基于多视图协同交互技术的换道图谱构建与分类

龙彦; 黄建玲; 赵晓华; 李振龙

doi:10.3963/j.jssn.1674-4861.2022.01.013

基于多视图协同交互技术的换道图谱构建与分类

doi: 10.3963/j.jssn.1674-4861.2022.01.013

龙彦^1,,
黄建玲^{1, 2},
赵晓华^1, ,,
李振龙¹

1.
北京工业大学城市交通学院北京 100124
2.
北京市交通信息中心北京 100073

基金项目:

国家自然科学基金项目 61876011

详细信息

作者简介:
龙彦（1979—），博士研究生. 研究方向：驾驶行为及智能交通.E-mail: longyan@emails.bjut.edu.cn

通讯作者:
赵晓华（1971—），博士，教授. 研究方向：驾驶行为与交通安全. E-mail: zhaoxiaohua@bjut.edu.cn

中图分类号: U491.54
计量
- 文章访问数: 929
- HTML全文浏览量: 399
- PDF下载量: 31
- 被引次数: 0
出版历程
- 收稿日期: 2021-09-20
- 网络出版日期: 2022-03-31

Development and Classification of Lane-changing Graph Based on Multi-view Collaborative and Interactive Techniques

1.
College of Metropolitan Transportation, Beijing University of Technology, Beijing 100124, China
2.
Beijing Transportation Information Center, Beijing 100073, China

摘要

摘要:
为直观展示换道过程中驾驶人视觉感知与手脚操作的细节特征，研究了多视图协同可视化的换道图谱。采用驾驶模拟舱进行高速公路驾驶实验，提取换道过程相关指标数据。将平行坐标、计数图、柱状图与换道轨迹协同可视化以构建换道图谱。采用多视图交互技术对提取的40个换道过程进行分析，提出换道过程的合格区范围并以此将换道图谱分为合格、临界合格和不合格3类，并对不合格图谱进行致因分析。结果表明，合格、临界合格和不合格图谱的比例分别为10.00%、12.50%和77.50%。不合格图谱的转向盘转速、加速度、横向加速度的平均标准差（6.57°；0.91 m/s²；0.41 m/s²）都大于合格图谱的平均标准差（4.55°；0.34 m/s²；0.17 m/s²）。导致图谱不合格的主要因素是：驾驶人手的急速操作引起转向盘转动幅度过大、横向加速度过大；驾驶人脚的急速操作引起纵向加速度的变化幅度过大。换道图谱能够精准地对换道过程进行可视化分析与诊断，为驾驶人优化换道行为提供支撑。
- 智能交通 /
- 换道过程 /
- 换道图谱 /
- 多视图协同
Abstract:
This paper aims to intuitively display the details of drivers' visual perception and related driving behavior in the lane-changing process by developing a multi-view collaborative visualization-based lane-changing graph. Specifically, driving behavior data related to lane-changing process are extracted from a simulated expressway, which is carried out by a driving simulator. The lane-changing graph is developed by coordinating parallel coordinates, count diagram, and bar chart with lane-changing trajectory. Following the analysis of 40 data sets of lane-changing behavior using the multi-view technique and the criteria for qualified lane-changing area, the lane-changing behavior is then classified into"Qualified""Barely Qualified", and"Unqualified". Meanwhile, the reasons of the unqualified lane-changing processes are also studied. The results show that the proportions of"Qualified""Barely Qualified", and"Unqualified"processes are 10.00%, 12.50%, and 77.50% respectively. The average standard deviations of the turning speed of the steering wheel, acceleration, and lateral acceleration observed over the unqualified processes (6.57°; 0.91 m/s²;0.41 m/s²) are larger than those observed over the qualified processes (4.55°; 0.34 m/s²;0.17 m/s²). The reasons for showing unqualified processes are mainly twofold: excessive lateral acceleration due to a large turning angle of the steering wheel and excessive change of longitudinal acceleration due to inappropriate operation of the gas panel. In general, the lane-changing graph can analyze and diagnose the lane-changing process accurately, which can provide supports for optimizing driver behavior in the lane-changing process.
- intelligent transportation /
- lane-changing process /
- lane-changing graph /
- multi-view collaborative visualization

HTML全文

图 1 模拟器与仿真场景

Figure 1. The simulator and scenarios

下载: 全尺寸图片幻灯片

图 2 模式组合图

Figure 2. Pattern combination diagram

下载: 全尺寸图片幻灯片

图 3 换道图谱构架

Figure 3. The framework of lane changing

下载: 全尺寸图片幻灯片

图 4 直角坐标与平行坐标

Figure 4. Cartesian coordinates and parallel coordinates

下载: 全尺寸图片幻灯片

图 5 平行坐标

Figure 5. Parallel coordinates

下载: 全尺寸图片幻灯片

图 6 换道图谱

Figure 6. Lane changing graph

下载: 全尺寸图片幻灯片

图 7 换道图谱合格区

Figure 7. The qualified area of the lane change graph

下载: 全尺寸图片幻灯片

图 8 图谱示例

Figure 8. The examples of the lane change graph

下载: 全尺寸图片幻灯片

图 9 多视图交互

Figure 9. Multi-view interaction

下载: 全尺寸图片幻灯片

图 10 不同类型图谱

Figure 10. Different types of graphs

下载: 全尺寸图片幻灯片

表 1 转向盘操作的分类

Table 1. Classification of steering wheel operation

类别	转向盘旋转速度ω的分类
急速左转	98%分位数≤ω
缓慢左转	75%分位数≤ω < 98%分位数
保持不动	25%分位数≤ω < 75%分位数
缓慢右转	2%分位数≤ω < 25%分位数
急速右转	ω < 2%分位数

下载: 导出CSV

表 2 3类图谱的指标标准差

Table 2. The SD of the indexes of three types of graphs

指标	合格图谱	临界合格图谱	不合格图谱
转向盘转速标准差/(°)	4.55	5.27	6.57
油门踏板标准差/%	12.48	11.94	20.12
速度标准差/(km/h)	5.74	3.66	6.80
横向位置标准差/m	1.40	1.63	1.60
加速度标准差/(m/s²)	0.34	0.29	0.91
横向加速度标准差/(m/s²)	0.17	0.25	0.41
刹车踏板标准差/%	0.00	0.00	2.45

下载: 导出CSV

表 3 导致图谱不合格的异常指标数

Table 3. The number of abnormal indexes resulting in the unqualified

异常指标数	不合格图谱的数量	占所有不合格图谱的比例/%
2	4	12.90
3	9	29.03
4	10	32.26
5	3	9.68
6	3	9.68
7	1	3.23
8	1	3.23
9	0	0.00
10	0	0.00

下载: 导出CSV

表 4 临界合格和不合格图谱中异常指标的频繁项

Table 4. Frequent items of abnormal indexes in critical qualified and unqualified graphs

	指标	影响频率/%
频繁1项集	{转向盘角度}	63.89
	{手的急速操作}	63.89
	{横向加速度}	58.33
	{脚的急速操作}	55.56
	{加速度}	36.11
频繁2项集	{转向盘角度，手的急速操作}	55.56
	{转向盘角度，横向加速度}	44.44
	{横向加速度，手的急速操作}	41.67
	{手的急速操作、脚的急速操作}	36.11
	{脚的急速操作，转向盘角度}	33.33
频繁3项集	{转向盘角度，手的急速操作，横向加速度}	38.89
频繁3项集	{转向盘角度，手的急速操作，脚的急速操作}	30.56

下载: 导出CSV

参考文献(30)

[1]	谷新平, 韩云鹏, 于俊甫. 基于决策机理与支持向量机的车辆换道决策模型[J]. 哈尔滨工业大学学报, 2020, 52(7): 111-121. https://www.cnki.com.cn/Article/CJFDTOTAL-HEBX202007016.htm GU X P, HAN Y P, YU J F. Vehicle lane-changing decision model based on decision mechanism and support vector machine[J]. Journal of Harbin Institute of Technology, 2020, 52 (7): 111-121. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-HEBX202007016.htm
[2]	陆建, 李英帅. 车辆换道行为建模的回顾与展望[J]. 交通运输系统工程与信息, 2017, 17(4): 48-55. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201704008.htm LU J, LI Y S. Review and outlook of modeling of lane changing behavior[J]. Journal of Transportation Systems Engineering and Information Technology, 2017, 17(4): 48-55. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201704008.htm
[3]	KUMAR P, PERROLLAZ M, LEFEVRE S, et al. Learning-based approach for online lane change intention prediction[C]. 2013 IEEE Intelligent Vehicles Symposium(IV), Gold Coast, Australia: IEEE, 2013.
[4]	MANDALIA H M, SALVUCCI D D. Using support vector machines for lane-change detection[C]. The Human Factors & Ergonomics Society Annual Meeting, Orlando, FL, United states: Human Factors an Ergonomics Society Inc, 2005.
[5]	LIU L, XU G, SONG Z. Driver lane changing behavior analysis based on parallel Bayesian networks[C]. 6th International Conference on Natural Computation, Yantai, China: IEEE, 2010.
[6]	KUGE N, YAMAMURA T, SHIMOYAMA O, et al. A driver behavior recognition method based on a driver model framework[C]. SAE 2000 World Congres, Detroit, MI, United States: SAE International, 2000.
[7]	PENTLAND A, LIU A. Modeling and prediction of human behavior[J]. Neural Computation, 1999(11): 229-242.
[8]	王一男. 基于隐马尔科夫模型的驾驶员换道驾驶意图识别方法研究[D]. 长春: 吉林大学, 2020. WANG Y N. Drivers' lane changing intention recognition method research based on Hidden Markov Model[D]. Changchun: Jilin University, 2020. (in Chinese)
[9]	宗长富, 王畅, 何磊, 等. 基于双层隐式马尔科夫模型的驾驶意图辨识[J]. 汽车工程, 2011, 33(08): 701-706. https://www.cnki.com.cn/Article/CJFDTOTAL-QCGC201108013.htm ZONG C F, WANG C, HE L, et al. Driving intention recognition based on double-layer HMM[J]. Automoltive Engineering, 2011, 33(8): 701-706. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-QCGC201108013.htm
[10]	胡少伟. 基于驾驶意图识别的主动换道系统研究[D]. 北京: 清华大学, 2019. HU S W. Research on active lane changeSystem based on driving intention recognition[D]. Beijing: Tsinghua University, 2019. (in Chinese)
[11]	PENG J, GUO Y, FU R, et al. Multi-parameter prediction of drivers' lane-changing behaviour with neural network model[J]. Applied Ergonomics, 2015(50): 207-217.
[12]	WIRTHMUELLER F, KLIMKE M, SCHLECHTRIEMEN J, et al. Predicting the time until a vehicle changes the lane using LSTM-based Recurrent Neural Networks[J]. IEEE Robotics and Automation Letters, 2021, 6(2): 2357-2364. doi: 10.1109/LRA.2021.3058930
[13]	GEBERT P, ROITBERG A, HAURILET M, et al. End-to-end prediction of driver intention using 3D convolutional neural networks[C]. 2019 IEEE Intelligent Vehicles Symposium (IV), Paris, France: IEEE, 2019.
[14]	GIPPS P. G. A model for the structure of lane-changing decisions[J]. Transportation Research Part B: Methodological. 1986, 20(5): 403-414. doi: 10.1016/0191-2615(86)90012-3
[15]	HUNT G J, LYONS D G. Modelling dual carriageway lane changing using neural networks[J]. Transportation Research Part C: Emerging Technologies, 1994, 2(4): 231-245. doi: 10.1016/0968-090X(94)90012-4
[16]	房哲哲. 基于深度学习的换道行为建模与分析[D]. 北京: 北京交通大学, 2018. FANG Z Z. Modeling and analysis of the lane-changing behavior through deep learning[D]. Beijing: Beijing Jiaotong University, 2018. (in Chinese)
[17]	MORIDPOUR S, SARVI M, ROSE G, et al. Lane-changing decision model for heavy vehicle drivers[J]. Journal of Intelligent Transportation Systems: Technology, Planning, and Operations, 2012, 16(1): 24-35. doi: 10.1080/15472450.2012.639640
[18]	许伦辉, 倪艳明, 罗强, 等. 基于最小安全距离的车辆换道模型研究[J]. 广西师范大学学报(自然科学版), 2011, 29 (4): 1-6. doi: 10.3969/j.issn.1001-6600.2011.04.001 XU L H, NI Y M, LUO Q, et al. Lane-changing model based on minimum safety distance[J]. Journal of Guangxi Normal University: Natural Science Edition, 2011, 29(4): 1-6. (in Chinese) doi: 10.3969/j.issn.1001-6600.2011.04.001
[19]	刘晨强. 车辆轨迹数据与换道行为特性研究[D]. 北京: 北京工业大学, 2018. LIU C Q. Research on vehicle trajectory the characteristics of lane-changing behavior[D]. Beijing: Beijing University of Technology, 2018. (in Chinese)
[20]	伍毅平. 生态驾驶行为特征甄别及反馈优化方法研究[D]. 北京: 北京工业大学, 2017. WU Y P. Research on eco-driving behavior characteristics identification and feedback optimization method[D]. Beijing: Beijing University of Technology, 2017. (in Chinese)
[21]	WANG W, ZHANG W, GUO H, et al. A safety-based approaching behavioural model with various driving characteristics[J]. Transportation Research Part C: Emerging Technologies, 2011, 19(6): 1202-1214. doi: 10.1016/j.trc.2011.02.002
[22]	刘畅, 亓航, 陈晨. 基于安全驾驶行为风险特征的图谱表达方法[J]. 交通工程, 2019, 19(6): 13-18. https://www.cnki.com.cn/Article/CJFDTOTAL-DLJA201906003.htm LIU C, QI H, CHEN C. Graph expression method based on risk characteristics of safedriving behavior[J]. Journal of Transportation Engineering, 2019, 19(6): 13-18. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DLJA201906003.htm
[23]	伍毅平, 赵晓华. 基于图谱的个体驾驶行为特征描述方法研究[J]. 交通工程, 2018, 18(1): 13-17. https://www.cnki.com.cn/Article/CJFDTOTAL-DLJA201801003.htm WU Y P, ZHAO X H. A graph based method to describe individual driving behavior[J]. Journal of Transportation Engineering, 2018, 18(1): 13-17. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DLJA201801003.htm
[24]	郑淑欣. 基于循环神经网络的车辆换道轨迹评价方法研究[D]. 北京: 北京工业大学, 2020. ZHENG S X. Research on evaluation method of lane-changing trajectory based on recurrent neural network[D]. Beijing: Beijing University of Technology, 2020.
[25]	李慧轩. 基于驾驶行为动态获取的换道行为微观建模及仿真校验研究[D]. 北京: 北京交通大学, 2016. LI H X. Research on microscopic modeling and simulation validation of lane changing behavior based on dynamic acquisition of driving behavior[D]. Beijing: Beijing Jiaotong University, 2016. (in Chinese)
[26]	龙彦, 黄建玲, 赵晓华. 换道过程中驾驶人感知操作的模式发现与规则挖掘[J]. 交通运输系统工程与信息, 2021, 21 (3): 237-246. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT202103030.htm LONG Y, HUANG J L, ZHAO X H. Pattern discovery and rule mining of drivers' per ception and operation during lane changing process[J]. Journal of Transportation Systems Engineering and Infomation Technology, 2021, 21(3): 237-246. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT202103030.htm
[27]	陈谊, 蔡进峰, 石耀斌, 等. 基于平行坐标的多视图协同可视分析方法[J]. 系统仿真学报, 2013, 25(1): 81-86. https://www.cnki.com.cn/Article/CJFDTOTAL-XTFZ201301016.htm CHEN Y, CAI J F, SHI Y B, et al. Coordinated visual analytics method based on multiple views with parallel coordinates[J]. Journal of System Simulation, 2013, 25(1): 81-86. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-XTFZ201301016.htm
[28]	INSELBERG A. Parallel coordinates: A tool for visualizing multidimensional geometry[C]. The lst IEEE Conference on Visualization, San Francisco, CA, United States: IEEE, 1990
[29]	张信雪, 吕晓琪, 张继凯, 等. 基于平行坐标的航道规划可视化分析研究[J]. 海洋环境科学, 2019, 38(1): 84-88. https://www.cnki.com.cn/Article/CJFDTOTAL-HYHJ201901013.htm ZHANG X X, LYU X Q, ZHANG J K, et al. Visualization analysis of channel planning based on parallel[J]. Marine Environmental Science, 2019, 38(1): 84-88. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-HYHJ201901013.htm
[30]	孙玮. 基于平行坐标可视化的滑坡预报预警研究[D]. 武汉: 武汉大学, 2013. SUN W. Research on landslides early warning based on parallel coordinate visualization[D]. Wuhan: Wuhan University, 2013. (in Chinese)