基于驾驶员避撞行为的行车风险判别方法的仿真研究
|
摘要
提出了一种基于驾驶员避撞行为的行车风险状态分类方法,并综合考虑驾驶员驾驶行为、道路和环境因素对行车风险状态变化的影响,运用支持向量机(SVM)建立不同行车模式下行车风险判别算法。基于美国弗吉尼亚理工大学"100-car"自然驾驶数据对预测算法进行了训练和验证,结果表明,在进行行车风险状态预测建模时考虑驾驶员行为、道路和环境因素的差异(特别是驾驶员分心状态)将有利于提高预测模型的准确率;另外,在满足假正率低于5%的条件下,本文构建的预测算法对未来行车过程中的高风险状态预测具有较高的准确率,有助于对临近危险状态的驾驶员给予及时的警告或辅助纠正,为防撞预警策略和控制方法的研究提供了新的思路。
A driving risk classification method based on driver's collision avoidance behavior is proposed, and the driving risk discrimination algorithms under different driving modes are established by using support vector machine with concurrent consideration of the effects of driving behavior, road condition and environmental factor on driving risk states. Training and validation on prediction algorithm are conducted based on the "100-car" natural driving data from Virginia Tech in the US. The results show that in driving risk prediction modeling, the consideration of the discrepancies in driver's behavior, road condition and environmental factor, in particular the driver's distraction state, is conducive to increasing the accuracy of prediction model. In addition, under the condition of false positive rate lower than 5%, the prediction of high-risk state for future driving process by using prediction algorithm created has higher accuracy, in favor of giving timely warning or correction aids to drivers in near danger state, providing a new idea for the research on collision avoidance warning strategy and control method.
A driving risk classification method based on driver's collision avoidance behavior is proposed, and the driving risk discrimination algorithms under different driving modes are established by using support vector machine with concurrent consideration of the effects of driving behavior, road condition and environmental factor on driving risk states. Training and validation on prediction algorithm are conducted based on the "100-car" natural driving data from Virginia Tech in the US. The results show that in driving risk prediction modeling, the consideration of the discrepancies in driver's behavior, road condition and environmental factor, in particular the driver's distraction state, is conducive to increasing the accuracy of prediction model. In addition, under the condition of false positive rate lower than 5%, the prediction of high-risk state for future driving process by using prediction algorithm created has higher accuracy, in favor of giving timely warning or correction aids to drivers in near danger state, providing a new idea for the research on collision avoidance warning strategy and control method.
引文
[1] 侯德藻,李克强,郑四发,等.汽车主动避撞系统中的报警方法及其关键技术[J].汽车工程,2002,24(5):438-444.
[2] KAKE A. Automatic time headway setting for adaptive cruise control system: US7966118[P].2011.
[3] 王畅,付锐,张琼,等.换道预警系统中参数TTC 特性研究[J].中国公路学报,2015,28(8):91-107.
[4] 倪捷,刘志强,涂孝军,等.面向驾驶辅助系统的换道安全性预测模型研究[J].交通运输系统工程与信息,2016,16(4):95-100.
[5] XIONG X, CHEN L, LIANG J. A new framework of vehicle collision prediction by combining SVM and HMM[J]. IEEE Transactions on Intelligent Transportation Systems,2017,19(3):699-710.
[6] WANG J, WU J, ZHENG X, et al. Driving safety field theory modeling and its application in pre-collision warning system[J]. Transportation Research Part C Emerging Technologies,2016,72:306-324.
[7] 林庆峰,成波,屈肖蕾,等.基于驾驶员制动操作行为的车辆追尾预警算法[J].汽车工程,2012,34(3):232-235.
[8] Virginia Tech Transportation Institute. VTTI data warehouse[DB/OL]. http://forums.vtti.vt.edu/index.php?/files/category/3-100-car-data/,2016-11-15.
[9] DAVID J, Jr CHRISTOPHER L. The application of cluster analysis in strategic management research: an analysis and critique[J]. Strategic Management Journal,1996,17(6):441-458.
[10] LI Y, LU J, XU K. Crash risk prediction model of lane-change behavior on approaching intersections[J]. Discrete Dynamics in Nature and Society,2017.
[11] THEODORIDIS S, KOUTROUMBAS K. Pattern recognition[M]. Academic Press (ISBN 0-12-686140-4),1999.
[12] BRUNSON S, KYLE E, PHAMDO N, et al. Alert algorithm development program: NHTSA rear-end collision alert algorithm[R]. U.S. Dept. of Transp., Tech. Rep. DOT HS 809 526,Sep.2002.
[13] TALBOT R, FAGERLIND H, MORRIS A. Exploring inattention and distraction in the safety net accident causation database[J]. Accident Analysis & Prevention,2013,60(45):445-455.
[14] 苗强,孙强,白书战,等.基于聚类和马尔可夫链的公交车典型行驶工况构建[J].中国公路学报,2016,29(11):161-169.
[15] DINGUS T, HULSE M, ANTIN J, et al. Attentional demand requirements of an automobile moving-map navigation system[J]. Transportation Research Part A General,1989,23(4):301-315.
[16] LINTING M, MEULMAN J, GROENEN P, et al. Nonlinear principal components analysis: introduction and application[J]. Psychological Methods,2007,12(3):336.
[17] SAS Institute, Inc. SAS/Stat 9.1 user's guide[G/OL]. http://support.sas.com/documentation/onlinedoc/91pdf/index_913.html,2004.
[18] 吴明隆.问卷统计分析实务:SPSS操作与应用[M].重庆:重庆大学出版社,2010.
[19] 熊晓夏,陈龙,梁军,等.危险换道驾驶行为预测方法研究[J].汽车工程,2017,39(9):1040-1046.
[20] MEINEL H. Automotive millimeterwave radar history and present status[C]. IEEE European Microwave Conference,1998:619-629.
[2] KAKE A. Automatic time headway setting for adaptive cruise control system: US7966118[P].2011.
[3] 王畅,付锐,张琼,等.换道预警系统中参数TTC 特性研究[J].中国公路学报,2015,28(8):91-107.
[4] 倪捷,刘志强,涂孝军,等.面向驾驶辅助系统的换道安全性预测模型研究[J].交通运输系统工程与信息,2016,16(4):95-100.
[5] XIONG X, CHEN L, LIANG J. A new framework of vehicle collision prediction by combining SVM and HMM[J]. IEEE Transactions on Intelligent Transportation Systems,2017,19(3):699-710.
[6] WANG J, WU J, ZHENG X, et al. Driving safety field theory modeling and its application in pre-collision warning system[J]. Transportation Research Part C Emerging Technologies,2016,72:306-324.
[7] 林庆峰,成波,屈肖蕾,等.基于驾驶员制动操作行为的车辆追尾预警算法[J].汽车工程,2012,34(3):232-235.
[8] Virginia Tech Transportation Institute. VTTI data warehouse[DB/OL]. http://forums.vtti.vt.edu/index.php?/files/category/3-100-car-data/,2016-11-15.
[9] DAVID J, Jr CHRISTOPHER L. The application of cluster analysis in strategic management research: an analysis and critique[J]. Strategic Management Journal,1996,17(6):441-458.
[10] LI Y, LU J, XU K. Crash risk prediction model of lane-change behavior on approaching intersections[J]. Discrete Dynamics in Nature and Society,2017.
[11] THEODORIDIS S, KOUTROUMBAS K. Pattern recognition[M]. Academic Press (ISBN 0-12-686140-4),1999.
[12] BRUNSON S, KYLE E, PHAMDO N, et al. Alert algorithm development program: NHTSA rear-end collision alert algorithm[R]. U.S. Dept. of Transp., Tech. Rep. DOT HS 809 526,Sep.2002.
[13] TALBOT R, FAGERLIND H, MORRIS A. Exploring inattention and distraction in the safety net accident causation database[J]. Accident Analysis & Prevention,2013,60(45):445-455.
[14] 苗强,孙强,白书战,等.基于聚类和马尔可夫链的公交车典型行驶工况构建[J].中国公路学报,2016,29(11):161-169.
[15] DINGUS T, HULSE M, ANTIN J, et al. Attentional demand requirements of an automobile moving-map navigation system[J]. Transportation Research Part A General,1989,23(4):301-315.
[16] LINTING M, MEULMAN J, GROENEN P, et al. Nonlinear principal components analysis: introduction and application[J]. Psychological Methods,2007,12(3):336.
[17] SAS Institute, Inc. SAS/Stat 9.1 user's guide[G/OL]. http://support.sas.com/documentation/onlinedoc/91pdf/index_913.html,2004.
[18] 吴明隆.问卷统计分析实务:SPSS操作与应用[M].重庆:重庆大学出版社,2010.
[19] 熊晓夏,陈龙,梁军,等.危险换道驾驶行为预测方法研究[J].汽车工程,2017,39(9):1040-1046.
[20] MEINEL H. Automotive millimeterwave radar history and present status[C]. IEEE European Microwave Conference,1998:619-629.