmaneuverpredictionfordriverrearendriskavoidancebehaviorsincutinscenarios
AT wenjunwang decisiontreebasedmaneuverpredictionfordriverrearendriskavoidancebehaviorsincutinscenarios
AT guofali decisiontreebasedmaneuverpredictionfordriverrearendriskavoidancebehaviorsincutinscenarios
AT bocheng decisiontreebasedmaneuverpredictionfordriverrearendriskavoidancebehaviorsincutinscenarios
AT fangchen decisiontreebasedmaneuverpredictionfordriverrearendriskavoidancebehaviorsincutinscenarios
_version_ 1724794902929211392

Similar Items