基于轨迹数据的高速公路小客车异常驾驶行为

doi:10.13229/j.cnki.jdxbgxb.20221504

摘要/Abstract

摘要：

为了分析不同异常驾驶行为带来的事故可能性与风险性，量化不同驾驶行为下加减速度的阈值大小，基于车辆的轨迹数据分析了速度与加速度的交互关系。采用回归的方式对速度与加速度的函数关系进行标定，构建了异常驾驶行为的数学判断模型。结果表明，在对应的速度区间内，加速度均值与1倍标准差的和可以作为一般异常行为判断阈值，此范围驾驶员存在产生风险的可能性；加速度均值与2倍标准差的和可以作为极端异常行为的判断阈值，此范围驾驶员已存在一定的风险，需要进行特定的管控。该模型克服了以往采用固定阈值的要求，能够实现实时动态的监控，为微观驾驶行为的研究提供了新方法。

关键词: 交通工程, 异常驾驶行为, 轨迹数据, 速度-加速度, 参数标定

Abstract:

In order to analyze the possibility and riskiness of accidents caused by different abnormal driving behaviors， quantify the threshold size of acceleration and deceleration under different driving behaviors. Based on the trajectory data of the vehicle， the interaction relationship between speed and acceleration was analyzed， and the function relationship between speed and acceleration was calibrated using regression， and finally the judgment model of different abnormal behaviors was constructed. The results show that the sum of the mean acceleration and 1 times the standard deviation can be used as the general abnormal behavior judgment threshold， in this range drivers have the potential to create risk and need to be reasonably alerted； The sum of the mean value of acceleration and 2 times the standard deviation can be used as the threshold for judging extreme abnormal behavior， in this range of drivers already has some risk and requires some control. The model overcomes the previous requirement of using fixed thresholds and allows for real-time dynamic monitoring of driving behavior， providing a new approach to the study of microscopic driving behavior.

Key words: traffic engineering, abnormal driving behavior, trajectory data, velocity-acceleration, parameter calibration

中图分类号:

U491

周荣贵,高沛,李雨璇,周建. 基于轨迹数据的高速公路小客车异常驾驶行为[J]. 吉林大学学报(工学版), 2024, 54(9): 2581-2587.

Rong-gui ZHOU,Pei GAO,Yu-xuan LI,Jian ZHOU. Abnormal driving behavior thresholds of highway minibuses based on trajectory data[J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(9): 2581-2587.

图/表 8

图1

图2

表1

图3

表2

图4

表3

图5

参考文献 20

1	郭孜政, 陈崇双, 闫伟, 等. 驾驶威胁感知评估方法[J]. 吉林大学学报:工学版, 2012, 42(1): 46-50.
	Guo Zi-zheng, Chen Chong-shuang, Yan Wei, et al. Assessment method for driving threat perception [J]. Journal of Jilin University (Engineering and Technology Edition), 2012, 42(1): 46-50.
2	Eboli L, Mazzulla G, Pungillo G, et al. Combining speed and acceleration to define car users' safe or unsafe driving behaviour[J]. Transportation Research Part C, Emerging Technologies, 2016, 68(7): 113-125.
3	马聪. 基于OBD技术的驾驶行为习惯评价方法研究[D]. 南京: 南京大学软件学院, 2016.
	Ma Cong. Study on the evaluation method of driving behavior habit based on OBD technology[D]. Nanjing: School of Software, Nanjing University, 2016.
4	丁琛. 基于车辆动态监控数据的异常驾驶行为识别技术研究[D]. 北京:北京交通大学电子信息工程学院, 2015.
	Ding Chen. Research of abnormal driving behavior recognition technology based on vehicle dynamic monitoring data[D]. Beijing: School of Electronic Information Engineering, Beijing Jiaotong University, 2015.
5	任慧君, 许涛, 李响. 利用车载GPS轨迹数据实现公交车驾驶安全性分析[J]. 武汉大学学报:信息科学版, 2014, 39(6): 739-744.
	Ren Hui-jun, Xu Tao, Li Xiang. Driving behavior analysis based on trajectory data collected with vehicle-mounted GPS receivers[J].Journal of Wuhan University (Information Science Edition),2014,39(6):739-744.
6	王伟, 赵琦, 王力, 等. 基于车辆轨迹数据的急减速驾驶行为判定方法[J]. 科学技术与工程, 2022, 22(10):4215-4221.
	Wang Wei, Zhao Qi, Wang Li,et al. Rapid deceleration driving behavior judgment method based on vehicle trajectory data[J]. Science, Technology and Engineering, 2022, 22(10):4215-4221.
7	赵建东, 陈溱, 焦彦利, 等. 重点营运车辆的异常驾驶行为识别研究[J]. 交通运输系统工程与信息, 2022, 22(1):282-291.
	Zhao Jian-dong, Chen Qin, Jiao Yan-li, et al. Recognition of abnormal driving behavior of key commercial vehicle[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(1):282-291.
8	耿凯. 基于数据挖掘技术的出租车轨迹异常分析研究[D]. 西安:长安大学信息工程学院, 2018.
	Geng Kai. Research on abnormal trajectory detection of taxi based on data mining technology[D]. Xi'an: College of Information Engineering, Chang'an University, 2018.
9	杨龙海, 徐洪, 张春. 基于GPS数据的高速公路车辆异常行为检测[J]. 重庆交通大学学报:自然科学版, 2018, 37(5):97-103.
	Yang Long-hai, Xu Hong, Zhang Chun. Vehicle abnormal behavior detection on freeway based on global positioning system data[J]. Journal of Chongqing Jiaotong University (Natural Science Edition), 2018, 37(5):97-103.
10	Jiho Y, Jooyoung L, Kitae J. The effects of rainfall on driving behaviors based on driving volatility[J]. International Journal of Sustainable Transportation, 2020, 15(6):435-443.
11	严利鑫, 黄珍, 朱敦尧, 等. 基于马尔科夫毯和隐朴素贝叶斯的驾驶行为险态辨识[J]. 吉林大学学报:工学版, 2016, 46(6): 1851-1857.
	Yan Li-xin, Huang Zhen, Zhu Dun-yao, et al.Driving risk status identification based on markovblanket hidden naive bayes[J]. Journal of Jilin University (Engineering and Technology Edition), 2016, 46(6):1851-1857.
12	郭静. 基于深度学习的异常驾驶行为检测识别[D]. 西安:长安大学信息工程学院, 2021.
	Guo Jing. Detection and recognition of abnormal driving behavior based on deep learning[D]. Xi'an: College of Information Engineering, Chang'an University, 2021.
13	Xue Q W, Wang K, Lu J J, et al. Rapid driving style recognition in car following using machine learning and vehicle trajectory data[J]. Journal of Advanced Transportation, 2019, 2019(1):1-11.
14	Da Lio M, Biral F, Bertolazzi E. Combining safety margins and user preferences into a driving criterion for optimal control-based computation of reference manoeuvres for an ADAS of the next generation[J]. Intelligent Vehicles Symposium, Las Vegas, USA, 2005(6): 6-8.
15	Rosolino V, Teresa I, Vittorio A, et al. Driving behavior and traffic safety: an acceleration based safety evaluation procedure for smartphones[J]. Modern Applied Science, 2014, 8(1):88-96.
16	丁瑞, 刘俊, 蒋艳, 等.基于车辆加速度数据的互通立交匝道驾驶风险分析[J]. 交通信息与安全, 2021, 39(1):17-25.
	Ding Rui, Liu Jun, Jiang Yan, et al. Driving risks of interchange ramps based on vehicle acceleration data [J]. Transportation Information and Safety, 2021, 39(1):17-25.
17	Wang X, Asad J K, Liu J, et al. What is the level of volatility in instantaneous driving decisions?[J]. Transportation Research Part C, 2015, 58(9):413-427.
18	Behram W, Asad J K, Thomas K. Exploring microscopic driving volatility in naturalistic driving environment prior to involvement in safety critical events: concept of event-based driving volatility[J]. Accident Analysis and Prevention, 2019, 132(11):1-25.
19	Fu X, Nie Q F, Liu J, et al. Constructing spatiotemporal driving volatility profiles for connected and automated vehicles in existing highway networks[J]. Journal of Intelligent Transportation Systems, 2022, 26(5):572-585.
20	贺宜, 李继朴, 吴超仲. 一种基于车辆信息采集系统的驾驶风险评价特征画像方法[P].中国:29795980, 2022-04-23.

相关文章 15

[1]	张丽平,刘斌毓,李松,郝忠孝. 基于稀疏多头自注意力的轨迹kNN查询方法[J]. 吉林大学学报(工学版), 2024, 54(6): 1756-1766.
[2]	马庆禄,闫浩,聂振宇,李杨梅. 匝道合流区智能网联车辆协同控制方法[J]. 吉林大学学报(工学版), 2024, 54(5): 1332-1346.
[3]	秦雅琴,钱正富,谢济铭. 协同换道避障模型和轨迹数据驱动的车辆协同避障策略[J]. 吉林大学学报(工学版), 2024, 54(5): 1311-1322.
[4]	许清津,付锐,郭应时,吴付威. 载货汽车弯道侧翻路侧预测方法[J]. 吉林大学学报(工学版), 2024, 54(5): 1302-1310.
[5]	蒲云,徐银,刘海旭,谭一帆. 考虑多车影响的智能网联车跟驰模型[J]. 吉林大学学报(工学版), 2024, 54(5): 1285-1292.
[6]	曹倩,李志慧,陶鹏飞,李海涛,马永建. 面向交通事故检测及预防的异质传感器布设方法[J]. 吉林大学学报(工学版), 2024, 54(4): 969-978.
[7]	张鑫,胡启洲,何君,吴啸宇. 考虑交通梗塞的合流区交通状况诊断[J]. 吉林大学学报(工学版), 2024, 54(2): 478-484.
[8]	张卫华,刘嘉茗,解立鹏,丁恒. 网联混合环境快速路交织区自动驾驶车辆换道模型[J]. 吉林大学学报(工学版), 2024, 54(2): 469-477.
[9]	岳昊,张琦悦,杨子玉,任孟杰,张旭. 拥堵空间排队的静态交通流分配迭代加权算法[J]. 吉林大学学报(工学版), 2024, 54(1): 136-145.
[10]	杜筱婧,姚荣涵. 智能网联公交车出站强制换道的演化博弈机制[J]. 吉林大学学报(工学版), 2024, 54(1): 124-135.
[11]	马壮林,崔姗姗,胡大伟,王晋. 限行政策下传统小汽车出行者出行方式选择[J]. 吉林大学学报(工学版), 2023, 53(7): 1981-1993.
[12]	张雅丽,付锐,袁伟,郭应时. 考虑能耗的进出站驾驶风格分类及识别模型[J]. 吉林大学学报(工学版), 2023, 53(7): 2029-2042.
[13]	尹超英,陆颖,邵春福,马健霄,许得杰. 考虑空间自相关的建成环境对通勤方式选择的影响[J]. 吉林大学学报(工学版), 2023, 53(7): 1994-2000.
[14]	潘恒彦,王永岗,李德林,陈俊先,宋杰,杨钰泉. 基于交通冲突的长纵坡路段追尾风险评估及预测[J]. 吉林大学学报(工学版), 2023, 53(5): 1355-1363.
[15]	宋灿灿,荆迪菲,谢俊峰,康可心. 设置广告牌的高速公路平曲线路段驾驶行为分析[J]. 吉林大学学报(工学版), 2023, 53(5): 1345-1354.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

指标	范围	（mean +SD）/%	（mean +2SD）/%	（mean +3SD）/%
加速度/（m·s^-2）	极值外侧	12.68	4.37	1.68
加速度/（m·s^-2）	极值内侧	87.32	95.63	98.32
减速度/（m·s^-2）	极值内侧	87.20	95.42	98.22
减速度/（m·s^-2）	极值外侧	12.80	4.58	1.78

R²	mean+SD （加速度）	mean+SD （减速度）	mean+2SD （加速度）	mean+2SD （减速度）
线性	0.84	0.88	0.849	0.90
对数	0.80	-	0.80	-
二次	0.841	0.88	0.85	0.90
三次	0.90	0.93	0.91	0.94
指数	0.83	-	0.84	-

编号	实线内侧/%	实线-虚线之间/%	虚线外侧/%
1	87.6	8.1	4.3
2	86.0	9.5	4.5
3	88.5	7.9	3.6
4	85.9	9.47	4.63