期刊检索

  • 2024年第56卷
  • 2023年第55卷
  • 2022年第54卷
  • 2021年第53卷
  • 2020年第52卷
  • 2019年第51卷
  • 2018年第50卷
  • 2017年第49卷
  • 2016年第48卷
  • 2015年第47卷
  • 2014年第46卷
  • 2013年第45卷
  • 2012年第44卷
  • 2011年第43卷
  • 2010年第42卷
  • 第1期
  • 第2期

主管单位 中华人民共和国
工业和信息化部
主办单位 哈尔滨工业大学 主编 李隆球 国际刊号ISSN 0367-6234 国内刊号CN 23-1235/T

期刊网站二维码
微信公众号二维码
引用本文:朱顺应,邹禾,蒋若曦,肖文彬,王红.高速公路施工区合流路段交通冲突模型[J].哈尔滨工业大学学报,2020,52(9):70.DOI:10.11918/201903133
ZHU Shunying,ZOU He,JIANG Ruoxi,XIAO Wenbin,WANG Hong.Traffic conflict model for confluence section in highway construction area[J].Journal of Harbin Institute of Technology,2020,52(9):70.DOI:10.11918/201903133
【打印本页】   【HTML】   【下载PDF全文】   查看/发表评论  下载PDF阅读器  关闭
过刊浏览    高级检索
本文已被:浏览 2020次   下载 1103 本文二维码信息
码上扫一扫!
分享到: 微信 更多
高速公路施工区合流路段交通冲突模型
朱顺应,邹禾,蒋若曦,肖文彬,王红
(武汉理工大学 交通学院,武汉 430000)
摘要:
为了对高速公路施工区合流路段交通冲突进行微观分析以及探索交通冲突技术在无人驾驶领域的应用,采集12个交通微观信息变量数据作为训练集,结合先验知识,建立了贝叶斯网络模型并采用交叉验证方式评估模型精确度. 结果表明:大车作为冲突主体车辆会导致交通冲突概率和冲突严重性上升;与冲突两车的前后相邻车辆会对两车的冲突有一定影响;当车辆采取超车行为时,会提升车辆发生交通冲突的概率;匝道合流路段发生交通冲突的概率和严重性较转幅路段更高. 采用建立的贝叶斯网络交通冲突模型对驾驶策略进行评估并提出冲突规避措施,如分流大车;在特定路段采取管制措施禁止超车,限制单车道长度,设置车距确认设施等.
关键词:  高速公路施工区  合流路段  交通冲突  贝叶斯网络  多车交互作用  驾驶策略评估
DOI:10.11918/201903133
分类号:U491
文献标识码:A
基金项目:国家自然科学基金(71771183)
Traffic conflict model for confluence section in highway construction area
ZHU Shunying,ZOU He,JIANG Ruoxi,XIAO Wenbin,WANG Hong
(School of Transportation, Wuhan University of Technology, Wuhan 430000, China)
Abstract:
For the microscopic analysis of road traffic conflicts in confluence sections of highway construction area and to explore the application of traffic conflict technology in the field of unmanned driving, 12 variables of microscopic traffic information were collected as training set. The Bayesian network model was established combined with prior knowledge, and the precision of the model was evaluated by using cross validation method. Results show that large vehicles, as the main body of the conflict, could lead to the increase of the probability and severity of traffic conflicts. The preceding and following vehicles of two conflict vehicles had certain impact on the collision between the two vehicles. Overtaking behavior increased the probability of traffic conflicts. The probability and severity of traffic conflicts were higher in ramp merging sections than in turning sections. The proposed Bayesian network traffic conflict model was used to evaluate driving strategies, and conflict avoidance measures were put forward, such as diverging large vehicles. In certain road sections, it is suggested to take control measures to prohibit overtaking, limit the length of a single lane, set up distance confirmation facilities, and so on.
Key words:  highway construction area  confluence section  traffic conflict  Bayesian networks  multiple vehicle interaction  driving strategy assessment

友情链接LINKS