基于视觉特性与车辆相对运动的驾驶人换道意图识别方法
|
摘要
变换车道时，如果驾驶人对周围环境的观察不够充分，或判断决策失误，极易酿成事故。当前应用的换道辅助系统多以转向灯信号作为识别驾驶人换道意图的主要依据，由于实际驾驶过程中转向灯开启率低及开启时间提前量不够，使系统存在漏报及错误报警。如果能在换道开始前提前识别出驾驶人的操作意图，不再单独依靠转向灯信号作为识别依据，则可预先对驾驶人所处环境进行安全性评估，在危险的酝酿期向驾驶人预警，从而规避交通事故的发生，并降低不安全驾驶行为对交通流的扰动。
本文结合驾驶期望及博弈理论等对驾驶人车道变换决策机制进行深入分析，确定换道意图识别研究需求参数。选取16名被试驾驶人，在拟定路线上开展真实道路环境下的驾驶试验，采集反映驾驶人行为特性的视觉搜索、操作特性、车辆运动状态及周围环境等相关参数，为进行换道意图识别提供相应的数据支撑。
基于对驾驶人换道前后视镜注视特性的深入分析，确定驾驶人车道变换意图表征时窗，分析意图时窗内驾驶人基本注视及扫视参数的变化规律；采用视野平面法划分驾驶人兴趣区域，应用马尔可夫链理论计算驾驶人在不同注视区域间的一步及两步转移概率，提取车道保持阶段与换道意图阶段驾驶人获取外界信息的主要搜索路径，进一步基于马尔可夫链平稳分布，得到不同行驶阶段驾驶人对各区域的注视概率分布差异；结合驾驶人头部转动角度与注视角度的相关性分析及头眼协作模式的探索，综合确定可以有效表征驾驶人换道意图的视觉特征参数；在对车道保持与换道意图阶段车辆运动状态、驾驶人操作特性以及周围环境状态进行深入分析的基础上，确定车辆运动子模块中与驾驶人换道意图及换道行为相关性较强的因素。
基于证据理论，构建识别框架，确定驾驶人换道意图表征证据链，构造基于广义汉明距离的基本信任分配函数，采用滑动累积时窗，对视觉特性子模块的换道意图进行多证据融合识别；确定待选因子，基于车道保持与意图学习样本建立Logistic模型，据此识别车辆运动子模块所体现的换道意图，并进一步预测换道行为是否会如期而至。集成以上两种识别方法，并分析其识别成功率及时序性。本文主要研究结论如下：
1．驾驶人在当前车道驾驶期望满足度较低是其产生换道意图的根本原因；
2．驾驶人车道变换意图的表征时窗宽约为5s；
3．对后视镜的注视特性可以有效体现驾驶人的换道意图，且意图阶段驾驶人对当前车道的关注程度明显低于车道保持阶段；
4．视点小幅度转移条件下，头部转动与注视角度相关性较低，而在视点大幅转移条件下，二者相关性较强，且头部运动比眼睛运动能更早的体现驾驶人换道意图；
5．基于证据理论与Logistic模型均可以有效识别驾驶人的换道意图，识别准确率分别为90.02%与86.07%。
本研究得到了国家自然科学基金项目（51178053）的资助。
When lane change maneuver is executed, if the driver doesn’t observe the surroundingenvironment sufficiently, or wrong decision and judgements are made, this may easily lead toaccidents. The lane changing assistance system in the application serves turn signal as themain basis to identify drivers’ lane change intent, given the low usage rate and the short leadtime of the turn signal lamps, this result in poor performance of the assistance system. Ifdriver's maneuver intention could be identified precisely before lane change occurs, and nolonger solely depending on turn signals as the main basis of identification, then we canevaluate the driving environments in advance, warn the drivers in the incubation period of thedanger to avoid traffic accidents, and then reduce the disturbance of traffic flow caused byunsafe driving behaviors.
Combining with driving expectation and game theory, lane change decision-makingmechanism was thoroughly analyzed, related demand parameters of lane changing intentidentification were determined. Large scale real-world experiments were conducted on theselected routes, and16subjects took part in the experiments. Related parameters which couldreflect drivers’ visual search, operating characteristics, vehicles’ motion states and drivingenvironments were synchronously collected, so as to provide corresponding data items to lanechange intent identification research.
Based on the deep analysis of driver’s fixation characteristics to the rearview mirrorbefore lane changing, time window which could characterizes driver’s lane changing intentwas determined, variation law of basic fixation and saccade parameters were analyzed withinthe time window. Regions of Interest were divided by the visual field plane, one-step andtwo-step transition probabilities between the regions were calculated with the application ofMarkov chain theory, the main visual search paths where the driver acquired informationduring the stage of lane keeping and lane changing intent were selected. Based on the Markovchain stationary distribution, glance proportions discrepancies among the interest regionsduring different driving stages were obtained. Combining with correlations analysis betweenhead rotations and gaze angles, as well as the analysis of driver’s head-eye coordination mode,visual parameters that can characterize driver’s lane change intention were extracted. In addition, based on the deep analysis of vehicle dynamics, drivers’ operation characteristicsand surrounding environment conditions, factors that own strong correlation with lanechanging intent and behavior were determined.
Based on the evidence theory, identification framework was constructed, evidence chainthat could characterize drivers’ lane change intent was determined, based on generalizedhamming distance, basic belief assignment function was established. Sliding and accumulatedtime window was adopted, then multi-evidence fusion identification was carried out withinthe visual characteristics submodule. Given the selected factors ascertained, logisticregression models were built to identify lane change intent reflected by the vehicle dynamicsubmodule, whether a lane change would take place was further predicted. With theintegration of the two identification methods mentioned above, success rate and timesequence of the identification were soon afterwards determined. The following conclusionscan be drawn from this research work.
1. Drivers’ low satisfaction in the current lane is the root of the lane changing intent.
2. The time window that characterizes driver’s lane change intent is about five seconds.
3. Fixation characteristics to the rearview mirror is the vital reflection of lane changeintent, in the lane changing intent stage drivers focus fewer minds on current lane than in thelane keeping stage.
4. Under the condition of small amplitude transfer of fixation points, head rotations showweak correlation with gaze angles, while there is a strong correlation between them whenlarge scale transfer of fixation occurs, and head rotations can reflect drivers’ lane changingintent earlier than eye movements.
5. Based on evidence theory and Logistic regression, drivers’ lane change intent caneffectively be identified, and accuracy rates are90.02%and86.07%, respectively.
The research was sponsored by National Natural Science Foundation (51178053).
本文结合驾驶期望及博弈理论等对驾驶人车道变换决策机制进行深入分析，确定换道意图识别研究需求参数。选取16名被试驾驶人，在拟定路线上开展真实道路环境下的驾驶试验，采集反映驾驶人行为特性的视觉搜索、操作特性、车辆运动状态及周围环境等相关参数，为进行换道意图识别提供相应的数据支撑。
基于对驾驶人换道前后视镜注视特性的深入分析，确定驾驶人车道变换意图表征时窗，分析意图时窗内驾驶人基本注视及扫视参数的变化规律；采用视野平面法划分驾驶人兴趣区域，应用马尔可夫链理论计算驾驶人在不同注视区域间的一步及两步转移概率，提取车道保持阶段与换道意图阶段驾驶人获取外界信息的主要搜索路径，进一步基于马尔可夫链平稳分布，得到不同行驶阶段驾驶人对各区域的注视概率分布差异；结合驾驶人头部转动角度与注视角度的相关性分析及头眼协作模式的探索，综合确定可以有效表征驾驶人换道意图的视觉特征参数；在对车道保持与换道意图阶段车辆运动状态、驾驶人操作特性以及周围环境状态进行深入分析的基础上，确定车辆运动子模块中与驾驶人换道意图及换道行为相关性较强的因素。
基于证据理论，构建识别框架，确定驾驶人换道意图表征证据链，构造基于广义汉明距离的基本信任分配函数，采用滑动累积时窗，对视觉特性子模块的换道意图进行多证据融合识别；确定待选因子，基于车道保持与意图学习样本建立Logistic模型，据此识别车辆运动子模块所体现的换道意图，并进一步预测换道行为是否会如期而至。集成以上两种识别方法，并分析其识别成功率及时序性。本文主要研究结论如下：
1．驾驶人在当前车道驾驶期望满足度较低是其产生换道意图的根本原因；
2．驾驶人车道变换意图的表征时窗宽约为5s；
3．对后视镜的注视特性可以有效体现驾驶人的换道意图，且意图阶段驾驶人对当前车道的关注程度明显低于车道保持阶段；
4．视点小幅度转移条件下，头部转动与注视角度相关性较低，而在视点大幅转移条件下，二者相关性较强，且头部运动比眼睛运动能更早的体现驾驶人换道意图；
5．基于证据理论与Logistic模型均可以有效识别驾驶人的换道意图，识别准确率分别为90.02%与86.07%。
本研究得到了国家自然科学基金项目（51178053）的资助。
When lane change maneuver is executed, if the driver doesn’t observe the surroundingenvironment sufficiently, or wrong decision and judgements are made, this may easily lead toaccidents. The lane changing assistance system in the application serves turn signal as themain basis to identify drivers’ lane change intent, given the low usage rate and the short leadtime of the turn signal lamps, this result in poor performance of the assistance system. Ifdriver's maneuver intention could be identified precisely before lane change occurs, and nolonger solely depending on turn signals as the main basis of identification, then we canevaluate the driving environments in advance, warn the drivers in the incubation period of thedanger to avoid traffic accidents, and then reduce the disturbance of traffic flow caused byunsafe driving behaviors.
Combining with driving expectation and game theory, lane change decision-makingmechanism was thoroughly analyzed, related demand parameters of lane changing intentidentification were determined. Large scale real-world experiments were conducted on theselected routes, and16subjects took part in the experiments. Related parameters which couldreflect drivers’ visual search, operating characteristics, vehicles’ motion states and drivingenvironments were synchronously collected, so as to provide corresponding data items to lanechange intent identification research.
Based on the deep analysis of driver’s fixation characteristics to the rearview mirrorbefore lane changing, time window which could characterizes driver’s lane changing intentwas determined, variation law of basic fixation and saccade parameters were analyzed withinthe time window. Regions of Interest were divided by the visual field plane, one-step andtwo-step transition probabilities between the regions were calculated with the application ofMarkov chain theory, the main visual search paths where the driver acquired informationduring the stage of lane keeping and lane changing intent were selected. Based on the Markovchain stationary distribution, glance proportions discrepancies among the interest regionsduring different driving stages were obtained. Combining with correlations analysis betweenhead rotations and gaze angles, as well as the analysis of driver’s head-eye coordination mode,visual parameters that can characterize driver’s lane change intention were extracted. In addition, based on the deep analysis of vehicle dynamics, drivers’ operation characteristicsand surrounding environment conditions, factors that own strong correlation with lanechanging intent and behavior were determined.
Based on the evidence theory, identification framework was constructed, evidence chainthat could characterize drivers’ lane change intent was determined, based on generalizedhamming distance, basic belief assignment function was established. Sliding and accumulatedtime window was adopted, then multi-evidence fusion identification was carried out withinthe visual characteristics submodule. Given the selected factors ascertained, logisticregression models were built to identify lane change intent reflected by the vehicle dynamicsubmodule, whether a lane change would take place was further predicted. With theintegration of the two identification methods mentioned above, success rate and timesequence of the identification were soon afterwards determined. The following conclusionscan be drawn from this research work.
1. Drivers’ low satisfaction in the current lane is the root of the lane changing intent.
2. The time window that characterizes driver’s lane change intent is about five seconds.
3. Fixation characteristics to the rearview mirror is the vital reflection of lane changeintent, in the lane changing intent stage drivers focus fewer minds on current lane than in thelane keeping stage.
4. Under the condition of small amplitude transfer of fixation points, head rotations showweak correlation with gaze angles, while there is a strong correlation between them whenlarge scale transfer of fixation occurs, and head rotations can reflect drivers’ lane changingintent earlier than eye movements.
5. Based on evidence theory and Logistic regression, drivers’ lane change intent caneffectively be identified, and accuracy rates are90.02%and86.07%, respectively.
The research was sponsored by National Natural Science Foundation (51178053).
引文
[1]彭金栓，付锐.道路交通安全系统透析[J].长安大学学报（自然科学版），2011，30(6)：72-75.
[2] B.Sultan, M.McDonald.The lane changing process: data analysis&modelingbehaviour.Traffic Engineering Control.2001,42(3):202-207.
[3]公安部交通管理局.中华人民共和国道路交通事故统计年报[R].北京:公安部交通管理局，2010.
[4]路明辉，任宇立.奥迪Q7驾驶辅助系统之换道辅助系统[J].整车电路，2008，10：25-31.
[5] P.G.Gipps.A Model for the structure of lane-changing decisions.Transportation ResearchPart B.1986:403-414.
[6]李迎峰，史忠科，周致纳．微观交通仿真中随机决策换道行为研究[J].系统仿真学报，2008，20(16)：4273-4277.
[7]刘小明，关淑辉．基于动态重复博弈的车辆换道模型[J]．公路交通科技，2008，25（6）：121-125.
[8]金立生，杨双宾，Mascha van der Voort,Martijn Tidema．高速公路汽车辅助驾驶安全换道模型[J].吉林大学学报(工学版)，2009，39(3)：582-586.
[9]杨双宾．高速公路车辆行驶安全辅助换道系统研究[D]．吉林大学，2008.
[10]黄秋菊.车道变换行为特性及其对交通安全影响的研究[D]．哈尔滨工业大学，2007.
[11]魏丽英，隽志才，田春林.驾驶员车道变换行为模拟分析[J].中国公路学报，2001，14（1）：77-80.
[12]谭春满.基于Agent与模糊逻辑的车辆换道仿真模型[J].系统工程学报，2007，22（1）：40-45.
[13]林广宇，魏朗.基于机器视觉的驾驶员换道行驶检测研究[J].计算机工程与应用，2009，45（33）：22-24.
[14]叶品，钟诚文，李兵强.基于快慢车辆主动换道特性的双车道元胞自动机模型研究[J].交通与计算机，2007，25（1）：86-89.
[15]林旸，蒋珉，柴干.基于模糊控制的微观车辆换道模型的研究及仿真[J].计算机技术与发展，2009，19（11）：250-253.
[16]张发，宣慧玉，赵巧霞.基于有限状态自动机的车道变换模型[J].中国公路学报，2008,21（3）：97-100.
[17]杨小宝，张宁,黄留兵.通行能力仿真中的换道模型研究[J].公路交通科技，2007，24（5）：109-112.
[18]裴玉龙，张银.车道变换期望运行轨迹仿真[J].交通与计算机，2008，26(4)：68-71．
[19]裴玉龙，于涛．车道变换进程中驾驶员视点转移特性研究[J].交通信息与安全，2009，27（2）：92-95.
[20]霍克．城市道路驾驶员车道变换行为及注视转移特性研究[D]．长安大学，2010．
[21]邓海军，尹全军，胡记文,查亚兵.基于MEBN的战术意图识别[J].系统工程与电子技术，2010，32（11）：2374-2379.
[22]吴涛，王崇骏，谢俊元.基于部分可观测马尔可夫决策过程的网络入侵意图识别研究[J].南京大学学报自然科学版，2010，46(2)：122-130.
[23]李之棠，王莉，李东.一种新的在线攻击意图识别方法研究[J].小型微型计算机系统，2008，29(7)：1347-1352.
[24]储颖，肖献强，朱家诚.基于驾驶行为及意图的汽车主动安全技术研究[J].机械设计与制造，2011，1（1）：266-268.
[25]王英范，宁国宝，余卓平.乘用车驾驶员制动意图识别参数的选择[J].汽车工程，2011，33（3）：213-216.
[26]宗长富，王畅，何磊，郑宏宇.基于双层隐式马尔可夫模型的驾驶意图辨识[J].汽车工程，2011，33(8)：701-706.
[27]王玉海，宋健，李兴坤．驾驶员意图与行驶环境的统一识别及实时算法[J].机械工程学报，2006，42（4）：206-212.
[28]郭孜政，陈崇双，王欣.基于贝叶斯判别的驾驶行为危险状态辨识[J].西南交通大学学报，2009，44(5)：771-774.
[29]张旭东.基于稀疏贝叶斯分类器的汽车车型识别[J].小型微型计算机系统，2005，26（10）：1839-1841.
[30]王晓原，杨新月，王晓辉，刘智平. D-S证据理论在驾驶行为决策中的应用[J].计算机工程与应用，2007，43（27）：230-233.
[31] Ioannis Golias, Mstthew, G.Karlaftis.An International Comparative Study ofSelf-report Driver Behavior [J].Transportation Research Part F.2002:243-246.
[32] Martin Lavallière, Nathan Ngan. Age-Related Deficits in the Frequency of GazeResponse to the Mirrors and Blind-Spot during Lane Change Maneuvers of VariousComplexities [J].2007Proceedings of the Fourth International Driving Symposium onHuman Factors in Driver Assessment, Training and Vehicle Design:373-380.
[33] Guihua Yang, Beverly Jaeger. Driving performance of novice and experienced drivers inlane-change scenarios [J]. Proceedings of the human factors and ergonomics society50th annual meeting (2006):2712-2716.
[34] Louis Tijerina, W. R. Garrott, M. Gleckler. Van and Passenger Car Driver Eye GlanceBehavior during the Lane Change Decision Phase [R]. NHTSA Vehicle Research andTest Center, East Liberty, Ohio, Nov.1997.
[35] Louis Tijerina, W. Riley Garrott. Eye glance behavior of van and passenger car driversduring lane change decision phase [J]. Journal of the Transportation Research Board(2005):37-43.
[36] Thomas Ayres, Li, Doris. Passenger-side Rear-view Mirror: Driver Behavior andSafety.International [J]. Journal of Industrial Ergonomics.2005,(35):157-162.
[37] Tony Wynn, John. Cognitive activity modeling: a case study of lane change schemas andsensation seeking [J]. European Conference on Human Centered Design for IntelligentTransport Systems (2008):177-285.
[38] Cooper, J. M., Vladisavljevic. Drivers’ Lane Changing Behavior While Conversing On aCell Phone in a Variable Density Simulated Highway Environment [J]. TransportationResearch Board January2008:2-12.
[39] Yoshihiro Nishiwaki, Chiyomi Miyajima, Norihide Kitaoka. Generating Lane-ChangeTrajectories of Individual Drivers [J]. Proceedings of the2008IEEE InternationalConference on Vehicular Electronics and Safety:271-275.
[40] W.van Winsum, D.de Waard, K.A.Brookhuis.Lane Change Manoeuvres and SafetyMargins [J].Transportation Research Part F1999(2):139-149.
[41] Liu A. What the driver’s eye tells the car’s brain? In: G. Under wood (Ed). Eye guidancein reading and scene perception [J]. England: Elsevier,1998:431-452.
[42] Dario D. Salvucci, Andrew Liu. The time course of a lane change: Driver control andeye-movement behavior [J]. Transportation Research Part F5(2002):123-132.
[43] Matthias J. Henning, Olivier georgeon, Josef F.krems. The quality of behavioral andenvironmental indicators used to infer the intention to change lanes [J]. TransportationResearch Part F4(2001):1-7.
[44] V.Bhise, J.Meldrum, D. Jack, G.Troell, D.Hoffmeister, and L.Forbes. Driver headmovements in left outside mirror viewing [J]. Society of Autmotive Engineers, no.810761,1981.
[45] F. Lethaus, J. Rataj. Do eye movements reflect driving maneuvers [J]? IETIntell.September2007,1(3):199–204.
[46] N. Kuge, T. Yamamura, O. Shimoyama, A. Liu. A Driver Behavior Recognition MethodBased on a Driver Model Framework [J]. SAE Technical Paper,2000-01-0349.
[47] Andrew Liu, Alex pretend. Towards real-time recognition of driver intentions[J].Intelligent Transportation System,1997, IEEE Conference, Boston, MA:236-241.
[48] Huiping Zhou, Makoto Itoh, Toshiyuki Inagaki. How Do Cognitive Distraction AffectDriver Intent of Changing Lanes [J]. M. Xie et al.(Eds.): ICIRA2009:235-244,2009.
[49] Huiping Zhou, Makoto Itoh, Toshiyuki Inagaki. Influence of cognitively distractingactivity on driver's eye movement during preparation of changing lanes [J]. SICEAnnual Conference2008:866~871.
[50] Aris Polychronopoulos, Christos Koutsimanis, Manolis Tsogas, Angelos Amditis.Prediction of Unintentional Lane Departure Using Evidence Theory [J].20057thInternational Conference on Information Fusion:1396-1403.
[51] JoelC.MeCal, DavidRWIPf. Lane change Intent Analysis Using Robust Operators andSparse Bayesian Learning [J].IEEE Intelligent Transportation Systems,2007,8(3):431-440.
[52] Erik C. B. Olsen, Suzanne E. Lee, Walter W.Wierwille. Eye glance behavior during lanechanges and straight-ahead driving [J]. Transportation Research Board of the NationalAcademies, Washington, D.C.,2005:44–50.
[53] Eui Yoon Chung, Ho Choul Jung, Eugene Chang, and In Sik Lee. Vision Based for LaneChange Decision Aid System [J]. Strategic Technology, the1st International Forum2006:10-13.
[54] M.Ruder, Highway Lane Change Assistant, IEEE International Conference onIntelligent Vehicle,2000:17-22.
[55] Yiguang Xuan，Benjamin Coifman. Lane Change Maneuver Detection from ProbeVehicle DGPS Data [J].2006IEEE Intelligent Transportation Systems Conference inToronto:624-629.
[56] Nuria Oliver, Alex P. Pentland. Graphical Models for Driver Behavior Recognition in aSmart Car [J]. Proceedings of the lEEE Intelligent Vehicles Symposium2000:7-12.
[57] Suzanne E. Lee, Erik C.B. Olsen, Walter W. Wierwille. A Comprehensive Examination ofNaturalistic Lane-Changes [R]. Virginia Tech Transportation Institute, March2004.
[58] M. Fitch, J. Hankey, J. Sudweeks, and T. Dingus. Analysis of Lane-Change Crashes andNear-Crashes [R]. Virginia Tech Transportation Institute, June2009.
[59] Raymond J. Kiefer, Jonathan M. Hankey. Lane change behavior with a side blind zonealert system [J]. Accident Analysis and Prevention40(2008):683–690.
[60] Rafael Toledo-Moreo. IMM-Based Lane-Change Prediction in Highways With Low-CostGPS/INS [J]. IEEE transactions on intelligent transportation systems,2009,10(1):180-185.
[61] Nobuyuki Kuge, Hiroshi Ueno, Hideaki Ichikawa, Kiyoshi Ochiai.A Study on the Causesof Rear-end Collision Based on an Analysis of Driver Behavior [J]. JSAR Review,1995,(16):55-60.
[62] Worrall R D, Bullen A G R. An empirical analysis of lane changing on multilanehighways[R]. Washington: Highway Research Board.
[63]杨建国，王金梅，李庆丰，王兆安.微观仿真中车辆换道的行为分析和建模[J].公路交通科技，2004，21（11）：93-97.
[64]金艳秋.基于模拟实验的驾驶员期望车速模型研究[D].昆明理工大学，2009.
[65]王晓原，邢丽，吴芳.基于决策树模型的驾驶员期望车速[J].计算机应用，2009，29（12）：318-321.
[66]郑安文.期望车速的意义及其影响因素分析[J].武汉科技大学学报（自然科学版），2005，28(1)：61-64.
[67]徐杰，杜文.跟随车安全距离的分析[J].交通运输工程学报，2002，2(1)：101-104.
[68]杨伟，徐杰，李宗平.高速公路上跟随车安全距离的一种确定方法[J].四川工业学院学报，2002，21(1)：20-22.
[69] Peng Jin-shuan. Research of Lane Change Decision Based on Drivers’Perception-Judgment and Game Theory [J].3rd International Conference on PowerElectronics and Intelligent Transportation System,2010,(6):5-9.
[70]彭金栓，付锐，石磊磊，张琼.驾驶人车道变换决策分析[J].武汉理工大学学报，2011，33(12)：46-50.
[71] HIDAS P. Modeling lane changing and merging in microscopic traffic simulation[J].Transportation Research Part C,2002,10(5):351-371.
[72]周立军.基于驾驶员信息处理特性的跟驰及换道模型研究[D].吉林大学，2008.
[73] C.Altavilla, L.Luini, p.Sloriglia. Social learning in market game [J]. Journal of EconomicBehavior&Organization,2006,61:632-652.
[74]彭金栓，付锐，郭应时，袁伟.基于有限零和灰色博弈的车道变换决策分析[J].科技导报，2011，29（3）：52-56.
[75] Von Neumann, O.Morgenstrn. Theory of Games and Economic Behavior. PrincetonUniversity Press,1944.
[76]罗党.灰色决策问题的分析方法研究[D].南京：南京航空航天大学，2004.
[77] M.Dietze, D.Ebersbach, CH.Lippold. Road Geometry, Driving Behaviour and RoadSafety[R].Road Infrastructure Safety Protection-Core Research and Development forRoad Safety in Europe,2008.
[78] Seeing Machines. http://www.seeingmachines.com.
[79] Hanowski, Wierwille, Garness. A field evaluation of safety issues in local/short haultrucking. In Proceedings of the XIVth Triennial Congress of the InternationalErgonomics Association and44th Annual Meeting of the Human Factors andErgonomics Society. Santa Monica, CA: Human Factors and Ergonomics Society,2000(3):365-368.
[80] Erik C. B. Olsen. Modeling Slow Lead Vehicle Lane Changing [D]. Doctor ofphilosophy in industrial and systems engineering, Virginia polytechnic institute and stateuniversity,2003.
[81] http://tool.chinaz.com/Tools/unixtime.aspx.
[82] Torbj rn Falkmer, Nils Petter Gregersen．Fixation patterns of learner drivers with andwithout cerebral palsy (CP) when driving in real traffic environments[J]． Transportation Research Part F,2001,4(3):171-185.
[83] David Crundall, Geoffrey Underwood．Effects of experience and processing demands onvisual information acquisition in drivers [J]． Ergonomics,1998,41(4):448-458.
[84] Geoffrey Underwood, Peter Chapman, Neil Brocklehurst, Jean Underwood, DavidCrundall． Visual attention while driving: sequences of eye fixations made byexperienced and novice drivers [J]． Ergonomics,2003,46(6):629-646.
[85] Albrecht W. Inhoff，Matthew S. Solomon，Bradley A. Seymour，Ralph Radach. Eyeposition changes during reading fixations are spatially selective [J]. Vision research，2007，48（26）：1027-1039.
[86]白志锋.最小角定理及其它[J].数学大世界，2002（Z1）：12-13.
[87]袁伟.城市道路环境中汽车驾驶员动态视觉特性试验研究[D].长安大学，2008.
[88] Underwood Geoffrey, Crundall David, Chapman Peter. Selective searching while driving:the role of experience in hazard detection and general surveillance [J]. Ergonomics,2002,45（1）:1-12.
[89] Bao Shan, Boyle Linda Ng. Age-related differences in visual scanning at median-dividedhighway intersections in rural areas [J]. Accident Analysis&Prevention,2009,41（1）:146-152.
[90]刘次华.随机过程[M].武汉：华中科技大学出版社，2001.
[91]刘建民．随机过程[M]．西安：西北大学出版社，2004.
[92] Geoffrey Underwood, Peter Chapman, Karen Bowden, David Crundall. Visual searchwhile driving: skill and awareness during inspection of the scene [J].TransportationResearch Part F,2002,5(2):87-97.
[93] Peter Chapman, Geoffrey Underwood, Katharine Roberts．Visual search patterns intrained and untrained novice drivers [J]. Transportation Research Part F,2002,5(2):157-167.
[94] Trent W. Victor, Joanne L. Harbluk. Sensitivity of eye-movement measures to in-vehicletask difficulty [J]. Transportation Research Part F8(2005):167–190.
[95]方烈义，孙复川.眼一头运动协同中头部运动的双重模式控制[J].生理学报，1995，47(1)：45-53.
[96]黎清.方向盘转角与行车安全[J].河北农机，1999，（1）：15-16.
[97] Nakayama. Development of a steering entropy method for evaluating driver workload[C].1999Proceeding SAE International Congress and Exposition:1-10.
[98] Michael E. Rakauskas, Leo J. Gugerty, Nicholas J. Ward. Effects of naturalistic cellphone conversations on driving performance [J]. Journal of Safety Research,2004,35:453–464.
[99] Minderhoud, M.M.and Bovy, P.H.L. Extended time-to-collision measures for road trafficsafety assessment.Acc.Anal.Prev.33,2001:89-97.
[100] Hirst, S.and Graham, R.The format and presentation of collision warnings [J].Ergonomics and safety of Intelligent Driver Interfaces,1997.
[101] ANAND S S, BELL D A. A general framework for data mining based on evidencetheory [J].Data&Knowledge Engineering,1996,18:189-223.
[102] Shafer G.A mathematical theory of evidence[M].New Jersay：Princeton UniversityPress，1996．
[103] Jennie Pearce，Simon Ferrier. Evaluating the predictive performance of habitat modelsdeveloped using logistic regression [J]. Ecological Modelling,2000,133(3):225-245.
[104] Georg Heinze, Michael Schemper. A solution to the problem of separation in logisticregression [J]. Statistics in Medicine,2002,21(16):2409-2419.
[105] John D. Chovan, Louis Tijerina. Examination of Lane Change Crashes and PotentialIVHS [R]. National Highway Traffic Safety Administration,1994.
[2] B.Sultan, M.McDonald.The lane changing process: data analysis&modelingbehaviour.Traffic Engineering Control.2001,42(3):202-207.
[3]公安部交通管理局.中华人民共和国道路交通事故统计年报[R].北京:公安部交通管理局，2010.
[4]路明辉，任宇立.奥迪Q7驾驶辅助系统之换道辅助系统[J].整车电路，2008，10：25-31.
[5] P.G.Gipps.A Model for the structure of lane-changing decisions.Transportation ResearchPart B.1986:403-414.
[6]李迎峰，史忠科，周致纳．微观交通仿真中随机决策换道行为研究[J].系统仿真学报，2008，20(16)：4273-4277.
[7]刘小明，关淑辉．基于动态重复博弈的车辆换道模型[J]．公路交通科技，2008，25（6）：121-125.
[8]金立生，杨双宾，Mascha van der Voort,Martijn Tidema．高速公路汽车辅助驾驶安全换道模型[J].吉林大学学报(工学版)，2009，39(3)：582-586.
[9]杨双宾．高速公路车辆行驶安全辅助换道系统研究[D]．吉林大学，2008.
[10]黄秋菊.车道变换行为特性及其对交通安全影响的研究[D]．哈尔滨工业大学，2007.
[11]魏丽英，隽志才，田春林.驾驶员车道变换行为模拟分析[J].中国公路学报，2001，14（1）：77-80.
[12]谭春满.基于Agent与模糊逻辑的车辆换道仿真模型[J].系统工程学报，2007，22（1）：40-45.
[13]林广宇，魏朗.基于机器视觉的驾驶员换道行驶检测研究[J].计算机工程与应用，2009，45（33）：22-24.
[14]叶品，钟诚文，李兵强.基于快慢车辆主动换道特性的双车道元胞自动机模型研究[J].交通与计算机，2007，25（1）：86-89.
[15]林旸，蒋珉，柴干.基于模糊控制的微观车辆换道模型的研究及仿真[J].计算机技术与发展，2009，19（11）：250-253.
[16]张发，宣慧玉，赵巧霞.基于有限状态自动机的车道变换模型[J].中国公路学报，2008,21（3）：97-100.
[17]杨小宝，张宁,黄留兵.通行能力仿真中的换道模型研究[J].公路交通科技，2007，24（5）：109-112.
[18]裴玉龙，张银.车道变换期望运行轨迹仿真[J].交通与计算机，2008，26(4)：68-71．
[19]裴玉龙，于涛．车道变换进程中驾驶员视点转移特性研究[J].交通信息与安全，2009，27（2）：92-95.
[20]霍克．城市道路驾驶员车道变换行为及注视转移特性研究[D]．长安大学，2010．
[21]邓海军，尹全军，胡记文,查亚兵.基于MEBN的战术意图识别[J].系统工程与电子技术，2010，32（11）：2374-2379.
[22]吴涛，王崇骏，谢俊元.基于部分可观测马尔可夫决策过程的网络入侵意图识别研究[J].南京大学学报自然科学版，2010，46(2)：122-130.
[23]李之棠，王莉，李东.一种新的在线攻击意图识别方法研究[J].小型微型计算机系统，2008，29(7)：1347-1352.
[24]储颖，肖献强，朱家诚.基于驾驶行为及意图的汽车主动安全技术研究[J].机械设计与制造，2011，1（1）：266-268.
[25]王英范，宁国宝，余卓平.乘用车驾驶员制动意图识别参数的选择[J].汽车工程，2011，33（3）：213-216.
[26]宗长富，王畅，何磊，郑宏宇.基于双层隐式马尔可夫模型的驾驶意图辨识[J].汽车工程，2011，33(8)：701-706.
[27]王玉海，宋健，李兴坤．驾驶员意图与行驶环境的统一识别及实时算法[J].机械工程学报，2006，42（4）：206-212.
[28]郭孜政，陈崇双，王欣.基于贝叶斯判别的驾驶行为危险状态辨识[J].西南交通大学学报，2009，44(5)：771-774.
[29]张旭东.基于稀疏贝叶斯分类器的汽车车型识别[J].小型微型计算机系统，2005，26（10）：1839-1841.
[30]王晓原，杨新月，王晓辉，刘智平. D-S证据理论在驾驶行为决策中的应用[J].计算机工程与应用，2007，43（27）：230-233.
[31] Ioannis Golias, Mstthew, G.Karlaftis.An International Comparative Study ofSelf-report Driver Behavior [J].Transportation Research Part F.2002:243-246.
[32] Martin Lavallière, Nathan Ngan. Age-Related Deficits in the Frequency of GazeResponse to the Mirrors and Blind-Spot during Lane Change Maneuvers of VariousComplexities [J].2007Proceedings of the Fourth International Driving Symposium onHuman Factors in Driver Assessment, Training and Vehicle Design:373-380.
[33] Guihua Yang, Beverly Jaeger. Driving performance of novice and experienced drivers inlane-change scenarios [J]. Proceedings of the human factors and ergonomics society50th annual meeting (2006):2712-2716.
[34] Louis Tijerina, W. R. Garrott, M. Gleckler. Van and Passenger Car Driver Eye GlanceBehavior during the Lane Change Decision Phase [R]. NHTSA Vehicle Research andTest Center, East Liberty, Ohio, Nov.1997.
[35] Louis Tijerina, W. Riley Garrott. Eye glance behavior of van and passenger car driversduring lane change decision phase [J]. Journal of the Transportation Research Board(2005):37-43.
[36] Thomas Ayres, Li, Doris. Passenger-side Rear-view Mirror: Driver Behavior andSafety.International [J]. Journal of Industrial Ergonomics.2005,(35):157-162.
[37] Tony Wynn, John. Cognitive activity modeling: a case study of lane change schemas andsensation seeking [J]. European Conference on Human Centered Design for IntelligentTransport Systems (2008):177-285.
[38] Cooper, J. M., Vladisavljevic. Drivers’ Lane Changing Behavior While Conversing On aCell Phone in a Variable Density Simulated Highway Environment [J]. TransportationResearch Board January2008:2-12.
[39] Yoshihiro Nishiwaki, Chiyomi Miyajima, Norihide Kitaoka. Generating Lane-ChangeTrajectories of Individual Drivers [J]. Proceedings of the2008IEEE InternationalConference on Vehicular Electronics and Safety:271-275.
[40] W.van Winsum, D.de Waard, K.A.Brookhuis.Lane Change Manoeuvres and SafetyMargins [J].Transportation Research Part F1999(2):139-149.
[41] Liu A. What the driver’s eye tells the car’s brain? In: G. Under wood (Ed). Eye guidancein reading and scene perception [J]. England: Elsevier,1998:431-452.
[42] Dario D. Salvucci, Andrew Liu. The time course of a lane change: Driver control andeye-movement behavior [J]. Transportation Research Part F5(2002):123-132.
[43] Matthias J. Henning, Olivier georgeon, Josef F.krems. The quality of behavioral andenvironmental indicators used to infer the intention to change lanes [J]. TransportationResearch Part F4(2001):1-7.
[44] V.Bhise, J.Meldrum, D. Jack, G.Troell, D.Hoffmeister, and L.Forbes. Driver headmovements in left outside mirror viewing [J]. Society of Autmotive Engineers, no.810761,1981.
[45] F. Lethaus, J. Rataj. Do eye movements reflect driving maneuvers [J]? IETIntell.September2007,1(3):199–204.
[46] N. Kuge, T. Yamamura, O. Shimoyama, A. Liu. A Driver Behavior Recognition MethodBased on a Driver Model Framework [J]. SAE Technical Paper,2000-01-0349.
[47] Andrew Liu, Alex pretend. Towards real-time recognition of driver intentions[J].Intelligent Transportation System,1997, IEEE Conference, Boston, MA:236-241.
[48] Huiping Zhou, Makoto Itoh, Toshiyuki Inagaki. How Do Cognitive Distraction AffectDriver Intent of Changing Lanes [J]. M. Xie et al.(Eds.): ICIRA2009:235-244,2009.
[49] Huiping Zhou, Makoto Itoh, Toshiyuki Inagaki. Influence of cognitively distractingactivity on driver's eye movement during preparation of changing lanes [J]. SICEAnnual Conference2008:866~871.
[50] Aris Polychronopoulos, Christos Koutsimanis, Manolis Tsogas, Angelos Amditis.Prediction of Unintentional Lane Departure Using Evidence Theory [J].20057thInternational Conference on Information Fusion:1396-1403.
[51] JoelC.MeCal, DavidRWIPf. Lane change Intent Analysis Using Robust Operators andSparse Bayesian Learning [J].IEEE Intelligent Transportation Systems,2007,8(3):431-440.
[52] Erik C. B. Olsen, Suzanne E. Lee, Walter W.Wierwille. Eye glance behavior during lanechanges and straight-ahead driving [J]. Transportation Research Board of the NationalAcademies, Washington, D.C.,2005:44–50.
[53] Eui Yoon Chung, Ho Choul Jung, Eugene Chang, and In Sik Lee. Vision Based for LaneChange Decision Aid System [J]. Strategic Technology, the1st International Forum2006:10-13.
[54] M.Ruder, Highway Lane Change Assistant, IEEE International Conference onIntelligent Vehicle,2000:17-22.
[55] Yiguang Xuan，Benjamin Coifman. Lane Change Maneuver Detection from ProbeVehicle DGPS Data [J].2006IEEE Intelligent Transportation Systems Conference inToronto:624-629.
[56] Nuria Oliver, Alex P. Pentland. Graphical Models for Driver Behavior Recognition in aSmart Car [J]. Proceedings of the lEEE Intelligent Vehicles Symposium2000:7-12.
[57] Suzanne E. Lee, Erik C.B. Olsen, Walter W. Wierwille. A Comprehensive Examination ofNaturalistic Lane-Changes [R]. Virginia Tech Transportation Institute, March2004.
[58] M. Fitch, J. Hankey, J. Sudweeks, and T. Dingus. Analysis of Lane-Change Crashes andNear-Crashes [R]. Virginia Tech Transportation Institute, June2009.
[59] Raymond J. Kiefer, Jonathan M. Hankey. Lane change behavior with a side blind zonealert system [J]. Accident Analysis and Prevention40(2008):683–690.
[60] Rafael Toledo-Moreo. IMM-Based Lane-Change Prediction in Highways With Low-CostGPS/INS [J]. IEEE transactions on intelligent transportation systems,2009,10(1):180-185.
[61] Nobuyuki Kuge, Hiroshi Ueno, Hideaki Ichikawa, Kiyoshi Ochiai.A Study on the Causesof Rear-end Collision Based on an Analysis of Driver Behavior [J]. JSAR Review,1995,(16):55-60.
[62] Worrall R D, Bullen A G R. An empirical analysis of lane changing on multilanehighways[R]. Washington: Highway Research Board.
[63]杨建国，王金梅，李庆丰，王兆安.微观仿真中车辆换道的行为分析和建模[J].公路交通科技，2004，21（11）：93-97.
[64]金艳秋.基于模拟实验的驾驶员期望车速模型研究[D].昆明理工大学，2009.
[65]王晓原，邢丽，吴芳.基于决策树模型的驾驶员期望车速[J].计算机应用，2009，29（12）：318-321.
[66]郑安文.期望车速的意义及其影响因素分析[J].武汉科技大学学报（自然科学版），2005，28(1)：61-64.
[67]徐杰，杜文.跟随车安全距离的分析[J].交通运输工程学报，2002，2(1)：101-104.
[68]杨伟，徐杰，李宗平.高速公路上跟随车安全距离的一种确定方法[J].四川工业学院学报，2002，21(1)：20-22.
[69] Peng Jin-shuan. Research of Lane Change Decision Based on Drivers’Perception-Judgment and Game Theory [J].3rd International Conference on PowerElectronics and Intelligent Transportation System,2010,(6):5-9.
[70]彭金栓，付锐，石磊磊，张琼.驾驶人车道变换决策分析[J].武汉理工大学学报，2011，33(12)：46-50.
[71] HIDAS P. Modeling lane changing and merging in microscopic traffic simulation[J].Transportation Research Part C,2002,10(5):351-371.
[72]周立军.基于驾驶员信息处理特性的跟驰及换道模型研究[D].吉林大学，2008.
[73] C.Altavilla, L.Luini, p.Sloriglia. Social learning in market game [J]. Journal of EconomicBehavior&Organization,2006,61:632-652.
[74]彭金栓，付锐，郭应时，袁伟.基于有限零和灰色博弈的车道变换决策分析[J].科技导报，2011，29（3）：52-56.
[75] Von Neumann, O.Morgenstrn. Theory of Games and Economic Behavior. PrincetonUniversity Press,1944.
[76]罗党.灰色决策问题的分析方法研究[D].南京：南京航空航天大学，2004.
[77] M.Dietze, D.Ebersbach, CH.Lippold. Road Geometry, Driving Behaviour and RoadSafety[R].Road Infrastructure Safety Protection-Core Research and Development forRoad Safety in Europe,2008.
[78] Seeing Machines. http://www.seeingmachines.com.
[79] Hanowski, Wierwille, Garness. A field evaluation of safety issues in local/short haultrucking. In Proceedings of the XIVth Triennial Congress of the InternationalErgonomics Association and44th Annual Meeting of the Human Factors andErgonomics Society. Santa Monica, CA: Human Factors and Ergonomics Society,2000(3):365-368.
[80] Erik C. B. Olsen. Modeling Slow Lead Vehicle Lane Changing [D]. Doctor ofphilosophy in industrial and systems engineering, Virginia polytechnic institute and stateuniversity,2003.
[81] http://tool.chinaz.com/Tools/unixtime.aspx.
[82] Torbj rn Falkmer, Nils Petter Gregersen．Fixation patterns of learner drivers with andwithout cerebral palsy (CP) when driving in real traffic environments[J]． Transportation Research Part F,2001,4(3):171-185.
[83] David Crundall, Geoffrey Underwood．Effects of experience and processing demands onvisual information acquisition in drivers [J]． Ergonomics,1998,41(4):448-458.
[84] Geoffrey Underwood, Peter Chapman, Neil Brocklehurst, Jean Underwood, DavidCrundall． Visual attention while driving: sequences of eye fixations made byexperienced and novice drivers [J]． Ergonomics,2003,46(6):629-646.
[85] Albrecht W. Inhoff，Matthew S. Solomon，Bradley A. Seymour，Ralph Radach. Eyeposition changes during reading fixations are spatially selective [J]. Vision research，2007，48（26）：1027-1039.
[86]白志锋.最小角定理及其它[J].数学大世界，2002（Z1）：12-13.
[87]袁伟.城市道路环境中汽车驾驶员动态视觉特性试验研究[D].长安大学，2008.
[88] Underwood Geoffrey, Crundall David, Chapman Peter. Selective searching while driving:the role of experience in hazard detection and general surveillance [J]. Ergonomics,2002,45（1）:1-12.
[89] Bao Shan, Boyle Linda Ng. Age-related differences in visual scanning at median-dividedhighway intersections in rural areas [J]. Accident Analysis&Prevention,2009,41（1）:146-152.
[90]刘次华.随机过程[M].武汉：华中科技大学出版社，2001.
[91]刘建民．随机过程[M]．西安：西北大学出版社，2004.
[92] Geoffrey Underwood, Peter Chapman, Karen Bowden, David Crundall. Visual searchwhile driving: skill and awareness during inspection of the scene [J].TransportationResearch Part F,2002,5(2):87-97.
[93] Peter Chapman, Geoffrey Underwood, Katharine Roberts．Visual search patterns intrained and untrained novice drivers [J]. Transportation Research Part F,2002,5(2):157-167.
[94] Trent W. Victor, Joanne L. Harbluk. Sensitivity of eye-movement measures to in-vehicletask difficulty [J]. Transportation Research Part F8(2005):167–190.
[95]方烈义，孙复川.眼一头运动协同中头部运动的双重模式控制[J].生理学报，1995，47(1)：45-53.
[96]黎清.方向盘转角与行车安全[J].河北农机，1999，（1）：15-16.
[97] Nakayama. Development of a steering entropy method for evaluating driver workload[C].1999Proceeding SAE International Congress and Exposition:1-10.
[98] Michael E. Rakauskas, Leo J. Gugerty, Nicholas J. Ward. Effects of naturalistic cellphone conversations on driving performance [J]. Journal of Safety Research,2004,35:453–464.
[99] Minderhoud, M.M.and Bovy, P.H.L. Extended time-to-collision measures for road trafficsafety assessment.Acc.Anal.Prev.33,2001:89-97.
[100] Hirst, S.and Graham, R.The format and presentation of collision warnings [J].Ergonomics and safety of Intelligent Driver Interfaces,1997.
[101] ANAND S S, BELL D A. A general framework for data mining based on evidencetheory [J].Data&Knowledge Engineering,1996,18:189-223.
[102] Shafer G.A mathematical theory of evidence[M].New Jersay：Princeton UniversityPress，1996．
[103] Jennie Pearce，Simon Ferrier. Evaluating the predictive performance of habitat modelsdeveloped using logistic regression [J]. Ecological Modelling,2000,133(3):225-245.
[104] Georg Heinze, Michael Schemper. A solution to the problem of separation in logisticregression [J]. Statistics in Medicine,2002,21(16):2409-2419.
[105] John D. Chovan, Louis Tijerina. Examination of Lane Change Crashes and PotentialIVHS [R]. National Highway Traffic Safety Administration,1994.