基于自然驾驶数据的城市交叉口纵向驾驶特征分析

doi:10.19562/j.chinasae.qcgc.2022.06.003

摘要/Abstract

摘要：

为满足驾驶辅助系统在城市交叉口对类人驾驶能力的更高需求，本文中研究了实际交通中的驾驶人在该区域的纵向驾驶行为特征。从自然驾驶数据中提取了778条驾驶人接近城市交叉口的样本数据，应用YOLOv4识别了交通场景中的各类道路使用者，采用方差分析研究了反应特性在不同运动类型和交通密度中的差异，建立分层回归模型分析了制动特性与运动状态、运动类型和道路使用者的关系。结果表明：高密度交通显著降低接近速度；与右转驾驶人相比，停车驾驶人的反应距离更长；当接近速度较高或反应距离较短时，会在更短的时间内以更高的减速度和制动强度接近交叉口，且提前4.46 s开始制动；不同道路使用者对制动特性产生了不同影响，停车驾驶人主要关注同向行驶的他车，右转驾驶人主要关注行人和骑车人。

关键词: 城市交叉口, 驾驶行为, 方差分析, 分层回归, 自然驾驶数据, 类人驾驶

Abstract:

In order to meet the higher requirements of driver assistance systems for human-like driving ability in urban intersection， the longitudinal driving characteristics of drivers in real traffic in that area are investigated in this paper. 778 sample data of drivers approaching urban intersections are extracted from natural driving data， and YOLOv4 is applied to identifying various types of road users in traffic scene. ANOVA is used to investigate the differences in reaction characteristics across motion types and traffic densities， and hierarchical regression models are established to analyze the relationships between braking characteristics and motion state， motion type and road users. The results show that high-density traffic significantly reduces approaching speed. Compared with right-turning drivers， stopping drivers have longer reaction distance and may approach intersection with higher acceleration and braking intensity in a shorter time with braking started 4.46s earlier when approach speed is higher or reaction distance is shorter. Different road users have different effects on braking characteristics： stopping drivers primarily pay attentions to the vehicles traveling in the same direction， and right-turning drivers are mainly concerned with pedestrians and cyclists.

Key words: urban intersections, driving behavior, ANOVA, hierarchical regression, natural driving data, human-like driving

袁田,赵轩,刘瑞,余强,朱西产,王姝. 基于自然驾驶数据的城市交叉口纵向驾驶特征分析[J]. 汽车工程, 2022, 44(6): 821-830.

Tian Yuan,Xuan Zhao,Rui Liu,Qiang Yu,Xichan Zhu,Shu Wang. An Analysis on Longitudinal Driving Characteristics in Urban Intersection Based on Natural Driving Data[J]. Automotive Engineering, 2022, 44(6): 821-830.

图/表 3

参考文献 28

1	HARTWICH F， BEGGIATO M， KREMS J F. Driving comfort， enjoyment and acceptance of automated driving-effects of drivers' age and driving style familiarity［J］. Ergonomics， 2018，61：1017-1032.
2	NORDHOFF S， AREM B V， HAPPEE R. A conceptual model to explain， predict， and improve user acceptance of driverless vehicles［J］. Transportation Research Record： Journal of the Transportation Research Board， 2016， 2602（1）：60-67.
3	DELIGIANNI S P， QUDDUS M， MORRIS A， et al. Analyzing and modeling drivers' deceleration behavior from normal driving［J］. Transportation Research Record： Journal of the Transportation Research Board， 2017， 2663（1）：134-141.
4	LI S， LI P， YAO Y， et al. Analysis of drivers' deceleration behavior based on naturalistic driving data［J］. Traffic Injury Prevention， 2020， 21（12）：1-6.
5	MERAT N， LEE J D. Preface to the special section on human factors and automation in vehicles： designing highly automated vehicles with the driver in mind［J］. Human Factors the Journal of the Human Factors and Ergonomics Society， 2012， 54（5）：681-686.
6	ANJANA S， ANJANEYULU M. Safety analysis of urban signalized intersections under mixed traffic［J］. J Safety Res， 2015， 52：9-14.
7	唐克双，谈超鹏，周楠. 基于轨迹数据的交叉口相位切换期间危险驾驶行为实证分析［J］. 中国公路学报， 2018， 31（4）：10.
	TANG K S， TAN C P， ZHOU N. Empirical analysis of risky driving behaviors during the phase transition intervals at signalized intersection based on vehicle trajectory data［J］. China Journal of Highway and Transport， 2018， 31（4）： 10.
8	龙岩松，徐进，潘存书，等.基于实车驾驶数据的信号交叉口车辆运行特性［J］.科学技术与工程，2021，21（31）：13567-13573.
	LONG Y S， XU J， PAN C S， et al. Vehicle operating characteristics signalized intersections based on field driving data［J］. Science Technology and Engineering， 2021， 21（31）： 13567-13573.
9	SATO T， AKAMATSU M. Influence of traffic conditions on driver behavior before making a right turn at an intersection： analysis of driver behavior based on measured data on an actual road［J］. Transportation Research Part F：Traffic Psychology & Behavior， 2007， 10（5）：397-413.
10	THAPA R， HALLMARK S， ONEYEAR N. Braking behavior of major approach turning vehicles at rural two-way stop controlled intersections： a naturalistic driving study［J］. Traffic Injury Prevention，2020.
11	ONEYEAR N L， HALLMARK S L， WANG B. Evaluating the relationship between the driver and roadway to address rural intersection safety using the SHRP 2 naturalistic driving study data［J］. DOI： 10.15787/VTT1MW2P.2015.
12	WU J， XU H. Driver behavior analysis for right-turn drivers at signalized intersections using SHRP 2 naturalistic driving study data［J］. J Safety Res， 2017， 63：177-185.
13	BERNDT H， WENDER S， DIETMAYER K. Driver braking behavior during intersection approaches and implications for warning strategies for driver assistant systems［C］. Intelligent Vehicles Symposium. IEEE， 2007.
14	EL-SHAWARBY I， RAKHA H， AMER A， et al. Impact of driver and surrounding traffic on vehicle deceleration behavior at onset of yellow indication［J］. Transportation Research Record Journal of the Transportation Research Board， 2011， 2248（2248）：10-20.
15	GATES T J， NOYCE D A， LARACUENTE L， et al. Analysis of driver behavior in dilemma zones at signalized intersections［J］. Transportation Research Record， 2007， 2030（1）： 29-39.
16	HAAS R， INMAN V， DIXSON A， et al. Use of intelligent transportation system data to determine driver deceleration and acceleration behavior［J］. Transportation Research Record Journal of the Transportation Research Board， 2004， 1899（1899）：3-10.
17	WANG J， DIXON K K， LI H， et al. Normal deceleration behavior of passenger vehicles at stop sign-controlled intersections evaluated with in-vehicle global positioning system data［J］. Transportation Research Record Journal of the Transportation Research Board， 2005， 1937（1937）：120-127.
18	BAO S， BOYLE L. Driver performance at two-way stop-controlled intersections on divided highways［J］. Transportation Research Record Journal of the Transportation Research Board， 2008， 2069：26-32.
19	王雪松，杨敏明.基于自然驾驶数据的变道切入行为分析［J］.同济大学学报（自然科学版），2018，46（8）：1057-1063.
	WANG X S， YANG M M. Cut-in behavior analyses based on naturalistic driving data［J］. Journal of Tongji University （Natural Science）， 2018， 46（8）： 1057-1063.
20	GIRSHICK R. Fast r-cnn ［C］.Proceedings of the IEEE International Conference on Computer Vision. 2015： 1440-1448.
21	REN S， HE K， GIRSHICK R， et al. Faster R-CNN： towards real-time object detection with region proposal networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2016， 39（6）： 1137-1149.
22	LIU W， ANGUELOV D， ERHAN D， et al. Ssd： single shot multibox detector［C］.European Conference on Computer Vision. Springer， Cham， 2016： 21-37.
23	REDMON J， FARHADI A. YOLO9000： better， faster， stronger［C］.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017： 7263-7271.
24	BOCHKOVSKIY A， WANG C Y， LIAO H. YOLOv4： optimal speed and accuracy of object detection［J］. arXiv：2004.10934，2020.
25	LUO H， YANG Y， TONG B， et al. Traffic sign recognition using a multi-task convolutional neural network［J］. IEEE Transactions on Intelligent Transportation Systems， 2018：1100-1111.
26	ZHU Y， ZHANG C， ZHOU D， et al. Traffic sign detection and recognition using fully convolutional network guided proposals［J］. Neurocomputing， 2016， 214：758-766.
27	OUYANG W， ZHOU H， LI H， et al. Jointly learning deep features， deformable parts， occlusion and classification for pedestrian detection［J］. IEEE Transactions on Pattern Analysis & Machine Intelligence， 2017：1-1.
28	SANG J， WU Z， GUO P， et al. An improved YOLOv2 for vehicle detection［J］. Sensors， 2018， 18（12）.

[1]	赵霞,李朝,付锐,葛振振,王畅. 基于深度卷积-Tokens降维优化视觉Transformer的分心驾驶行为实时检测[J]. 汽车工程, 2023, 45(6): 974-988.
[2]	金立生,纪丙东,郭柏苍. 基于多层时空融合网络的驾驶人注意力预测[J]. 汽车工程, 2023, 45(5): 759-767.
[3]	张斌,付俊怡,夏金祥. 基于类间距优化的分心驾驶行为识别模型训练方法[J]. 汽车工程, 2022, 44(2): 225-232.
[4]	宋东鉴,朱冰,赵健,韩嘉懿,刘彦辰. 基于驾驶行为生成机制的智能汽车类人行为决策[J]. 汽车工程, 2022, 44(12): 1797-1808.
[5]	朱冰,孙宇航,赵健,张培兴,范天昕,宋东鉴. 自动驾驶汽车测试场景基元自动提取方法[J]. 汽车工程, 2022, 44(11): 1647-1655.
[6]	郭景华,肖宝平,王靖瑶,罗禹贡,陈涛,李克强. 基于Residual BiLSTM网络的车辆切入意图预测研究[J]. 汽车工程, 2021, 43(7): 971-977.
[7]	袁伟,杨国松,付锐,张智,张康康. 驾驶人抑制控制对风险驾驶行为的影响研究[J]. 汽车工程, 2021, 43(4): 601-609.
[8]	郭景华, 李克强, 王进, 陈涛, 李文昌, 王班. 基于危险场景聚类分析的前车随机运动状态预测研究^*[J]. 汽车工程, 2020, 42(7): 847-853.