基于动态贝叶斯网络的地下道路行车风险评估

doi:10.16097/j.cnki.1009-6744.2025.03.021

交通运输系统工程与信息 ›› 2025, Vol. 25 ›› Issue (3): 232-245.DOI: 10.16097/j.cnki.1009-6744.2025.03.021

基于动态贝叶斯网络的地下道路行车风险评估

尚婷^*a,b，郭明洋^b，唐伯明^b，徐钰婷^b

重庆交通大学，a.智能综合立体交通重庆市重点实验室；b.交通运输学院，重庆400074

收稿日期:2024-11-25 修回日期:2024-12-22 接受日期:2025-01-02 出版日期:2025-06-25 发布日期:2025-06-21
作者简介:尚婷(1983—)，女，重庆人，副教授，博士。
基金资助:
重庆市研究生科研创新项目(CYS240480)；教育部青年人文社会科学研究青年基金(22YJCZH143)；重庆市自然科学基金(CSTB2023NSCQ-MSX0742)。

Risk Assessment of Underground Road Driving Based on Dynamic Bayesian Networks

SHANG Ting^*a,b, GUO Mingyang^b, TANG Boming^b, XU Yuting^b

a. Chongqing Key Laboratory of Intelligent Integrated and Multidimensional Transportation System; b. School of Traffic & Transportation, Chongqing Jiaotong University, Chongqing 400074, China

Received:2024-11-25 Revised:2024-12-22 Accepted:2025-01-02 Online:2025-06-25 Published:2025-06-21
Supported by:
Chongqing Postgraduate Research Innovation Project (CYS240480)；Youth Foundation for Humanities and Social Science Research of Ministry of Education (22YJCZH143)；Natural Science Foundation Project of Chongqing (CSTB2023NSCQ-MSX0742)。

摘要/Abstract

摘要： 为探究地下道路不同交通标志信息密度下驾驶员行车风险动态演变规律，本文以驾驶员视觉负荷为表征指标，利用自然驾驶试验采集驾驶员眼动数据，基于动态贝叶斯网络理论构建驾驶员行车风险评价模型。基于香农信息熵量化交通标志信息量，构建考虑交通标志信息量呈现速率的交通标志信息密度模型。选取解放碑地下道路4种不同交通标志信息密度的路段开展实车试验，提取并分析不同路段的驾驶员视觉特性指标。引入动态贝叶斯网络理论动态概率预测及推理评估驾驶员行车风险，由诊断推理、敏感性分析和影响链分析得到影响驾驶员行车风险的关键风险因素。结果表明：驾驶员注视持续时间、水平/垂直扫视幅度、水平/垂直扫视速度及瞳孔面积变化速率与交通标志信息密度呈正相关，眨眼频率与交通标志信息密度呈负相关；驾驶员行车风险发生概率随时间呈动态变化，先上升，后趋于平缓，且随交通标志信息密度的增加，4个路段的风险概率分别稳定于22.6%，35.7%，40.1%和43.8%；驾驶员行车风险受注视状态等环节风险因素影响较大，包括注视持续时间、瞳孔面积变化速率和眨眼频率等关键风险因素。

关键词: 交通工程, 视觉负荷, 动态贝叶斯网络, 地下道路, 实车试验, 风险评估

Abstract: This study aims to investigate the dynamic evolution law of driver's driving risk in underground roads under different traffic sign information densities. Using the driver's visual load as a representative metric, eye movement data of drivers were collected through natural driving tests. A driving risk evaluation model was constructed based on dynamic Bayesian network theory. The traffic sign information density model was constructed based on Shannon entropy to quantify the information volume of traffic signs, considering the presentation rate of traffic sign information. Four underground roads with different traffic sign information densities in Liangma Square were selected for the in-vehicle experiment, and the driver's visual characteristics indicators were extracted and analyzed. The driver's driving risk was dynamically predicted and inferred by the dynamic Bayesian network theory, and the key risk factors affecting the driver's driving risk were obtained through diagnosis inference, sensitivity analysis and impact chain analysis. The results show that the driver's fixation duration, horizontal/vertical saccadic amplitude, horizontal/vertical saccadic speed, and pupil area change rate are positively correlated with traffic sign information density, while the blinking frequency is negatively correlated; the driver's driving risk occurrence probability changes dynamically over time, first increasing and then becoming stable, and the risk probability of the four sections stabilizes at 22.6%, 35.7%, 40.1%, and 43.8% respectively as the traffic sign information density increases; the driver's driving risk is greatly affected by the link risk factors in the linkage process, including the key risk factors of fixation duration, pupil area change rate, and blinking frequency.

Key words: traffic engineering, visual load, dynamic Bayesian network, underground loop, real vehicle test, risk assessment

中图分类号:

U491

尚婷, 郭明洋, 唐伯明, 徐钰婷. 基于动态贝叶斯网络的地下道路行车风险评估[J]. 交通运输系统工程与信息, 2025, 25(3): 232-245.

SHANG Ting, GUO Mingyang, TANG Boming, XU Yuting. Risk Assessment of Underground Road Driving Based on Dynamic Bayesian Networks[J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(3): 232-245.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/10.16097/j.cnki.1009-6744.2025.03.021

http://www.tseit.org.cn/CN/Y2025/V25/I3/232

参考文献

[1]郑展骥,郑礼伟,许宇轩,等.基于实车数据的城市地下螺旋匝道小客车运行特性研究[J].中国公路学报, 2024, 37(9): 273-288. [ZHENG Z J, ZHENG L W, XU Y X, et al. Study on the operational characteristics of passenger cars in urban underground spiral ramps based on real vehicle data[J]. China Journal of Highway and Transport, 2024, 37(9): 273-288.]

[2]赵晓华,董文慧,李佳,等.基于驾驶行为的隧道交通标志影响特征及作用机理[J].华南理工大学学报(自然科学版), 2023, 51(4): 88-100. [ZHAO X H, DONG W H, LI J, et al. Influence characteristics and mechanism of tunnel traffic signs based on driving behavior[J]. Journal of South China University of Technology (Natural Science Edition), 2023, 51(4): 88-100.]

[3]叶飞,温小宝,张兴冰,等.渐变设计在缓解隧道景观带视觉突变问题中的贡献[J].中国公路学报,2023,36 (11): 375-385. [YE F, WEN X B, ZHANG X B, et al. Contribution of gradient design to alleviating visual mutation issues in tunnel landscapes[J]. China Journal of Highway and Transport, 2023, 36(11): 375-385.]

[4]周扬,付锐,刘卓凡.考虑驾驶人不同分心类型的分心识别研究[J]. 交通运输系统工程与信息,2022,22(3): 132-139. [ZHOU Y, FU R, LIU Z F. Research on distraction recognition considering different types of driver distraction[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(3): 132-139.]

[5]李坤宸,袁伟,李舒欣,等.听觉-言语认知负荷下工作记忆容量对跟车行驶影响[J].交通运输系统工程与信息, 2024, 24(1): 93-105. [LI K C, YUAN W, LI S X, et al. Impact of working memory capacity on car following under auditory-verbal cognitive load[J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(1): 93-105.]

[6]吕能超,曹越,秦羚,等.基于交通标志信息量的驾驶负荷加载有效性研究[J].中国公路学报,2018,31(8): 165-172. [LV N C, CAO Y, QIN L, et al. Study on the effectiveness of driver load based on traffic sign information[J]. China Journal of Highway and Transport, 2018, 31(8): 165-172.]

[7]张磊,彭金栓,陈晓利.接管场景驱动下非驾驶任务对驾驶人视觉与生理特征的影响[J].交通运输系统工程与信息, 2024, 24(3): 290-298. [ZHANG L, PENG J S, CHEN XL. Effects of non-driving tasks on drivers' visual and physiological characteristics in takeover scenarios [J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(3): 290-298.]

[8]杜永军,王宁,张攀,等.动态随机扰动事件下交通网络连边重要度评估[J]. 交通运输工程学报,2024,24 (4): 184-194. [DU Y J, WANG N, ZHANG P, et al. Evaluation of link importance in traffic networks under dynamic stochastic disturbances[J]. Journal of Transportation Engineering, 2024, 24(4): 184-194.]

[9]WANG N X, WU M, KUM F Y, et al. Urban transportation system long-term resilience assessment using multi-dimensional dynamic Bayesian network[J]. Transportation Research Part D: Transport and Environment, 2024, 136: 104427.

[10] SCHWEHR J, WILLERT V. Driver's gaze prediction in dynamic automotive scenes[C]. Yokohama, Japan: 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), 2017.

[11] LUAN T T, ZHANG X, LI H R, et al. Dynamic risk analysis of hazardous materials highway tunnel transportation based on fuzzy Bayesian network[J]. Journal of Loss Prevention in the Process Industries, 2024, 92: 105443.

[12] 杨子邈. 高速公路高密度立交驾驶人眼动特性研究[D]. 重庆: 重庆交通大学,2024. [YANG Z M. Study on human eye movement characteristics of high density freeway interchange drivers[D]. Chongqing: Chongqing Jiaotong University, 2024.]

[13] 乔建刚 ,张恒, 周荣贵.穿城镇公路驾驶员眼动特性[J]. 北京工业大学学报,2019, 45(8): 772-779. [QIAO J G, ZHANG H, ZHOU R G. Eye movement characteristics of drivers on cross-town highway[J]. Journal of Beijing University of Technology, 2019, 45(8): 772-779.]

[14] 胡江碧,李然,马勇.高速公路隧道入口段照明安全阈值评价方法[J]. 中国公路学报, 2014, 27(3): 92-99. [HU J B, LI R, MA Y. Safety threshold evaluation method for lighting in entrance section of expressway tunnel[J]. China Journal of Highway and Transportation, 2014, 27(3): 92-99.]

[15] 陈培焱, 吴刚,马小翔,等.基于驾驶员视觉负荷的格栅式减光罩频闪效应研究[J].武汉理工大学学报(交通科学与工程版), 2020, 44(5): 785-788, 793. [CHEN P Y, WU G, MA X X, et al. Stroboscopic effect of grille dimmer based on driver visual load[J]. Journal of Wuhan University of Technology (Transportation Science and Engineering), 2020, 44(5): 785-788, 793.]

基于动态贝叶斯网络的地下道路行车风险评估

Risk Assessment of Underground Road Driving Based on Dynamic Bayesian Networks

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	覃文文, 彭栋梁, 戢晓峰, 徐迎豪, 李冰, 李武, 曾浩. 山区双车道公路借道超车轨迹预测模型[J]. 交通运输系统工程与信息, 2025, 25(3): 96-106.
[2]	龙科军, 寇诗雨, 邢璐, 高志波, 唐幼仪, 费怡. 考虑货车影响的匝道合流区车辆微观换道行为建模[J]. 交通运输系统工程与信息, 2025, 25(3): 117-131.
[3]	程国柱, 陈永胜, 孟凤威, 徐亮. 客货混行异质交通流下高速公路专用道车流管理方法[J]. 交通运输系统工程与信息, 2025, 25(3): 178-189.
[4]	时玉琦, 杨晓光, 马成元. 随机需求下机非车道分配与复用优化研究[J]. 交通运输系统工程与信息, 2025, 25(3): 204-214.
[5]	陈永恒, 刘卓剑. 相邻信号影响下的无信号路段驾驶员礼让行人分析[J]. 交通运输系统工程与信息, 2025, 25(3): 215-223.
[6]	黄榕, 谢紫萱, 王天桐, 许慧嘉, 陈洋, 赵轩. 不同疏散动机下狭窄过道区域单列人员运动特性研究[J]. 交通运输系统工程与信息, 2025, 25(3): 224-231.
[7]	潘义勇, 朱梦. 不同光照条件下交通事故严重程度影响因素的可转移性分析[J]. 交通运输系统工程与信息, 2025, 25(3): 346-357.
[8]	胡立伟, 杨灿, 周泽禹, 潘江雄, 陈家乐, 龚麒, 马思月. 高速公路出口衔接城市路段交通风险时空动态识别研究[J]. 交通运输系统工程与信息, 2025, 25(3): 358-371.
[9]	张河山, 曾长坤, 王海洋, 田丰铭, 郑展骥, 张羽. 高速公路夜间养护作业区事故风险辨识及影响机理研究[J]. 交通运输系统工程与信息, 2025, 25(2): 157-168.
[10]	邓院昌, 蒋昀轩, 陶胜芹. 基于可解释集成学习的异常驾驶行为风险识别方法[J]. 交通运输系统工程与信息, 2025, 25(2): 180-189.
[11]	巩喆, 杨轸, 郑瑞平, 袁方. 旁车切入下驾驶人短时响应行为异质性建模与分析[J]. 交通运输系统工程与信息, 2025, 25(2): 190-200.
[12]	王建军, 武京, 李景涛, 周英杰. 非公交车辆停靠对主辅式站台延误的影响分析[J]. 交通运输系统工程与信息, 2025, 25(2): 241-252.
[13]	宋现敏, 刘博, 李海涛, 湛天舒, 李世豪, 张云翔. 考虑综合效益的周期型停车预约分配模型[J]. 交通运输系统工程与信息, 2025, 25(1): 24-35.
[14]	曹丹妮, 王涛, 杨松坡, 屈云超, 吴建军. 混合流环境下瓶颈区域车道定制化速度调控研究[J]. 交通运输系统工程与信息, 2025, 25(1): 76-85.
[15]	韩烽凡, 刘爽, 朱亚迪, 杨烨, 王曦. 数据驱动的城轨车站行人仿真方法研究[J]. 交通运输系统工程与信息, 2025, 25(1): 86-91.