人机混驾环境下山地城市交织区交通安全评价方法

doi:10.16097/j.cnki.1009-6744.2026.01.025

交通运输系统工程与信息 ›› 2026, Vol. 26 ›› Issue (1): 270-282.DOI: 10.16097/j.cnki.1009-6744.2026.01.025

人机混驾环境下山地城市交织区交通安全评价方法

蔡晓禹^a，聂成^a，雷财林^*a，彭博^a，谢青雨^b

重庆交通大学，a.智慧城市学院；b.交通运输学院，重庆400041

收稿日期:2025-11-18 修回日期:2025-12-28 接受日期:2026-01-06 出版日期:2026-02-25 发布日期:2026-02-15
作者简介:蔡晓禹（1979—），男，四川达州人，教授。
基金资助:
重庆市教育委员会教委重大项目基金(KJZD-M202300702)；重庆市科技局面上自然科学基金(CSTB2025NSCO-GPX0902)。

Traffic Safety Evaluation Method for Mountainous Urban Interchange Areas in Human-Vehicle Mixed Driving Environments

CAI Xiaoyu^a, NIE Cheng^a, LEI Cailin^*a, PENG Bo^a, XIE Qingyu^b

a. School of Smart City; b. School of Transportation, Chongqing Jiaotong University, Chongqing 400041, China

Received:2025-11-18 Revised:2025-12-28 Accepted:2026-01-06 Online:2026-02-25 Published:2026-02-15
Supported by:
Major Project Fund of Chongqing Municipal Education Commission,China(KJZD-M202300702)；General Program of Natural Science Foundation of Chongqing Municipal Science and Technology Commission, China (CSTB2025NSCO-GPX0902)。

摘要/Abstract

摘要： 为精准评估人机混驾环境下交织区的交通安全水平，本文提出一种基于交通冲突的改进灰色定权聚类评价方法。首先，通过无人机高空定点航拍采集缓行与畅行两种交通状态下的车辆运行视频数据，通过轨迹提取与清洗，提取速度、加速度、换道行为及追尾冲突等核心特征参数；基于实测数据在SUMO仿真平台构建仿真场景，完成人工驾驶与自动驾驶车辆的行为参数标定。其次，选取小时交通量、自动驾驶渗透率、大车比、交织比、交织流量比、交织长度、道路纵坡这7个交通冲突影响因素，设计正交仿真实验，采用负二项回归方法构建交通冲突计算模型；以交通冲突发生率为评价指标，基于灰色定权聚类方法，结合组合赋权与正弦曲线型可能度函数，提出一种改进的安全评价方法。最后，以重庆市某典型交织区为实例开展仿真样本对比验证，选取改进的灰色定权聚类、直线型灰色变权聚类、直线型灰色定权聚类这3种评价方法进行性能对比。结果表明：改进评价方法的安全等级判定准确率达98%，直线型灰色变权聚类与直线型灰色定权聚类的判定准确率分别为78%和94%；相较于后两种方法，改进方法的安全等级判定精度更高，适用性更优。总体而言，本文提出的评价方法可为自动驾驶准入等政策制定提供支撑。

关键词: 城市交通, 交通安全评价, 灰色聚类模型, 智能网联混驾环境, 复杂交织区, 交通冲突

Abstract: This paper proposes an improved grey weighted clustering evaluation method based on traffic conflicts to assess traffic safety in weaving zones under human-vehicle mixed driving environments. The Unmanned Aerial Vehicle (UAV) aerial footage was used to collect vehicle data under congested and free-flowing conditions. Key features like speed, acceleration, lane changes, and rear-end collisions were extracted from the field datasets. A simulation scenario was built on the Simulation of Urban MObility (SUMO) platform, using real-world data to calibrate the behavior of both human-driven and autonomous vehicles. Seven traffic conflict factors, including traffic volume, autonomous vehicle penetration, heavy vehicle ratio, weaving ratio, flow ratio, weaving length, and road grade, were selected for an orthogonal simulation experiment. A negative binomial regression model was used to calculate traffic conflicts. Using the traffic conflict occurrence rate as the evaluation index, an improved safety evaluation method was developed with combination weighting and a sine curve probability function. A simulation comparison was conducted using a typical weaving zone in Chongqing. The results showed that the improved method had a 98% accuracy in determining safety levels, outperforming the linear grey variable-weight clustering (78%) and linear grey weighted clustering (94%). The improved method demonstrated higher accuracy and better applicability. Overall, the proposed method supports policy-making, such as autonomous vehicle admission.

Key words: urban transportation, traffic safety evaluation, grey clustering model, connected and autonomous vehicle mixed traffic environment, complex weaving area, traffic conflict

中图分类号:

U491.2

蔡晓禹, 聂成, 雷财林, 彭博, 谢青雨. 人机混驾环境下山地城市交织区交通安全评价方法[J]. 交通运输系统工程与信息, 2026, 26(1): 270-282.

CAI Xiaoyu, NIE Cheng, LEI Cailin, PENG Bo, XIE Qingyu. Traffic Safety Evaluation Method for Mountainous Urban Interchange Areas in Human-Vehicle Mixed Driving Environments[J]. Journal of Transportation Systems Engineering and Information Technology, 2026, 26(1): 270-282.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/10.16097/j.cnki.1009-6744.2026.01.025

http://www.tseit.org.cn/CN/Y2026/V26/I1/270

参考文献

[1] LI T, HAN X, MA J, et al. Operational safety of automated and human driving in mixed traffic environments: A perspective of car-following behavior [J]. Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability, 2023, 237(2): 355-366.

[2]MA Z, ZHANG Y. Driver-automated vehicle interaction in mixed traffic: Types of interaction and drivers' driving styles [J]. Human Factors, 2024, 66(2): 544-561.

[3]CIRILLO J A. The relationship of accidents to length of speed-change lanes and weaving areas on interstate highways[J]. Highway Research Record, 1970, 312: 17-32.

[4]MANNER H, WüNSCH-ZIEGLER L. Analyzing the severity of accidents on the German Autobahn[J]. Accident Analysis & Prevention, 2013, 57: 40-48.

[5]钟连德,孙小端,陈永胜,等.高速公路大、小车速度差与事故率的关系[J]. 北京工业大学学报, 2007(2): 185-188. [ZHONG L D, SUN X D, CHEN YS, et al. Relationship between speed difference of large and small vehicles and accident rate on expressways[J]. Journal of Beijing University of Technology, 2007(2): 185-188.]

[6]FAZIO J, HOLDEN J, ROUPHAIL N M. Use of freeway conflict rates as an alternative to crash rates in weaving section safety analyses[J]. Transportation Research Record, 1993, 1401: 61.

[7]DAVIS G A, HOURDOS J, XIONG H, et al. Outline for a causal model of traffic conflicts and crashes[J]. Accident Analysis & Prevention, 2011, 43(6): 1907-1919.

[8]迟佳欣,贺玉龙.基于交通冲突的交织区安全评价方法研究[J]. 交通科技与经济,2020, 22(4): 27-32, 38. [CHI J X, HE Y L. Safety evaluation method for weaving sections based on traffic conflicts[J]. Traffic Science and Economy, 2020, 22(4): 27-32, 38.]

[9]YAO Z, HU R, JIANG Y, et al. Stability and safety evaluation of mixed traffic flow with connected automated vehicles on expressways[J]. Journal of Safety Research, 2020, 75: 262-274.

[10] JIANG Y, REN T, MA Y, et al. Traffic safety evaluation of mixed traffic flow considering the maximum platoon size of connected automated vehicles[J]. Physica A: Statistical Mechanics and its Applications, 2023, 612: 128452.

[11] GARG M, BOUROCHE M. Can connected autonomous vehicles improve mixed traffic safety without compromising efficiency in realistic scenarios?[J]. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(6): 6674-6689.

[12] CEN B L, XUE Y, ZHANG K, et al. Study on traffic flows with connected vehicles and human-driven vehicles[J]. Applied Mathematics and Computation, 2025, 490: 129182.

[13] 杜文举, 赵尚飞,李引珍,等.考虑前后多车的混合交通流稳定性与安全性分析[J].交通运输系统工程与信息, 2024, 24(6): 206-218. [DU W J, ZHAO S F, LI Y Z, et al. Stability and safety analysis of mixed traffic flow considering multiple preceding and following vehicles [J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(6): 206-218.]

[14] KUANG X, ZHANG Z. Proceedings of the 4th Asia- Pacific Artificial Intelligence and big data forum[C]. New York: Association for Computing Machinery, 2025: 392-397.

[15] 王健, 温常磊,张香,等.高速公路合流区车辆跟驰行为分车道差异性[J]. 交通运输研究,2020, 6(5): 59- 65, 91. [WANG J, WEN C L, ZHANG X, et al. Lane- based differences in car-following behavior in expressway merging areas[J]. Transport Research, 2020, 6 (5): 59-65, 91.]

[16] 中国公路工程咨询集团有限公司.公路立体交叉设计细则: JTG/T D21-2014 [M]. 北京：人民交通出版社, 2014. [China Highway Engineering Consulting Group Company Ltd. Guidelines for design of highway interchanges: JTG/T D21-2014[S]. Beijing: China Communications Press Co Ltd, 2014.]

[17] HE Y, KONG Y. Traffic impact analysis of expressway accident in mixed traffic environment of connected and autonomous considering multi-factor coupling[J]. IEEE Access, 2025, 13: 57342-57353.

[18] YAVUZ M N, OZEN H. Comprehensive evaluation of the impacts of mixed traffic conditions on urban networks[J]. IEEE Access, 2025, 13: 73408-73429.

[19] 马书红, 陈西芳,杨磊,等.可达性对城市群多模式交通碳排放的空间异质性影响[J].交通运输系统工程与信息, 2024, 24(3): 64-74. [MA S H, CHEN X F, YANG L, et al. Spatial heterogeneous impact of accessibility on multimodal transportation carbon emissions in urban agglomeration[J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(3): 64-74.]

[20] 杨鸣.基于综合指数模型的交通强国建设状态评估研究[D]. 北京: 清华大学, 2019. [YANG M. Research on the status assessment of building a leading transportation country based on a comprehensive index model[D]. Beijing: Tsinghua University, 2019.]

人机混驾环境下山地城市交织区交通安全评价方法

Traffic Safety Evaluation Method for Mountainous Urban Interchange Areas in Human-Vehicle Mixed Driving Environments

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]	郭瑞军, 盛诣皓, 姜凯宁, 郝梓彤. 基于约束卡尔曼滤波的信控干线动态OD估计[J]. 交通运输系统工程与信息, 2026, 26(1): 55-64.
[2]	苑少伟, 高维, 徐一康. 降雨扰动下外卖配送系统韧性度量方法[J]. 交通运输系统工程与信息, 2026, 26(1): 239-251.
[3]	谷远利, 武志磊, 宇泓儒, 杨澄璐. 社区-客流耦合视角下城市轨道交通网络脆弱性评估[J]. 交通运输系统工程与信息, 2026, 26(1): 340-350.
[4]	惠英, 王坪烨, 刘宇良, 余庆. 共享单车内循环区视角下的调度评估与分类管控[J]. 交通运输系统工程与信息, 2026, 26(1): 351-359.
[5]	张涛, 宋彤彤, 程龙, 贾庆林. 生命周期视角下建成环境对居民出行强度的影响机制[J]. 交通运输系统工程与信息, 2025, 25(6): 109-117.
[6]	牟亮, 康彧瑞, 闫梓续, 朱广宇. 考虑数据和模型不确定性的城轨线网客流短时预测方法[J]. 交通运输系统工程与信息, 2025, 25(6): 118-128.
[7]	朱昌锋, 高硕悦, 王傑, 符云琪, 成琳娜, 匡荣杰. 考虑乘客出行特性的城轨与市域铁路贯通运营开行方案研究[J]. 交通运输系统工程与信息, 2025, 25(6): 129-142.
[8]	刘斌, 赵靳辉, 田志强, 马超凡, 梁辉, 李和壁. 基于灵活编组的城市轨道交通大小交路列车开行方案优化[J]. 交通运输系统工程与信息, 2025, 25(6): 143-152.
[9]	张龙豪, 徐瑞华, 单奕嘉, 蓝阳泽. 网络整体效能导向的城轨线路运能协同优化配置[J]. 交通运输系统工程与信息, 2025, 25(6): 153-164.
[10]	闫菲, 姚向明, 韩梅, 陈超, 赵鹏. 跨线运营模式下城轨列车运行图协同编制模型[J]. 交通运输系统工程与信息, 2025, 25(6): 165-174.
[11]	刘晨辉, 陶梦鑫. 基于自动售检票数据的地铁换乘站换乘时间分析[J]. 交通运输系统工程与信息, 2025, 25(6): 175-184.
[12]	李贵阳, 谢秉磊, 李晓丹. 考虑公交替代效应的城市轨道交通网络级联失效分析[J]. 交通运输系统工程与信息, 2025, 25(6): 185-196.
[13]	张立业, 马月熙, 马志成, 赵丰磊, 焦春硕. 地铁突发事件中行李遗弃与结伴行为对疏散效能的耦合影响[J]. 交通运输系统工程与信息, 2025, 25(6): 197-208.
[14]	王连震, 庄涵颖, 王宇萍, 王宝杰. 考虑空间认知能力和恐慌传播的地铁车站应急疏散模型[J]. 交通运输系统工程与信息, 2025, 25(6): 209-219.
[15]	赵樱, 梁金鹏, 鲍月. 考虑乘客换乘的校园公交线路设计优化[J]. 交通运输系统工程与信息, 2025, 25(6): 220-228.