共驾型智能车辆人机接管行为序列编码与解析

doi:10.13229/j.cnki.jdxbgxb.20221391

摘要/Abstract

摘要：

共驾型智能车辆同时具备人工驾驶和自动驾驶模式，其驾驶行为特性必将呈现新的特征。本文收集了15名被试人机接管的驾驶数据，采用符号聚合近似方法和视频录像标定法构建了驾驶行为特征图谱，通过最长公共子序列算法得出共通行为序列。结果表明，当车辆前方出现障碍物时，驾驶接管共通行为序列为：同时注视前方和制动踏板踩下-同时观察左后视镜和打开左转向灯-向左打方向盘-关闭左转向灯，该结论有助于提高智能车辆接管的有效性。

关键词: 交通运输系统工程, 人机接管, 驾驶行为, 时间序列符号聚合近似方法, 图谱

Abstract:

Co-driving autonomous vehicles have manual and automated driving mode. The driving behavior characteristics of co-driving autonomous vehicles will show new characteristics. The driving behavior data of 15 drivers are collected. The characteristic map of driving behavior is constructed by using symbol aggregation approximation method and video recording calibration method. The common behavior sequence of autonomous vehicle man-machine takeover is excavated based on longest common subsequence algorithm. The results show that when obstacles appear in front of the autonomous vehicle the common behavior sequence is： looking ahead and pressing the brake pedal - observing the left rearview mirror and turning on the left turn signal - turning the steering wheel to the left - closing left turn signal. This study may helpful to improve the effectiveness of autonomous vehicle takeover.

Key words: engineering of transportation and communication system, human-machine takeover, driving behavior, symbolic aggregate approximation, graph

中图分类号:

U491.1

严利鑫,曾涛,贺宜,郭军华,胡鑫辉. 共驾型智能车辆人机接管行为序列编码与解析[J]. 吉林大学学报(工学版), 2024, 54(9): 2547-2556.

Li-xin YAN,Tao ZENG,Yi HE,Jun-hua GUO,Xin-hui HU. Man-machine takeover behavior sequence coding and analysis of shared driving intelligent vehicle[J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(9): 2547-2556.

图/表 15

表1

部分数据表"

速度/（km·h^-1）	加速度/（m·s^-2）	油门踏板深度/%	制动踏板深度/%	…	驾驶状态
7.88	-0.35	0	0	…	1
$?$	$?$	$?$	$?$		$?$
29.55	5.81	0.67	0	…	0
34.75	3.22	0.67	0	…	0

表1

表2

表3

划分的字符数m从3到10的断点"

$β i$	$m$
$β i$	3	4	5	6	7	8	9	10
$β 1$	-0.43	-0.67	-0.84	-0.97	-1.07	-1.15	-1.22	-1.28
$β 2$	0.43	0	-0.25	-0.43	-0.57	-0.67	-0.76	-0.84
$β 3$		0.67	0.25	0	-0.18	-0.32	-0.43	-0.52
$β 4$			0.84	0.43	0.18	0	-0.14	-0.25
$β 5$				0.97	0.57	0.32	0.14	0
$β 6$					1.07	0.67	0.43	0.25
$β 7$						1.15	0.76	0.52
$β 8$							1.22	0.84
$β 9$								1.28

表3

图 1

图2

图3

表4

图4

表5

表6

表7

图5

表8

图6

图7

参考文献 20

1	Lotz A, Russwinkel N, Wohlfarth E. Take-over expectation and criticality in level 3 automated driving: a test track study on take-over behavior in semi-trucks[J]. Cognition Technology & Work, 2020, 22(4): 733-744.
2	倪定安, 郭凤香, 周燕宁. 无信号控制交叉口老年驾驶人转向行为图谱研究[J]. 交通信息与安全, 2022, 40(3): 108-117.
	Ni Ding-an, Guo Feng-xiang, Zhou Yan-ning. A graph study on turning behaviors of older drivers at unsignalized intersections[J]. Journal of Transport Information and Safety, 2022, 40(3): 108-117.
3	Cai H, Hu Z, Chen Z, et al. A driving fingerprint map method of driving characteristic representation for driver identification[J]. IEEE Access, 2018, 6: 71012-71019.
4	Balsa-Barreiro J, Valero-Mora P M, Berné-Valero J L, et al. GIS mapping of driving behavior based on naturalistic driving data[J]. International Journal of Geo-Information, 2019, 8(5): No.226.
5	万平, 吴超仲, 林英姿, 等. 基于驾驶行为多元时间序列特征的愤怒驾驶状态检测[J]. 吉林大学学报:工学版, 2017, 47(5): 1426-1435.
	Wan Ping, Wu Chao-zhong, Lin Ying-zi, et al. Driving anger detection based on multivariate time series features of driving behavior[J]. Journal of Jilin University (Engineering and Technology Edition), 2017, 47(5): 1426-1435.
6	严利鑫, 冯进培, 郭军华, 等. 不同险态情景下共驾型智能车辆接管行为特征分析[J].吉林大学学报: 工学版, 2024, 54(3): 683-691.
	Yan Li-xin, Feng Jin-pei, Guo Jun-hua, et al. Analysis of characteristics of the takeover behavior of co-driving intelligent vehicles under different dangerous scenarios[J]. Journal of Jilin University (Engineering and Technology Edition), 2024, 54(3): 683-691.
7	Peng H, Chen F, Chen P. Examining the effects of visibility and time headway on the takeover risk during conditionally automated driving[J]. International Journal of Environmental Research and Public Health, 2022, 19(21): No. 13904.
8	Yang S, Kuo J, Lenné M G. Effects of distraction in on-road level 2 automated driving: impacts on glance behavior and takeover performance[J]. Human Factors, 2021, 63(8): 1485-1497.
9	Li Y, Sun D, Zhao M, et al. MPC-based switched driving model for human vehicle co-piloting considering human factors[J]. Transportation Research Part C Emerging Technologies, 2020, 115: No.102612.
10	王彦峰, 陈浩林, 赵晓华, 等. 驾驶次任务沉浸等级对接管行为的影响分析[J]. 交通信息与安全, 2022, 40(1): 135-143.
	Wang Yan-feng, Chen Hao-lin, Zhao Xiao-hua, et al. A study on the impact of immersion levels of non-driving-related tasks on takeover behavior[J]. Journal of Transport Information and Safety, 2022, 40(1): 135-143.
11	孙川. 基于自然驾驶数据的车辆驾驶风险辨识及控制研究[D]. 武汉: 武汉理工大学交通与物流工程学院, 2016.
	Sun Chuan. Identification and control for driving risk of vehicle using naturalistic driving data[D]. Wuhan: School of Transportation and Logistics Engineering, Wuhan University of Technology, 2016.
12	Chen H, Feng S, Xin P, et al. Dangerous driving behavior recognition and prevention using an autoregressive time-series model[J]. Tsinghua Science and Technology, 2017, 22(6): 682-690.
13	衡红军, 刘静. 基于混合方法的多维时间序列驾驶异常点检测[J]. 计算机工程, 2020, 46(3): 99-104.
	Heng Hong-jun, Liu Jing. Driving outlier detection using multidimensional time series based on hybrid methods[J]. Computer Engineering, 2020, 46(3): 99-104.
14	Le X T, Tran T M, Nguyen H T. An improvement of SAX representation for time series by using complexity invariance[J]. Intelligent Data Analysis, 2020, 24(3): 625-641.
15	Zhao A, Chen R, Qi Y, et al. Evaluating the impact of criminalizing drunk driving on road-traffic injuries in guangzhou, China: a time-series study[J]. Journal of Epidemiology, 2016, 26(8): 433-439.
16	Hung N, Anh D T. An improvement of PAA for dimensionality reduction in large time series databases[C]∥Pacific Rim International Conference on Artificial Intelligence: Trends in Artificial Intelligence. Berlin: Springer-Verlag, 2008: 698-707.
17	孙川, 吴超仲, 褚端峰, 等. 基于SAX的车载数据时空语义编码及分析方法[J]. 公路交通科技, 2019, 36(8): 124-132.
	Sun Chuan, Wu Chao-zhong, Chu Duan-feng, et al. Space-time semantic coding for on-board data and analysis method based on SAX[J]. Journal of Highway and Transportation Research and Development, 2019, 36(8): 124-132.
18	吕超, 鲁洪良, 于洋, 等. 基于分层强化学习和社会偏好的自主超车决策系统[J]. 中国公路学报, 2022, 35(3): 115-126.
	Chao Lyu, Lu Hong-liang, Yu Yang, et al. Autonomous overtaking decision making system based on hierarchical reinforcement learning and social preferences[J]. China Journal of Highway and Transport, 2022, 35(3): 115-126.
19	Cunneen M, Mullins M, Murphy F. Autonomous vehicles and embedded artificial intelligence: the challenges of framing machine driving decisions[J]. Applied Artificial Intelligence, 2019, 33(8): 706-731.
20	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.
	Wu Yi-ping, Zhao Xiao-hua. A graph based method to describe individual driving behavior[J]. Journal of Transportation Engineering, 2018, 18(1): 13-17.

相关文章 15

[1]	周锡浈,宫贺,李敦敦,季彦婕,严杰. 建成环境对路内停车泊位使用率的非线性影响模型[J]. 吉林大学学报(工学版), 2024, 54(9): 2520-2530.
[2]	曲昭伟,李霖,陈永恒,吴场建. 长区间掉头车辆特性分析及其安全评价[J]. 吉林大学学报(工学版), 2024, 54(8): 2206-2213.
[3]	何永明,权聪,魏堃,冯佳,万亚楠,陈世升. 超高速公路车路协同路侧单元感知融合方法[J]. 吉林大学学报(工学版), 2024, 54(7): 1923-1934.
[4]	程国柱,盛林,王浩宇,冯天军. 考虑右转车二次冲突的信号交叉口行人过街安全评价方法[J]. 吉林大学学报(工学版), 2024, 54(7): 1903-1912.
[5]	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.
[6]	张明业,杨敏,黎彧,黄世玉,李清韵. 考虑有序充电策略的多车型电动公交调度优化[J]. 吉林大学学报(工学版), 2024, 54(5): 1293-1301.
[7]	陈仁祥,胡超超,胡小林,杨黎霞,张军,何家乐. 基于改进YOLOv5的驾驶员分心驾驶检测[J]. 吉林大学学报(工学版), 2024, 54(4): 959-968.
[8]	赵晓华,刘畅,亓航,欧居尚,姚莹,郭淼,杨海益. 高速公路交通事故影响因素及异质性分析[J]. 吉林大学学报(工学版), 2024, 54(4): 987-995.
[9]	金志刚,苏仁鋆,赵晓芳. 基于异质图网络的心理评估方法[J]. 吉林大学学报(工学版), 2024, 54(4): 1078-1085.
[10]	涂辉招,王万锦,乔鹏,郭静秋,鹿畅,吴海飞. 自动驾驶卡车路测安全员接管干预行为解析[J]. 吉林大学学报(工学版), 2024, 54(3): 727-740.
[11]	曲大义,张可琨,顾原,王韬,宋慧,戴守晨. 自动驾驶车辆换道决策行为分析及分子动力学建模[J]. 吉林大学学报(工学版), 2024, 54(3): 700-710.
[12]	严利鑫,冯进培,郭军华,龚毅轲. 不同险态情景下共驾型智能车辆接管行为特征分析[J]. 吉林大学学报(工学版), 2024, 54(3): 683-691.
[13]	姜文明,齐立忠,张苏,荣经国,武宏波,左超,张晓龙. 基于知识图谱的电网工程建筑信息模型质量检查方法[J]. 吉林大学学报(工学版), 2024, 54(3): 807-814.
[14]	马潇驰,陆建. 基于基因表达式编程的高架道路事故实时预测[J]. 吉林大学学报(工学版), 2024, 54(3): 719-726.
[15]	张健,李青扬,李丹,姜夏,雷艳红,季亚平. 基于深度强化学习的自动驾驶车辆专用道汇入引导[J]. 吉林大学学报(工学版), 2023, 53(9): 2508-2518.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

驾驶操作	基本元素	驾驶操作	基本元素
注视前方	A	向左打转向盘	E₁
观察左后视镜	B₁	向右打转向盘	E₂
观察右后视镜	B₂	左转向灯开启	F₁
油门踏板踩下	C₁	左转向灯关闭	F₂
油门踏板松开	C₂	右转向灯开启	G₁
制动踏板踩下	D₁	右转向灯关闭	G₂
制动踏板松开	D₂	按喇叭	H

参数	降维后的长度N	字符数m	符号化编码
速度	15	4	caaaabccddddcbb
加速度	15	4	aaccdcdcdcababb
油门踏板深度	9	4	abdddbaa
制动踏板深度	9	4	dbbbbbbb
角速度	7	3	cabbbb
前轮转角	15	4	bbccdddcaaaaccc
角加速度	9	3	cabcbaba

车辆运动行为	Sig.（双侧）	相关系数
速度	0.000	0.537^**
加速度	0.000	-0.503^**
油门踏板深度	0.315	0.120
制动踏板深度	0.000	0.634^**
俯仰角	0.193	0.026
前轮转角	0.026	-0.468
横摆角速度	0.542	0.008

被试者序号	车辆运动指标
被试者序号	速度	加速度	制动踏板深度
1	daaaabccccddd	bbbcccccdddaa	ddbbbbbbb
2	dbaaabcddccc	aabcdddcbacc	ddbbbbbb
3	dbaaabdddcbcc	aabcdddbaaccc	dcbbbbbbb
4	daaabcdddcbbcc	aacccdcabbccdc	dcbbbbbbb
5	dcaaabcddcb	aabcccddbbc	dbbbbbb
6	daaabdddcbcc	aaccddbbbcdd	dbbbbbbb
7	caaaabcddddd	aaccccdddabb	dcbbbbbb
8	baaabcdddcc	aacdccdcaac	dbbbbbb
9	dbaaabccccdd	aabcccdbddda	dbbbbbbb
10	dbaaabbddd	aabccccdcd	dbbbbbb
11	daaabcdddbcb	acccccdcbccb	dbbbbbbbb
13	daaaaabccdddddd	aaccccccccccbcb	dbbbbbbb
14	caaaabbcccccdd	aacccccdcacdcc	dbbbbbb
15	caaaabccddddcbb	aaccdcdcdcababb	dbbbbbbb

被试者序号	驾驶行为次数	符号化编码	车辆运动轨迹变化
1	10	ad₁b₁f₁e₁d₂af₂c₁c₂	左变道
2	8	ad₁d₂f₁b₁e₁f₂a	左变道
3	9	d₁ad₂f₁b₁e₁af₂c₁c₂	左变道
4	7	ad₁g₁b₂e₂ag₂	右变道
5	10	ad₁b₁b₂f₁b₁e₁af₂c₂	左变道
6	9	ad₁af₁b₁e₁f₂d₂c₁	左变道
7	9	ad₁d₂f₁b₁e₁ac₁f₂	左变道
8	9	ad₁d₂f₁b₁e₁f₂c₁c₂	左变道
9	10	d₁ab₁af₁b₁e₁f₂d₂c₁	左变道
10	10	ad₁d₂f₁b₁e₁ac₁f₂c₂	左变道
11	15	ad₁d₂f₁b₁e₁af₂g₁b₂e₂ac₁g₂c₂	左变道+右变道
13	9	ad₁b₁f₁ae₁d₂c₁f₂	左变道
14	8	ad₁f₁b₁e₁af₂d₂	左变道
15	11	a₁d₁b₁a₁f₁b₁e₁a₁f₂d₂c₁	左变道