安全切入场景下的驾驶人初始制动时刻分析
|
摘要
基于中国自然驾驶项目的China-FOT数据库,研究安全切入场景下的驾驶人制动响应,为研究自动驾驶功能在安全切入场景下的控制策略开发及测试评价提供参考。首先使用人工截取车载视频的方法初步筛选出266例安全切入场景工况,通过观看车载视频提取交通环境参数(包括光照条件、切入车辆切入方向、车辆类型、横向位置变化等)以及本车驾驶人制动响应等视频数据;通过自动截取CAN总线数据提取本车车速、加速度等车辆动力学参数;并使用MATLAB图像分析的方法估算两车相对速度、相对距离等图像处理结果。然后基于提取到的工况数据,分析驾驶人响应类型及分布,得出在前车安全切入场景下,本车驾驶人保持本车道行驶的响应行为占96.24%,保持本车道行驶且同时制动的响应比例为51.13%。因此,对前车安全切入时,本车驾驶人保持本车道行驶的同时采取制动响应的行为进行了更深入的研究,以提取的136例符合此响应行为的工况数据为基础,以THW(Time Headway)值作为表征参数分析驾驶人初始制动时刻特征。预设交通环境、切入车辆参数、本车参数中可能对THW值产生影响的因素,分析THW值在预设的影响因素下的分布情况,并使用皮尔逊相关性检验验证THW值与该因素的相关关系,最终确定切入车辆类型、两车相对车速及相对距离与THW值显著相关。最后使用以上显著影响因素的参数进行聚类分析,得到5种典型的安全切入场景下的制动工况。
Based on the China Field Operational Tests database collected from the natural driving project of China, this study investigated a driver's braking response in the safety cut-in scenario, providing a reference for the development of control strategy and test evaluation of the automated driving function in this scenario. First, 266 cases of cut-in scenario were selected by manual interception of video data. Traffic environment parameters(such as light conditions, cut-in direction, type and lateral position of cut-in vehicle, and so on) and the driver's braking response were recorded. Dynamic parameters of the subject vehicle, such as vehicle speed and acceleration, were extracted by automatically intercepting data from Controller Area Network(CAN). MATLAB image analysis was used to estimate the relative speed and relative distance between the cut-in vehicle and subject vehicle. Then, based on these data, the type and distribution of the driver's response were analyzed. It is observed that the response behavior of keeping the original lane accounts for 96.24%, and the response ratio of keeping the original lane and braking at the same time is 51.13%. Therefore, a more in-depth study was conducted on the behavior of braking response while keeping the vehicle in the lane based on the 136 cases of this response behavior, and the time headway(THW) was defined as an indicator of the driver's initial braking time. Then, the distribution characteristics of THW under different conditions, such as various traffic parameters as well as cut-in and subject vehicle parameters, have been analyzed. The Pearson correlation test was used to verify the correlation between THW and the other factors. It was confirmed that cut-in vehicle type, relative velocity, and relative distance are significantly correlated with the THW. Finally, the factors that were significantly influenced by THW were used for cluster analysis to obtain five typical braking conditions in the safety cut-in scenario.
Based on the China Field Operational Tests database collected from the natural driving project of China, this study investigated a driver's braking response in the safety cut-in scenario, providing a reference for the development of control strategy and test evaluation of the automated driving function in this scenario. First, 266 cases of cut-in scenario were selected by manual interception of video data. Traffic environment parameters(such as light conditions, cut-in direction, type and lateral position of cut-in vehicle, and so on) and the driver's braking response were recorded. Dynamic parameters of the subject vehicle, such as vehicle speed and acceleration, were extracted by automatically intercepting data from Controller Area Network(CAN). MATLAB image analysis was used to estimate the relative speed and relative distance between the cut-in vehicle and subject vehicle. Then, based on these data, the type and distribution of the driver's response were analyzed. It is observed that the response behavior of keeping the original lane accounts for 96.24%, and the response ratio of keeping the original lane and braking at the same time is 51.13%. Therefore, a more in-depth study was conducted on the behavior of braking response while keeping the vehicle in the lane based on the 136 cases of this response behavior, and the time headway(THW) was defined as an indicator of the driver's initial braking time. Then, the distribution characteristics of THW under different conditions, such as various traffic parameters as well as cut-in and subject vehicle parameters, have been analyzed. The Pearson correlation test was used to verify the correlation between THW and the other factors. It was confirmed that cut-in vehicle type, relative velocity, and relative distance are significantly correlated with the THW. Finally, the factors that were significantly influenced by THW were used for cluster analysis to obtain five typical braking conditions in the safety cut-in scenario.
引文
[1] WINKELBAUER M,EICHHORN A,SAGBERG F,et al.Naturalistic Driving [M].Berlin:Springer,2010.
[2] ABDELRAHMAN A,ABU-ALI N,HASSANEIN H S.Driver Behavior Classification in Crash and Near-crash Events Using 100-CAR Naturalistic Data Set [C] // IEEE.Proceedings of the 2018 Global Communications Conference.New York:IEEE,2018:1-6.
[3] WU J,XU H.Driver Behavior Analysis for Right-turn Drivers at Signalized Intersections Using SHRP 2 Naturalistic Driving Study Data [J].Journal of Safety Research,2017,63:177-185.
[4] AHLSTROM C,VICTOR T,WEGE C,et al.Processing of Eye/Head-tracking Data in Large-scale Naturalistic Driving Data Sets [J].IEEE Transactions on Intelligent Transportation Systems,2012,13 (2):553-564.
[5] BENMIMOUN M,PüTZ A,ZLOCKI A,et al.EuroFOT:Field Operational Test and Impact Assessment of Advanced Driver Assistance Systems:Final Results [C] // Springer.Proceedings of the FISITA 2012 World Automotive Congress.Berlin:Springer,2013,537-547.
[6] 杨敏明,王雪松,朱美新.基于自然驾驶实验的驾驶行为研究[J].交通与运输,2017,33(3):7-9.YANG Min-ming,WANG Xue-song,ZHU Mei-xin.Driving Behavior Research Based on Natural Driving Study [J].Traffic & Transportation,2017,33 (3):7-9.
[7] KUSANO K D,GABLER H C.Target Population for Intersection Advanced Driver Assistance Systems in the U.S.[J].SAE Paper 2015-01-1408.
[8] LEMMEN P,FAGERLIND H,UNSELT T,et al.Assessment of Integrated Vehicle Safety Systems for Improved Vehicle Safety [J].Procedia-Social and Behavioral Sciences,2012,48:1632-1641.
[9] LIU L,ZHU X,CHEN M,et al.A Systematic Scenario Typology for Automated Vehicles Based on China-FOT [R].New York:SAE,2018.
[10] SUN X,ZHU X,ZHANG K,et al.Automatic Detection Method Research of Incidents in China-FOT Database [C] // IEEE.Proceedings of the 2016 IEEE International Conference on Intelligent Transportation Systems.New York:IEEE,2016:754-759.
[11] 王雪松,李艳.基于自然驾驶数据的驾驶员变道特征分析[J].交通信息与安全,2016,34(1):17-22.WANG Xue-song,LI Yan.Characteristics Analysis of Lane Changing Behavior Based on the Naturalistic Driving Data [J].Journal of Transport Information and Safety,2016,34 (1):17-22.
[12] MA X,MA Z,ZHU X,et al.Driver Behavior Classification Under Cut-in Scenarios Using Support Vector Machine Based on Naturalistic Driving Data [J].SAE Paper 2019-01-0136.
[13] XIA L,ZHU X,MA Z.Analysis of Driver’s Behavior Under Following-go Scenario [J].SAE Paper 2019-01-1018.
[14] WANG W,ZHAO D,XI J,et al.Development and Evaluation of Two Learning-based Personalized Driver Models for Car-following Behavior [C] // IEEE.2017 American Control Conference.New York:IEEE,2017:1133-1138.
[15] SCHMIED R,OBEREIGNER G,WASCHL H.Analysis and Adaptive Estimation of Human Car Following Behavior for Advanced Driver Assistance Systems [J].SAE Paper 2017-01-0044.
[16] LIU R,ZHU X.Driving Data Distribution of Human Drivers in Urban Driving Condition [C] // IEEE.Proceedings of the 2017 IEEE International Conference on Intelligent Transportation Systems.New York:IEEE,2017:1-8.
[17] KIM S H,WANG J,GUENTHER D,et al.Analysis of Human Driver Behavior in Highway Cut-in Scenarios [J].SAE Paper 2017-01-1402.
[18] LIAO Y,WANG W,YU J,et al.Brake Behavior Analysis in Low-speed Vehicle Cut-in Condition [C] // SAE-China.Proceedings of the 16th Conference of Automotive Safety Technology.Hangzhou:SAE-China,2013:7-12.
[19] FENG Z,MA X,ZHU X,et al.Analysis of Driver Brake Behavior Under Critical Cut-in Scenarios [C] // IEEE.Proceedings of the 2018 IEEE Intelligent Vehicles Symposium (Ⅳ).New York:IEEE,2018:2054-2059.
[20] MA X,FENG Z,ZHU X,et al.Driver Risk Perception Model Under Critical Cut-in Scenarios [J].SAE Paper 2018-01-1626.
[21] MENG M,WANG Y.Tool Development and Quantitative Analysis for Naturalistic Left Turn Across Path/Opposite Direction (LTAP/OD) Driving Scenarios [D].Gothenburg:Chalmers University of Technology,2016.
[2] ABDELRAHMAN A,ABU-ALI N,HASSANEIN H S.Driver Behavior Classification in Crash and Near-crash Events Using 100-CAR Naturalistic Data Set [C] // IEEE.Proceedings of the 2018 Global Communications Conference.New York:IEEE,2018:1-6.
[3] WU J,XU H.Driver Behavior Analysis for Right-turn Drivers at Signalized Intersections Using SHRP 2 Naturalistic Driving Study Data [J].Journal of Safety Research,2017,63:177-185.
[4] AHLSTROM C,VICTOR T,WEGE C,et al.Processing of Eye/Head-tracking Data in Large-scale Naturalistic Driving Data Sets [J].IEEE Transactions on Intelligent Transportation Systems,2012,13 (2):553-564.
[5] BENMIMOUN M,PüTZ A,ZLOCKI A,et al.EuroFOT:Field Operational Test and Impact Assessment of Advanced Driver Assistance Systems:Final Results [C] // Springer.Proceedings of the FISITA 2012 World Automotive Congress.Berlin:Springer,2013,537-547.
[6] 杨敏明,王雪松,朱美新.基于自然驾驶实验的驾驶行为研究[J].交通与运输,2017,33(3):7-9.YANG Min-ming,WANG Xue-song,ZHU Mei-xin.Driving Behavior Research Based on Natural Driving Study [J].Traffic & Transportation,2017,33 (3):7-9.
[7] KUSANO K D,GABLER H C.Target Population for Intersection Advanced Driver Assistance Systems in the U.S.[J].SAE Paper 2015-01-1408.
[8] LEMMEN P,FAGERLIND H,UNSELT T,et al.Assessment of Integrated Vehicle Safety Systems for Improved Vehicle Safety [J].Procedia-Social and Behavioral Sciences,2012,48:1632-1641.
[9] LIU L,ZHU X,CHEN M,et al.A Systematic Scenario Typology for Automated Vehicles Based on China-FOT [R].New York:SAE,2018.
[10] SUN X,ZHU X,ZHANG K,et al.Automatic Detection Method Research of Incidents in China-FOT Database [C] // IEEE.Proceedings of the 2016 IEEE International Conference on Intelligent Transportation Systems.New York:IEEE,2016:754-759.
[11] 王雪松,李艳.基于自然驾驶数据的驾驶员变道特征分析[J].交通信息与安全,2016,34(1):17-22.WANG Xue-song,LI Yan.Characteristics Analysis of Lane Changing Behavior Based on the Naturalistic Driving Data [J].Journal of Transport Information and Safety,2016,34 (1):17-22.
[12] MA X,MA Z,ZHU X,et al.Driver Behavior Classification Under Cut-in Scenarios Using Support Vector Machine Based on Naturalistic Driving Data [J].SAE Paper 2019-01-0136.
[13] XIA L,ZHU X,MA Z.Analysis of Driver’s Behavior Under Following-go Scenario [J].SAE Paper 2019-01-1018.
[14] WANG W,ZHAO D,XI J,et al.Development and Evaluation of Two Learning-based Personalized Driver Models for Car-following Behavior [C] // IEEE.2017 American Control Conference.New York:IEEE,2017:1133-1138.
[15] SCHMIED R,OBEREIGNER G,WASCHL H.Analysis and Adaptive Estimation of Human Car Following Behavior for Advanced Driver Assistance Systems [J].SAE Paper 2017-01-0044.
[16] LIU R,ZHU X.Driving Data Distribution of Human Drivers in Urban Driving Condition [C] // IEEE.Proceedings of the 2017 IEEE International Conference on Intelligent Transportation Systems.New York:IEEE,2017:1-8.
[17] KIM S H,WANG J,GUENTHER D,et al.Analysis of Human Driver Behavior in Highway Cut-in Scenarios [J].SAE Paper 2017-01-1402.
[18] LIAO Y,WANG W,YU J,et al.Brake Behavior Analysis in Low-speed Vehicle Cut-in Condition [C] // SAE-China.Proceedings of the 16th Conference of Automotive Safety Technology.Hangzhou:SAE-China,2013:7-12.
[19] FENG Z,MA X,ZHU X,et al.Analysis of Driver Brake Behavior Under Critical Cut-in Scenarios [C] // IEEE.Proceedings of the 2018 IEEE Intelligent Vehicles Symposium (Ⅳ).New York:IEEE,2018:2054-2059.
[20] MA X,FENG Z,ZHU X,et al.Driver Risk Perception Model Under Critical Cut-in Scenarios [J].SAE Paper 2018-01-1626.
[21] MENG M,WANG Y.Tool Development and Quantitative Analysis for Naturalistic Left Turn Across Path/Opposite Direction (LTAP/OD) Driving Scenarios [D].Gothenburg:Chalmers University of Technology,2016.