Evaluation on driving scenarios for safety of intended functionality of intelligent vehicles

doi:10.16265/j.cnki.issn1003-3033.2022.08.1768

Abstract

Abstract:

Safety of intended functionality of intelligent vehicles was directly affected by their sensing ability of driving scenarios. In order to evaluate scenarios accurately and reliably from a perceptual level, a new evaluation method was proposed. By using fuzzy reasoning and based on analysis of scenarios and elements, fuzzy judgment of scenarios was made from a perspective of drivers' perception, and their fuzzy level was established before correlation between scenario factors was developed by utilizing fuzzy relationship. Then, evaluation value was calculated according to decision function. In the end, rationality of the evaluation method was verified. The results show that this method could achieve a comprehensive understanding of scenarios by integrating driver's perception of them, thus proving to be feasible in scenario evaluation.

Key words: intelligent vehicle, safety of intended functionality, scenario evaluation, fuzzy reasoning, autonomous driving

LUO Qirui, ZHANG Daowen, ZHOU Hua, PANG Shaorong, LI Xiaoyan, WANG Chaojian. Evaluation on driving scenarios for safety of intended functionality of intelligent vehicles[J]. China Safety Science Journal, 2022, 32(8): 140-145.

Figures/Tables 5

Tab.1

Tab.2

Tab.3

Fuzzy indicators of 14 scenarios

场景	$u 1$	$u 2$	$u 3$	$u 4$	$u 5$	$v 1$	$v 2$	$v 3$
1	0.7	1	1	0.8	0.9	1	0.3	0.9
2	0.8	0.8	0.8	0.8	1	1	0.7	0.9
3	0.9	1	1	0.9	0.9	1	0	1
4	0.7	1	0.9	0.8	0.8	0.7	0.8	0.6
5	0.6	1	0.8	0.9	0.9	0.9	0.7	0.5
6	0.7	1	0.8	0.9	1	1	0.7	0.7
7	0.5	0.7	0.7	0.5	1	0.8	0.9	0.2
8	0.6	1	0.7	0.6	1	1	0.2	0.1
9	0.9	0.9	0.9	0.4	1	1	0.5	0.5
10	0.9	0.9	0.8	0.9	1	0.9	0.9	0.4
11	0.8	0.9	0.8	0.6	1	0.7	1	0.6
12	0.9	1	1	1	1	1	0	1
13	0.5	0.6	0.5	0.7	1	0.6	0.9	0.3
14	0.6	1	0.8	0.4	1	0.9	0.8	0.4

Tab.3

Fig.1

References 15

[1]	ISO/PAS 214482019. Road vehicles-safety of the intended functionality[S].
[2]	王荣, 孙亚夫, 宋娟. 自动驾驶车辆道路测试场景评价方法与试验验证[J]. 汽车工程, 2021, 43(4):620-628.
	WANG Rong, SUN Yafu, SONG Juan, et al. Evaluation method and test verification of road test scenes for autonomous vehicles[J]. Automotive Engineering, 2021, 43(4):620-628.
[3]	WANG Chen, XU Chengcheng, XIA Jingxin, et al. A combined use of microscopic traffic simulation and extreme value methods for traffic safety evaluation[J]. Transportation Research Part C: Emerging Technologies, 2018, 90:281-291. doi: 10.1016/j.trc.2018.03.011
[4]	李江坤, 邓伟文, 任秉韬, 等. 一种智能汽车测试场景复杂度的评估方法[C]. 2020中国汽车工程学会年会论文集, 2020:110-117.
	LI Jiangkun, DENG Weiwen, REN Bingtao, et al. An evaluation method of test scenario complexity for intelligent vehicles[C]. Proceedings of the 2020 China Society of Automotive Engineering Annual Meeting, 2020:110-117.
[5]	吴初娜, 曾诚. 场景对驾驶人危险辨识能力评估结果的影响[J]. 中国安全科学学报, 2018, 28(4):30-35. doi: 10.16265/j.cnki.issn1003-3033.2018.04.006
	WU Chu'na, ZENG Cheng. Effects of scenarios on drivers' hazard perception evaluation result[J]. China Safety Science Journal, 2018, 28(4): 30-35. doi: 10.16265/j.cnki.issn1003-3033.2018.04.006
[6]	ZHANG Xinyu, SHAO Wenbo, ZHOU Mo, et al. A scene comprehensive safety evaluation method based on binocular camera[J]. Robotics and Autonomous Systems, 2020, 128: DOI: 10.1016/j.robot.2020.103503. doi: 10.1016/j.robot.2020.103503
[7]	NAJM W G. Description of light-vehicle pre-crash scenarios for safety applications based on vehicle-to-vehicle communications[R]. NHTSA, 2013.
[8]	GEYER S, BALTZER M, FRANZ B, et al. Concept and development of a unified ontology for generating test and use-case catalogues for assisted and automated vehicle guidance[J]. IET Intelligent Transport Systems, 2013, 8(3):183-189. doi: 10.1049/iet-its.2012.0188
[9]	ULBRICH S, MENZEL T, RESCHKA A, et al. Defining and substantiating the terms scene, situation, and scenario for automated driving[C]. IEEE International Conference on Intelligent Transportation Systems, 2015:982-988.
[10]	ELROFAI H, PAARDEKOOPER J, GELDER E, et al. Scenario-based safety validation of connected and automated driving[R]. TNO, 2018.
[11]	董汉, 舒伟, 陈超, 等. 危险驾驶工况场景的复杂度评估方法研究[J]. 汽车工程, 2020, 42(6):808-814.
	DONG Han, SHU Wei, CHEN Chao, et al. Research on complexity evaluation method of dangerous driving scenes[J]. Automotive Engineering, 2020, 42(6): 808-814.
[12]	任秉韬, 邓伟文, 白雪松, 等. 面向智能驾驶测试的仿真场景构建技术综述[J]. 中国图象图形学报, 2021, 26(1): 1-12.
	REN Bingtao, DENG Weiwen, BAI Xuesong, et al. Technologies of virtual scenario construction for intelligent driving testing[J]. Journal of Image and Graphics, 2021, 26(1): 1-12.
[13]	WALTHER W, PHILIPP J. Test case variation and execution[R]. PEGASUS, 2019.
[14]	YAGER R R. Multicriteria decisions with soft information. I. an application of fuzzy set and possibility theory[J]. Fuzzy Math, 1982(2):21-28.
[15]	赵长安, 贺风华. 多变量鲁棒控制系统[M]. 哈尔滨: 哈尔滨工业大学出版社, 2011:31-48.
	ZHAO Chang'an, HE Fenghua. Multivariable robust control systems[M]. Harbin: Harbin Institute of Technology Press, 2011:31-48.

一级指标	二级指标	三级指标	指标分值 (0~1.0)
静态	天气状况	晴天	0.8~1.0
		雨天	0~0.6
		雪天	0~0.4
		雾天	0~0.4
		阴天	0.4~0.8
		多云	0.5~1.0
	路面条件	正常	0.8~1.0
		湿润	0.4~0.8
		泥土地	0~0.6
		积雪	0~0.4
	道路状况	单向道	0.7~1.0
		双向道	0.5~0.8
		分离式车道	0.8~1.0
	光照条件	白天	0.8~1.0
		黄昏	0.5~1.0
		黎明	0.5~1.0
		有照明的夜晚	0.3~0.6
		无照明的夜晚	0~0.5
	坡度	横坡	0.3~0.7
		纵坡	0.3~1.0
		无坡度	1.0

序号	场景描述	序号	场景描述
1	天气状况良好,双向4车道上坡红绿灯路段,左侧有大车驶过,右侧有行人	8	照明较差,多车道直行路段,车流量较少
2	天气状况良好,双向4车道无明显坡道路段,前方右侧车道有移动障碍物	9	照明条件差,双向4车道路段,前方有车辆慢速逆行
3	天气状况良好,双向4车道下坡路段,车流量少	10	天气状况良好,双向4车道十字路口人行横道处,车辆切入
4	天气状况良好,有红绿灯的十字路口路段,右方有车辆快速切入	11	光线条件较差,多车道,有大量穿行的非机动车

序号	场景描述	序号	场景描述
5	天气状况良好,双向4车道高速路路段,车辆跟车行驶后切入左侧车道,车流量较大	12	天气状况极好,双向6车道路段,车流量极少
6	天气状况良好,双向4车道高速路路段,车辆与大货车并行,车流量较小	13	雨天,双向2车道弯道路段,车辆跟行货车,对向有较大车流量
7	照明较差,多车道有红绿灯的十字路口路段,车辆右转,右后方有快速行驶的二轮车	14	光线较差,双向4车道路段,车流量较大,有大量行人、非机动车穿行马路