面向无人驾驶车辆的行车安全场模型构建方法

谢楚安; 任羿; 杨德真; 冯强; 孙博; 王自力

doi:10.13700/j.bh.1001-5965.2022.0462

面向无人驾驶车辆的行车安全场模型构建方法

doi: 10.13700/j.bh.1001-5965.2022.0462

北京航空航天大学可靠性与系统工程学院，北京 100191

基金项目: 可靠性与环境工程技术国家级重点实验室基金(6142004210108)

详细信息

通讯作者:
E-mail：09967@buaa.edu.cn

中图分类号: X981
计量
- 文章访问数: 188
- HTML全文浏览量: 96
- PDF下载量: 7
- 被引次数: 0
出版历程
- 收稿日期: 2022-06-08
- 录用日期: 2022-09-11
- 网络出版日期: 2022-11-03
- 整期出版日期: 2024-04-29

Construction method of driving safety field model for unmanned vehicles

School of Reliability and Systems Engineering, Beihang University, Beijing 100191, China

Funds: National Key Laboratory of Reliability and Environmental Engineering Technology Foundation (6142004210108)

More Information

Corresponding author: E-mail：09967@buaa.edu.cn

摘要

摘要:
针对全面系统评价无人驾驶车辆行车安全方法欠缺的问题，提出一种改进的无人驾驶车辆行车安全场模型。考虑无人驾驶车辆复杂道路因素，人工智能(AI)系统感知、决策、控制3大模块的特性对无人驾驶车辆行车安全的影响，基于胡克定律，建立动态势能场及安全行为场相结合的无人驾驶车辆行车安全场数学模型，以此表征道路上静止物体、运动物体与AI系统自身等因素造成的行车风险。结合典型行驶场景的行车安全分析验证所提模型的正确性和可用性。
- 无人驾驶车辆 /
- 行车安全场 /
- 风险 /
- 行车安全评价 /
- 动态势能场
Abstract:
In response to the shortage of comprehensive and systematic methods for evaluating the driving safety of unmanned vehicles, an enhanced driving safety field model is proposed, taking into account the impact of the complex road factors of unmanned vehicles as well as the characteristics of three artificial intelligence (AI) system modules: perception, decision-making, and control. A mathematical model of unmanned vehicle driving safety field combining dynamic potential field and safety behavior field is established based on Hooke’s law to characterize the driving risks caused by static objects, moving objects and AI system itself on the road. The correctness and usability of the proposed model is verified by the driving safety analysis of typical driving scenarios.
- unmanned vehicles /
- driving safety field /
- risk /
- driving safety evaluation /
- dynamic potential field

HTML全文

图 1 前后车车距与弹簧类比示意图

Figure 1. Analogous diagram of front and rear car distance and spring compression

下载: 全尺寸图片幻灯片

图 2 道路曲率直角坐标系示意图

Figure 2. Schematic diagram of road curvature rectangular coordinate system

下载: 全尺寸图片幻灯片

图 3 道路坡度示意图

Figure 3. Schematic diagram of road slope

下载: 全尺寸图片幻灯片

图 4 无人驾驶车辆实际轨迹及规划轨迹

Figure 4. Actual trajectory and planned trajectory of unmanned vehicle

下载: 全尺寸图片幻灯片

图 5 等效质量待定系数标定流程

Figure 5. Flow chart for calibration of equivalent mass undetermined coefficient

下载: 全尺寸图片幻灯片

图 6 公路平均车速与事故平均伤亡人数的关系

Figure 6. Relationship between average highway speed and average number of casualties in accidents

下载: 全尺寸图片幻灯片

图 7 无人驾驶车辆行车安全场典型场景

Figure 7. Typical driving safety field case of unmanned vehicles

下载: 全尺寸图片幻灯片

图 8 不同行车场景及其场强变化

Figure 8. Different driving case and field strength changes

下载: 全尺寸图片幻灯片

表 1 高速公路数据计算结果

Table 1. Calculation results of expressway data

高速公路	平均车速/ (km·h⁻¹)	亿车公里死亡人数/ (10⁸人·辆·km⁻¹)	亿车公里受伤人数/ (10⁸人·辆·km⁻¹)	亿车公里事故数/ (10⁸次·辆·km⁻¹)	N
成渝高速	87.61	7	23	23	0.513
石太高速	71.00	9	29	29	0.517
广佛高速	58.13	6	21	21	0.500
京石高速	93.00	15	47	45	0.547
沪宁高速	79.86	6	20	21	0.486
沈大高速	79.50	5	18	19	0.468
京津塘高速	88.70	10	32	31	0.535

下载: 导出CSV

表 2 典型场景当前状态信息

Table 2. Typical scenario state information

目标	$ \left( {{x_i},{y_i}} \right) $/m	$ {m_i} $/ kg	$ {v_i} $/ (m·s⁻¹)	$ {a_i} $/ (m·s⁻²)	$ {\theta _i} $/ (°)
目标①	(7,1)	800	45	2	0
目标②	(30,4)	200	0	0	0
目标③	(25，0)	1000	50	1.5	−25
目标④	(40,3)	900	30	−1	2
目标⑤	(47,2.5)	90	6	1	0
目标⑥	(4,−3)	88	15	1	0
目标⑦	(18,−4)	900	0	0	0
目标⑧	(37,-2.5)	60	15	1	−10

下载: 导出CSV

参考文献(29)

[1]	《中国公路学报》编辑部. 中国汽车工程学术研究综述·2017[J]. 中国公路学报, 2017, 30(6): 1-197. doi: 10.3969/j.issn.1001-7372.2017.06.001 Editorial Department of China Journal of Highway and Transport. Review on China's automotive engineering research progress: 2017[J]. China Journal of Highway and Transport, 2017, 30(6): 1-197 (in Chinese). doi: 10.3969/j.issn.1001-7372.2017.06.001
[2]	XU Q, LI K Q, WANG J Q, et al. The status, challenges, and trends: An interpretation of technology roadmap of intelligent and connected vehicles in China[J]. Journal of Intelligent and Connected Vehicles, 2022, 5(1): 1-7. doi: 10.1108/JICV-07-2021-0010
[3]	YUAN Q, XU X C, WANG T, et al. Investigating safety and liability of autonomous vehicles: Bayesian random parameter ordered probit model analysis[J]. Journal of Intelligent and Connected Vehicles, 2022, 5(3): 199-205. doi: 10.1108/JICV-04-2022-0012
[4]	VAN D H. A time-based analysis of road user behaviour in normal and critical encounters[M/OL]. (1990-04-24) [2021-11-01]. https://repository.tudelft.nl/islandora/object/uuid%3A8fb40be7-fae1-4481-bc37-12a7411b85c7.
[5]	KIEFER R J, FLANNAGAN C A, JEROME C J. Time-to-collision judgments under realistic driving conditions[J]. Human Factors: The Journal of the Human Factors and Ergonomics Society, 2006, 48(2): 334-345.
[6]	FULLER R G C. Determinants of time headway adopted by truck drivers[J]. Ergonomics, 1981, 24(6): 463-474. doi: 10.1080/00140138108924868
[7]	YUAN Q A, CHEN H Y. Factor comparison of passenger-vehicle to vulnerable road user crashes in Beijing, China[J]. International Journal of Crashworthiness, 2017, 22(3): 260-270. doi: 10.1080/13588265.2016.1248226
[8]	WANG J Q, WU J, ZHENG X J, et al. Driving safety field theory modeling and its application in pre-collision warning system[J]. Transportation Research Part C:Emerging Technologies, 2016, 72: 306-324. doi: 10.1016/j.trc.2016.10.003
[9]	ROSSETTER E J, GERDES J C. Lyapunov based performance guarantees for the potential field lane-keeping assistance system[J]. Journal of Dynamic Systems, Measurement, and Control, 2006, 128(3): 510-522. doi: 10.1115/1.2192835
[10]	BYRNE S, NAEEM W, FERGUSON S. Improved APF strategies for dual-arm local motion planning[J]. Transactions of the Institute of Measurement and Control, 2015, 37(1): 73-90. doi: 10.1177/0142331214532002
[11]	MILLER R, HUANG Q F. An adaptive peer-to-peer collision warning system[C]//Proceedings of the IEEE 55th Vehicular Technology Conference. Piscataway: IEEE Press, 2002: 317-321.
[12]	TSOURVELOUDIS N C, VALAVANIS K P, HEBERT T. Autonomous vehicle navigation utilizing electrostatic potential fields and fuzzy logic[J]. IEEE Transactions on Robotics and Automation, 2001, 17(4): 490-497. doi: 10.1109/70.954761
[13]	SATTEL T, BRANDT T. From robotics to automotive: Lane-keeping and collision avoidance based on elastic bands[J]. Vehicle System Dynamics, 2008, 46(7): 597-619. doi: 10.1080/00423110701543452
[14]	王建强, 吴剑, 李洋. 基于人-车-路协同的行车风险场概念、原理及建模[J]. 中国公路学报, 2016, 29(1): 105-114. doi: 10.3969/j.issn.1001-7372.2016.01.014 WANG J Q, WU J, LI Y. Concept, principle and modeling of driving risk field based on driver-vehicle-road interaction[J]. China Journal of Highway and Transport, 2016, 29(1): 105-114(in Chinese). doi: 10.3969/j.issn.1001-7372.2016.01.014
[15]	贺启才, 蔡少康, 王康. 基于场论的汽车避撞方法研究[J]. 汽车实用技术, 2021, 46(9): 25-29. HE Q C, CAI S K, WANG K. Research on collision avoidance method based on field theory[J]. Automobile Applied Technology, 2021, 46(9): 25-29(in Chinese).
[16]	刘帅. 基于安全场的智能汽车个性化换道决策与规划算法研究[D]. 长春: 吉林大学, 2019: 69-88. LIU S. A personalized lane-changing decision-making and trajectory-planning method based on safety field for intelligent vehicles[D]. Changchun: Jilin University, 2019: 69-88 (in Chinese).
[17]	NI D H. A unified perspective on traffic flow theory. Part I: The field theory[J]. Applied Mathematical Sciences, 2013, 7: 1929-1946. doi: 10.12988/ams.2013.13175
[18]	杨杨, 任少杰, 杨正才. 基于改进型人工势场的无人车局部避障[J]. 湖北汽车工业学院学报, 2020, 34(4): 5-10. doi: 10.3969/j.issn.1008-5483.2020.04.002 YANG Y, REN S J, YANG Z C. Local obstacle avoidance based on improved artificial potential field[J]. Journal of Hubei University of Automotive Technology, 2020, 34(4): 5-10(in Chinese). doi: 10.3969/j.issn.1008-5483.2020.04.002
[19]	张国辉, 王璇, 张雅楠, 等. 实际环境中多无人车协同路径规划模型研究[J]. 系统仿真学报, 2023, 35(2): 408-422. ZHANG G H, WANG X, ZHANG Y N, et al. Research on cooperative path planning model of multiple unmanned vehicles in real environment[J]. Journal of System Simulation, 2023, 35(2): 408-422 (in Chinese).
[20]	BERRY A J, HOWITT J, GU D W, et al. A continuous local motion planning framework for unmanned vehicles in complex environments[J]. Journal of Intelligent & Robotic Systems, 2012, 66: 477-494.
[21]	TRENTINI M, BECKMAN B, DIGNEY B. Control and learning for intelligent mobility of unmanned ground vehicles in complex terrains[C]//Proceedings of the Unmanned Ground Vehicle Technology VII. Orlando: SPIE, 2005, 5804: 203-216.
[22]	LI J X, DAI B, LI X H, et al. An Interaction-aware predictive motion planner for unmanned ground vehicles in dynamic street scenarios[J]. International Journal Of Robotics & Automation, 2019, 34(3): 203-215.
[23]	ZHANG C, BERGER C, DOZZA M. Social-IWSTCNN: A social interaction-weighted spatio- temporal convolutional neural network for pedestrian trajectory prediction in urban traffic scenarios[C]//Proceedings of the 2021 IEEE Intelligent Vehicles Symposium. Piscataway: IEEE Press, 2021: 1515-1522.
[24]	YU S Y, MALAWADE A V, MUTHIRAYAN D, et al. Scene-graph augmented data-driven risk assessment of autonomous vehicle decisions[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(7): 7941-7951. doi: 10.1109/TITS.2021.3074854
[25]	金立生, 郭柏苍, 谢宪毅, 等. 基于行车安全场模型的交叉口车辆控制算法[J]. 西南交通大学学报, 2022, 57(4): 753-760. JIN L S, GUO B C, XIE X Y, et al. Cooperative control algorithm for vehicle at intersection based on driving safety field model[J]. Journal of Southwest Jiaotong University, 2022, 57(4): 753-760 (in Chinese).
[26]	WANG J Q, WU J, LI Y, et al. The concept and modeling of driving safety field based on driver-vehicle-road interactions[C]//Proceedings of the 17th International IEEE Conference on Intelligent Transportation Systems. Piscataway: IEEE Press, 2014: 974-981.
[27]	吴剑. 考虑人-车-路因素的行车风险评价方法研究[D]. 北京: 清华大学, 2015: 17-18. WU J. Research on driver-vehicle-road factors considered driving risk evaluation method[D]. Beijing: Tsinghua University, 2015: 17-18 (in Chinese).
[28]	国家质量监督检验检疫总局, 中国国家标准化管理委员会. 水平能见度等级: GB/T 33673—2017[S]. 北京: 中国标准出版社, 2017: 1-8. General Administration of Quality Supervision, Inspection and Quarantine of the People's Republic of China, Standardization Administration of the People's Republic of China. Grade of horizontal visibility: GB/T 33673—2017[S]. Beijing: Standards Press of China, 2017: 1-8 (in Chinese).
[29]	裴玉龙, 程国柱. 高速公路车速离散性与交通事故的关系及车速管理研究[J]. 中国公路学报, 2004, 17(1): 74-78. PEI Y L, CHENG G Z. Research on the relationship between discrete character of speed and traffic accident and speed management of freeway[J]. China Journal of Highway and Transport, 2004, 17(1): 74-78 (in Chinese).