基于BKPE安全场模型的复杂天气状态下的行车风险识别方法

李诚信; 柳本民; 廖晨非; 王鹏飞; 胡佳欣; 刘鹏乾; 涂辉招

doi:10.3963/j.jssn.1674-4861.2025.02.018

基于BKPE安全场模型的复杂天气状态下的行车风险识别方法

doi: 10.3963/j.jssn.1674-4861.2025.02.018

1.
同济大学道路与交通工程教育部重点实验室上海 201804
2.
香港科技大学（广州）人工智能学域广州 511466
3.
中国矿业大学（北京）应急管理与安全工程学院北京 100083

基金项目:

国家重点研发计划项目 2019YFE0108300

云南公路资产管理项目 HAMP-CS-05

详细信息

作者简介:
李诚信（2000—)，硕士研究生. 研究方向：智能交通安全、多智能体与缺陷检测. E-mail: 15319792170@163.com

通讯作者:
柳本民（1968—)，博士，副教授. 研究方向：道路安全与环境. E-mail: liubenming@tongji.edu.cn

中图分类号: U492.8
计量
- 文章访问数: 36
- HTML全文浏览量: 21
- PDF下载量: 3
- 被引次数: 0
出版历程
- 收稿日期: 2024-07-09

A Method for Traffic Risk Identification Under Complex Weather Conditions Based on the BKPE Security Field Model

1.
The Key Laboratory of Road and Traffic Engineering of Ministry of Education, Tongji University, Shanghai 201804, China
2.
AI thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511466, China
3.
School of Emergency Management and Safety Engineering, China University of Mining & Technology (Beijing), Beijing 100083, China

摘要

摘要: 目前的行车安全场理论基于“人-车-路”三维构建势能函数，但忽略了复杂的天气因素对行车风险的复合影响，将道路状况（“路”）与天气情况（“环”）所产生的影响简单地归于一类。这低估了天气环境对行车风险的影响程度，并存在对极端天气的风险解算不够敏感的问题，使得方法的实际应用受到较大局限。因此基于行车安全场（driving safety field，DSF）理论，引入了新的环境场函数，实现“人-车-路-环”的风险因素全覆盖，分别构建行为场（behavior field）、动能场（kinetic energy field）、势能场（potential energy field）和环境场（environment field），以此提出针对恶劣天气下的行车安全场BKPE模型。基于中国道路交通安全数据集对原有行车安全场相关参数进行重新标定。同时分析天气因素对行车安全影响的指数变化特征，构建环境了影响因子，并提出环境场函数。在构建包含环境场的行车安全场模型的基础上，基于Car-100数据集，对具体实例计算其人工势能函数，进行微观分析。通过2个典型事件进行多类型风险的量化分析，同时与原有行车安全场模型进行比较分析，说明原有行车安全场模型对于天气环境形成的风险存在低估。随后基于Bootstrap抽样，6次采样计算所得人工势能函数对实际交通事件的描述平均准确率达到91.7%。最终，基于BKPE模型，提出相应的行车风险控制对策。
- 道路交通安全 /
- 行车风险 /
- BKPE模型 /
- 行车安全场（DSF）理论 /
- 环境场函数
Abstract: The current driving safety field (DSF) theory is based on a three-dimensional framework of "driver-vehicle-road" to construct the potential energy function. However, it overlooks the complex impact of weather conditions on driving risk, simplistically categorizing the influence of road conditions ("road") and weather conditions ("environment") into one category. This approach underestimates the extent of the impact of weather conditions ondriving risk and exhibits insufficient sensitivity to the risk calculation associated with extreme weather conditions, thereby significantly limiting the practical application of the method. Therefore, based on the DSF theory, a new environmental field function is introduced to achieve comprehensive coverage of risk factors in a"driver-vehicle-road-environment"framework. Specifically, the Behavior field, Kinetic energy field, Potential energy field, andEnvironmental field are constructed separately, and the BKPE model for driving safety field under adverse weatherconditions is proposed. In this study, the relevant parameters of the original driving safety field are re-calibratedbased on the Chinese road traffic safety dataset. Meanwhile, the exponential change characteristics of weather factors on driving safety are analyzed, and an environmental impact factor is constructed, leading to the proposal of theenvironmental field function. On the basis of the driving safety field model incorporating the environmental field, the artificial potential energy function is calculated for specific cases using the Car-100 data set for micro-analysis.Two typical events are analyzed to quantify multiple types of risks, and a comparative analysis with the originaldriving safety field model is conducted, demonstrating that the original model underestimates the risks associatedwith weather conditions. Subsequently, based on Bootstrap sampling, the average accuracy rate of the artificial potential energy function in describing actual traffic events, calculated from six samples, reaches 91.7%. Finally, corresponding driving risk control strategies are proposed based on the BKPE model.
- road traffic safety /
- driving risk /
- "BKPE"Model /
- DSF theory /
- environmental field function

HTML全文

图 1 基于场论的人-车-路-环要素的行车风险表示

Figure 1. Driving risk representation of human-car-road-ring elements based on field theory

下载: 全尺寸图片幻灯片

图 2 Car-100数据集项目的压缩视频图像

Figure 2. Compressed video image from the Car-100 dataset project

下载: 全尺寸图片幻灯片

图 3 事件1主车S_SPE值

Figure 3. The SSPE of the main vehicle in Event 1

下载: 全尺寸图片幻灯片

图 4 事件2主车S_SPE值

Figure 4. The SSPE of the main vehicle in Event 2

下载: 全尺寸图片幻灯片

图 5 事件1主车修改前后的S_SPE的对比图

Figure 5. Comparison diagram of the SSPE before and after the modification of the main vehicle in Event 1

下载: 全尺寸图片幻灯片

图 6 事件2主车修改前后的S_SPE的对比图

Figure 6. Comparison diagram of the SSPE before and after the modification of the main vehicle in Event 2

下载: 全尺寸图片幻灯片

图 7 Bootstrap抽样图示

Figure 7. Bootstrap resampling illustration

下载: 全尺寸图片幻灯片

表 1 参数表

Table 1. Parameter table

参数符号	物理意义	参数类型
T_i	物体类型	离散型
m_i	物体质量	连续型
v_i	物体速度	连续型
δ_i	能见度	离散型
μ_i	路面附着系数	连续型
τ_i	道路线形	离散型
D_{dR_p}	身心状态	离散型
D_{DR_c}	认知水平	离散型
D_{DR_s}	驾驶技能	离散型
D_{DR_v}	违法行为	离散型
w	天气类型	离散型

下载: 导出CSV

表 2 2016年中国道路交通事故数据（道路等级）

Table 2. Chinese road traffic accident data in 2016 (road grade)

道路等级	平均车速/(km/h)	事故死亡人数/人
高速公路	100	5 947
一级公路	70	5 467
二级公路	50	13 807
三级公路	35	7 857
四级公路	30	5 956

下载: 导出CSV

表 3 5种道路物体的单位事故损失与标定值

Table 3. Unit accident loss and calibration value of 5 kinds of road objects

编号i	物体类别T_i	单位事故损失/元	ψ(T_i)
1	汽车	5 630	1.000
2	货车	8 124	1.443
3	摩托车	1 887	0.335
4	非机动车辆	1 769	0.314
5	行人	6 393	1.136

下载: 导出CSV

表 4 4种能见度的事故死亡人数和标定值

Table 4. Accident deaths and calibration values for 4 types of visibility

编号i	能见度条件δ_i/m	事故死亡人数/人	ψ(δ_i)
1	< 50	8 992	0.351
2	> 50~100	15 860	0.620
3	> 100~200	12 646	0.494
4	> 200	25 595	1.000

下载: 导出CSV

表 5 7种道路线形的事故死亡人数和标定值

Table 5. Accident deaths and calibration values for 7 road lines

道路线形τ_i	死亡人数/人
急弯	444
陡坡	134
连续下坡	191
一般弯坡	4 227
急弯陡坡	618
一般坡急弯	383
一般弯陡坡	311

下载: 导出CSV

表 6 2016年中国道路安全交通事故数据（路面状态）

Table 6. Road safety traffic accident data in 2016 (pavement state)

编号i	路面通行条件	路面附着系数μ_i	死亡人数/人
1	干燥	0.90	52 497
2	潮湿	0.60	8 708
3	积水	0.50	746
4	漫水	0.55	41
5	冰雪	0.30	794
6	泥泞	0.20	78

下载: 导出CSV

表 7 不同年龄段驾驶人的事故风险标定值

Table 7. Accident risk calibration values for drivers of different ages

编号i	驾驶人年龄D_{DR_p}/岁	ψ(D_{DR_p})
1	> 16~20	0.199
2	> 20~25	0.612
3	> 25~30	1.000
4	> 30~35	0.917
5	> 35~40	0.861
6	> 40 ~45	0.919
7	> 45 ~50	0.761
8	> 50~55	0.462
9	> 55~60	0.241
10	> 60~65	0.156
11	> 65	0.186

下载: 导出CSV

表 8 不同职业驾驶人的风险标定值

Table 8. Risk calibration values for different occupational drivers

行业类型	死亡人数/人	Ψ(D_{DR_c})
公务员	283	0.015 9
公安民警	68	0.003 8
职员	3 899	0.218 5
工人	5 750	0.322 3
农民	17 841	1.000 0
自主经营者	8 661	0.485 5
军人	17	0.001 0
武警	22	0.001 2
教师	233	0.013 1
大(专)学生	89	0.005 0
中(专)学生	254	0.0142
小学生	50	0.002 8
学龄前儿童	17	0.001 0
港澳台胞	22	0.001 2
华侨	2	0.000 1
外国人	37	0.002 1
外来务工者	3 151	0.176 6
不在业人员	993	0.055 7

下载: 导出CSV

表 9 不同驾龄驾驶人的事故风险标定值

Table 9. Accident risk calibration value of drivers with different driving ages

编号i	驾驶人驾龄D_{DR_s}/年	Ψ(D_{DR_s})
1	< 1	0.408
2	> 1~2	0.224
3	> 2~3	0.229
4	> 3~4	0.258
5	> 4~5	0.264
6	> 5~10	1.000
7	> 10 ~15	0.691
8	> 15~20	0.364
9	> 20	0.273

下载: 导出CSV

表 10 交通违法行为的标定值

Table 10. The calibration value of traffic violations

编号i	交通违法行为D_{DR_v}	Ψ(D_{DR_v})
1	超速行驶	0.506
2	酒后驾驶	0.383
3	逆行	0.348
4	疲劳驾驶	0.087
5	违法变更车道	0.089
6	违法超车	0.179
7	违法倒车	0.099
8	违法掉头	0.040
9	违法会车	0.242
10	违法牵引	0.004
11	违法抢行	0.093
12	违法上道路行驶	0.289
13	违法停车	0.041
14	违法占道行驶	0.184
15	违法装载	0.120
16	违法装载超限及危险品运输	0.026
17	违反交通信号	0.222
18	未按规定让行	1.000
19	无证驾驶	0.755
20	不按规定使用灯光	0.017

下载: 导出CSV

表 11 天气类型参数标定结果

Table 11. Results of the weather type parameter calibration

天气类型	标定结果
晴天	0.158
阴天	0.143
雨天	0.248
雪天	0.282

下载: 导出CSV

表 11 Bootstrap采样计算结果

Table 11. Bootstrap sampling of the calculation results

采样集编号	准确率/%
1	100
2	80
3	100
4	90
5	90
6	90

下载: 导出CSV

参考文献(29)

[1]	张旭欣, 王雪松, 马勇, 等. 驾驶行为与驾驶风险国际研究进展[J]. 中国公路学报, 2020, 33(6): 1-17. ZHANG X X, WANG X S, MA Y, et al. International research progress on driving behavior and driving risks[J]. China Journal of Highway and Transport, 2020, 33(6): 1-17. (in Chinese)
[2]	柳本民, 李诚信, 王子天, 等. 考虑不良天气的山区公路运营耦合风险识别[J]. 交通与运输, 2023, 39(5): 1-7. LIU B M, LI C X, WANG Z T, et al. Risk identification of coupled mountain road operations considering adverse weather[J]. Traffic & Transportation, 2023, 39(5): 1-7. (in Chinese)
[3]	MA Y, XU J, GAO C, et al. Review of research on road traffic operation risk prevention and control[J]. International Journal of Environmental Research and Public Health, 2022, 19(19): 12115.
[4]	DAS A, AHMED M M. Structural equation modeling approach for investigating drivers'risky behavior in clear and adverse weather using SHRP2 naturalistic driving data[J]. Journal of Transportation Safety & Security, 2022, 15(11): 1116-1147.
[5]	NASIM KHAN M, DAS A, AHMED M M. Non-parametric association rules mining and parametric ordinal logistic regression for an in-depth investigation of driver speed selection behavior in adverse weather using SHRP2 naturalistic driving study data[J]. Transportation Research Record: Journal of the Transportation Research Board, 2020, 2674(11): 101-119.
[6]	DAS A, AHMED M M. Exploring the effect of fog on lane-changing characteristics utilizing the SHRP2 naturalistic driving study data[J]. Journal of Transportation Safety & Security, 2021, 13(5): 477-502.
[7]	KIM Y, ALI N, HONG J E. Safety-based platoon driving simulation with variable environmental conditions[C]. 16^th International Conference on Software Technologies (ICSOFT), Online Streaming: Science and Technology Publications, 2021.
[8]	WANG J, WU J, LI Y. The driving safety field based on driver-vehicle-road interactions[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(4): 2203-2214.
[9]	NI D. A Unified perspective on traffic flow theory, part Ⅰ: the field theory[J]. Applied Mathematical Sciences, 2013, 7(39): 1929-1946.
[10]	MATSUMI R, RAKSINCHAROENSAK P, NAGAI M. Autonomous braking control system for pedestrian collision avoidance by using potential field[J]. IFAC Proceedings Volumes, 2013, 46(21): 328-334.
[11]	RAKSINCHAROENSAK P, AKAMATSU Y, MORO K, et al. Predictive braking assistance system for intersection safety based on risk potential[J]. IFAC Proceedings Volumes, 2013, 46(21): 335-340.
[12]	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. WU J. Research on driver-vehicle-road factors considered driving risk evaluation method[D]. Beijing: Tsinghua University, 2015. (in Chinese)
[13]	WANG J, WU J, ZHENG X, 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.
[14]	KOLEKAR S, PETERMEIJER B, BOER E, et al. A risk field-based metric correlates with driver's perceived risk in manual and automated driving: a test-track study[J]. Transportation Research Part C: Emerging Technologies, 2021, 133: 103428.
[15]	HUANG H Y, WANG J Q, FEI C, et al. A probabilistic risk assessment framework considering lane-changing behavior interaction[J]. Science China Information Sciences, 2020, 63 (9): 190203.
[16]	熊坚, 施锦浩, 万华森. 人车路综合风险场模型构建及驾驶风格评估[J]. 交通运输系统工程与信息, 2021, 21(6): 105-114. XIONG J, SHI J H, WAN H S, et al. Modeling of driver-vehicle-road integrated risk field and driving style assessment[J]. Journal of Transportation Systems Engineering and Information Technology, 2021, 21(6): 105-114. (in Chinese)
[17]	李珂, 韩同群, 杨正才, 等. 基于驾驶人心理风险场模型的个性化换道决策方法[J]. 交通信息与安全, 2023, 41(6): 32-41. doi: 10.3963/j.jssn.1674-4861.2023.06.004 LI K, HAN T Q, YANG Z C, et al. A personalized lane change decision method based on driver's psychological risk field model[J]. Journal of Transport Information and Safety, 2023, 41(6): 32-41. (in Chinese) doi: 10.3963/j.jssn.1674-4861.2023.06.004
[18]	CUSTER K. 100-car data[R/OL].（2018-03-09）[2024-07-09]. https://dataverse.vtti.vt.edu/citation?persistentId=doi:10.15787/VTT1/CEU6RB" target="_blank">10.15787/VTT1/CEU6RB">https://dataverse.vtti.vt.edu/citation?persistentId=doi:10.15787/VTT1/CEU6RB.
[19]	王献伟. 基于自然驾驶数据的驾驶行为辨识和建模方法研究[D]. 开封: 河南大学, 2021. WANG X W. Research on driving behavior identification and modeling method based on natural driving data[D]. Kaifeng: Henan University, 2021. (in Chinese)
[20]	陈浩, 王红, 李维汉, 等. 基于行车安全场理论的预期功能安全场景风险评估[J]. 汽车工程, 2022, 44(11): 1636-1646. CHEN H, WANG H, LI W, et al. Risk assessment of safety of the intended functionality scenes based on driving safety field theory[J]. Automotive Engineering, 2022, 44(11): 1636-1646. (in Chinese)
[21]	SE C, CHAMPAHOM T, JOMNONKWAO S, et al. Examining factors affecting driver injury severity in speeding-related crashes: a comparative study across driver age groups[J]. International Journal of Injury Control and Safety Promotion, 2024, 31(2): 234-255.
[22]	POLIAK M, SVABOVA L, BENUS J, et al. Driver response time and age impact on the reaction time of drivers: a driving simulator study among professional-truck drivers[J]. Mathematics, 2022, 10(9): 1489.
[23]	HABECK C, EICH T S, GU Y, et al. Occupational patterns of structural brain health: independent contributions beyond education, gender, intelligence, and age[J]. Frontiers in Human Neuroscience, 2019, 13: 449.
[24]	WOLFRAM T. (Not just) Intelligence stratifies the occupational hierarchy: ranking 360 professions by IQ and non-cognitive traits[J]. Intelligence, 2023, 98: 101755.
[25]	OH D J, SHIN Y C, OH K S, et al. Examining the links between burnout and suicidal ideation in diverse occupations[J]. Frontiers in Public Health, 2023, 11: 1243920.
[26]	CERNI T, DI BENEDETTO A, RUMIATI R I. The contribution of personality and intelligence toward cognitive competences in higher education[J]. Frontiers in Psychology, 2021, 12: 621990.
[27]	BONFIGLIO D J, LEE Y C, LAVOIE N, et al. Progression of hazard perception knowledge, licensure status and driving experience among teen drivers[J]. Proceedings of the Human Factors and Ergonomics Society Annual Meeting, 2014, 58 (1): 2136-2140.
[28]	MA Y, SUN L. Reliability and validity of self-assessment of driving skills scale in Chinese drivers[J]. Advances in Psychology, 2018, 8(6): 848-854.
[29]	吴海涛, 刘月, 杜彗敏. 小样本条件下地铁运营事故致因推理模型[J]. 中国安全科学学报, 2023, 33(3): 134-140. WU H T, LIU Y, DU H M. Research on model of subway operation accident's cause under small sample condition[J]. China Safety Science Journal, 2023, 33(3): 134-140. (in Chinese)