Article(id=1153978731459764987, tenantId=1146029695717560320, journalId=1152916057816748034, issueId=1153978730306331381, articleNumber=null, orderNo=null, doi=10.3969/j.issn.2095-1469.2024.03.04, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1702915200000, receivedDateStr=2023-12-19, revisedDate=1711382400000, revisedDateStr=2024-03-26, acceptedDate=null, acceptedDateStr=null, onlineDate=1753059569468, onlineDateStr=2025-07-21, pubDate=null, pubDateStr=null, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1753059569468, onlineIssueDateStr=2025-07-21, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1753059569468, creator=13701087609, updateTime=1753059569468, updator=13701087609, issue=Issue{id=1153978730306331381, tenantId=1146029695717560320, journalId=1152916057816748034, year='2024', volume='14', issue='3', pageStart='321', pageEnd='552', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=0, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1753059569193, creator=13701087609, updateTime=1757481634700, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1172526217405280450, tenantId=1146029695717560320, journalId=1152916057816748034, issueId=1153978730306331381, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1172526217405280451, tenantId=1146029695717560320, journalId=1152916057816748034, issueId=1153978730306331381, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=363, endPage=375, ext={EN=ArticleExt(id=1153978731883389695, articleId=1153978731459764987, tenantId=1146029695717560320, journalId=1152916057816748034, language=EN, title=Research on Testing and Evaluation of ADAS Systems in Lane Change Cut-in Scenarios, columnId=1153978731191329527, journalTitle=Chinese Journal of Automotive Engineering, columnName=Intelligent Safety/Security Technologies and Test/Evaluation, runingTitle=null, highlight=null, articleAbstract=

To meet the requirements for testing and evaluating ADAS systems in lane change cutin scenarios, the paper proposes a method for generating such scenarios and an objective, comprehensive evaluation model considering the scenario risk coefficients. By collecting natural driving data, the threshold method is used to automatically extract lane change cutin function scenarios and deeply analyze the lane change cutin behavior characteristics. The correlation between scenario risk coefficients and scenario elements is jointly analyzed using oneway ANOVA and Pearson's correlation test to identify key scenario elements. Furthermore, by applying the Kmeans clustering method to the parameters of discrete logic scenarios, five typical test scenarios are obtained. Based on the scenario risk coefficient, the AHP and CRITIC methods are used to construct a multilevel comprehensive evaluation model. The ADAS system is objectively evaluated using the gray correlation theory. Finally, the VTD simulation software is used to create a virtual test scene library for lane change cutin scenarios for simulation testing and validation. The results show that correlation analysis reduces the dimensionality of scenario elements by 60%. The generated test scenarios can effectively validate the comprehensive performance of the ADAS system. Moreover, the comprehensive evaluation model can objectively and effectively evaluate the performance of the ADAS system, providing a valuable reference for the development of intelligent driving systems.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Yue SONG, Jie ZENG, Xiong HU, Weizhen LIU, Wenli LI), CN=ArticleExt(id=1153978782395392210, articleId=1153978731459764987, tenantId=1146029695717560320, journalId=1152916057816748034, language=CN, title=变道切入场景下ADAS 系统测试与评价研究, columnId=1153978731333935865, journalTitle=汽车工程学报, columnName=智能安全技术及其测评, runingTitle=null, highlight=null, articleAbstract=

为了满足变道切入场景下的ADAS系统测试评价需求,提出一种考虑场景风险系数的变道切入场景生成方法和客观综合评价模型。通过采集自然驾驶数据,采用阈值法自动提取变道切入功能场景并深入分析变道切入行为特征。使用单因素方差分析法与皮尔逊相关性检验法共同分析场景风险系数与场景要素的相关性来确定关键场景要素。结合Kmeans算法对离散逻辑场景参数进行聚类,从而得到5个典型测试场景。基于场景风险系数,采用AHP与CRITIC法构建多层次综合评价模型,采用灰色关联理论对ADAS系统进行客观评价。借助VTD仿真软件构建变道切入虚拟测试场景库,进行仿真试验验证。结果表明,相关性分析使场景要素维度降低了60%,生成的测试场景可以有效验证ADAS系统的综合性能,综合评价模型可对ADAS系统表现进行客观有效的评价,为智能驾驶系统开发提供有效参考。

, correspAuthors=null, authorNote=null, correspAuthorsNote=

李文礼(1983-),男,河南驻马店人,博士,副教授,主要研究方向为智能网联汽车测试与评价。Tel: 023-68667370 E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=0dc0nTwn2D28fxpmylZ/5g==, magXml=rgRoR+RyfnMKZot/Bm4L8A==, pdfUrl=null, pdf=YksNyPpCATZfY2Al050cQw==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=3GG7APsd2ehcTeBGaxRCag==, mapNumber=null, authorCompany=null, fund=null, authors=

宋越(1999-),男,河南开封人,硕士研究生,主要研究方向为智能网联汽车测试与评价。Tel: 13693783908 E-mail:

, authorsList=宋越, 曾杰, 胡雄, 刘维镇, 李文礼)}, authors=[Author(id=1153978783351693554, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=Songyue@stu.cqut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1153978783422996724, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, authorId=1153978783351693554, language=EN, stringName=Yue SONG, firstName=Yue, middleName=null, lastName=SONG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Key Laboratory of Advanced Manufacture Technology for Automobile Parts, Ministry of Education Chongqing University of Technology Chongqing 400054 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1153978783485911288, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, authorId=1153978783351693554, language=CN, stringName=宋越, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 重庆理工大学 汽车零部件先进制造技术教育部重点实验室 重庆 400054, bio={"img":"Ndnt/51LjJXXcgsBXBzziw==","content":"

宋越(1999-),男,河南开封人,硕士研究生,主要研究方向为智能网联汽车测试与评价。Tel: 13693783908 E-mail:

"}, bioImg=Ndnt/51LjJXXcgsBXBzziw==, bioContent=

宋越(1999-),男,河南开封人,硕士研究生,主要研究方向为智能网联汽车测试与评价。Tel: 13693783908 E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1153978783183921383, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, xref=1, ext=[AuthorCompanyExt(id=1153978783192309992, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, companyId=1153978783183921383, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Key Laboratory of Advanced Manufacture Technology for Automobile Parts, Ministry of Education Chongqing University of Technology Chongqing 400054 China), AuthorCompanyExt(id=1153978783204892908, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, companyId=1153978783183921383, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 重庆理工大学 汽车零部件先进制造技术教育部重点实验室 重庆 400054)])]), Author(id=1153978783544631549, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1153978783620129024, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, authorId=1153978783544631549, language=EN, stringName=Jie ZENG, firstName=Jie, middleName=null, lastName=ZENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 China Merchants Testing Vehicle Technology Research Institute Co., Ltd. Chongqing 401122 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1153978783687237891, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, authorId=1153978783544631549, language=CN, stringName=曾杰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 招商局检测车辆技术研究院有限公司 重庆 401122, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1153978783284584686, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, xref=2, ext=[AuthorCompanyExt(id=1153978783292973292, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, companyId=1153978783284584686, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 China Merchants Testing Vehicle Technology Research Institute Co., Ltd. Chongqing 401122 China), AuthorCompanyExt(id=1153978783297167597, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, companyId=1153978783284584686, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 招商局检测车辆技术研究院有限公司 重庆 401122)])]), Author(id=1153978783741763846, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1153978783808872713, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, authorId=1153978783741763846, language=EN, stringName=Xiong HU, firstName=Xiong, middleName=null, lastName=HU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 China Merchants Testing Vehicle Technology Research Institute Co., Ltd. Chongqing 401122 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1153978783871787275, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, authorId=1153978783741763846, language=CN, stringName=胡雄, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 招商局检测车辆技术研究院有限公司 重庆 401122, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1153978783284584686, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, xref=2, ext=[AuthorCompanyExt(id=1153978783292973292, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, companyId=1153978783284584686, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 China Merchants Testing Vehicle Technology Research Institute Co., Ltd. Chongqing 401122 China), AuthorCompanyExt(id=1153978783297167597, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, companyId=1153978783284584686, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 招商局检测车辆技术研究院有限公司 重庆 401122)])]), Author(id=1153978783947284750, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1153978784035365137, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, authorId=1153978783947284750, language=EN, stringName=Weizhen LIU, firstName=Weizhen, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Key Laboratory of Advanced Manufacture Technology for Automobile Parts, Ministry of Education Chongqing University of Technology Chongqing 400054 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1153978784102474004, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, authorId=1153978783947284750, language=CN, stringName=刘维镇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 重庆理工大学 汽车零部件先进制造技术教育部重点实验室 重庆 400054, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1153978783183921383, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, xref=1, ext=[AuthorCompanyExt(id=1153978783192309992, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, companyId=1153978783183921383, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Key Laboratory of Advanced Manufacture Technology for Automobile Parts, Ministry of Education Chongqing University of Technology Chongqing 400054 China), AuthorCompanyExt(id=1153978783204892908, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, companyId=1153978783183921383, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 重庆理工大学 汽车零部件先进制造技术教育部重点实验室 重庆 400054)])]), Author(id=1153978784177971480, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=liwenli999@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1153978784270246174, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, authorId=1153978784177971480, language=EN, stringName=Wenli LI, firstName=Wenli, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Key Laboratory of Advanced Manufacture Technology for Automobile Parts, Ministry of Education Chongqing University of Technology Chongqing 400054 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1153978784333160737, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, authorId=1153978784177971480, language=CN, stringName=李文礼, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 重庆理工大学 汽车零部件先进制造技术教育部重点实验室 重庆 400054, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1153978783183921383, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, xref=1, ext=[AuthorCompanyExt(id=1153978783192309992, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, companyId=1153978783183921383, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Key Laboratory of Advanced Manufacture Technology for Automobile Parts, Ministry of Education Chongqing University of Technology Chongqing 400054 China), AuthorCompanyExt(id=1153978783204892908, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, companyId=1153978783183921383, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 重庆理工大学 汽车零部件先进制造技术教育部重点实验室 重庆 400054)])])], keywords=[Keyword(id=1153978784622567729, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, orderNo=1, keyword=lane change cut-in scenario), Keyword(id=1153978784689676594, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, orderNo=2, keyword=ADAS system), Keyword(id=1153978784748396852, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, orderNo=3, keyword=natural driving data), Keyword(id=1153978784865837367, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, orderNo=4, keyword=gray correlation theory), Keyword(id=1153978784932946234, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, orderNo=5, keyword=objective evaluation), Keyword(id=1153978785000055099, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, orderNo=1, keyword=变道切入场景), Keyword(id=1153978785046192444, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, orderNo=2, keyword=ADAS系统), Keyword(id=1153978785096524094, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, orderNo=3, keyword=自然驾驶数据), Keyword(id=1153978785151050049, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, orderNo=4, keyword=灰色关联理论), Keyword(id=1153978785209770308, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, orderNo=5, keyword=客观评价)], refs=[Reference(id=1153978789945139701, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2017, volume=18, issue=3, pageStart=595, pageEnd=607, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=ZHAO Ding, LAM H, PENG H, journalName=IEEE Transactions on Intelligent Transportation Systems, refType=null, unstructuredReference=ZHAO Ding, LAM H, PENG H, et al. Accelerated Evaluation of Automated Vehicles Safety in Lane-Change Scenarios Based on Importance Sampling Techniques[J]. IEEE Transactions on Intelligent Transportation Systems, 2017,18(3):595-607., articleTitle=Accelerated Evaluation of Automated Vehicles Safety in Lane-Change Scenarios Based on Importance Sampling Techniques, refAbstract=null), Reference(id=1153978789995471352, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=99, pageStart=1, pageEnd=11, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=ZHAO Chunqing, WANG Wenshuo, LI Shaopeng, journalName=IEEE Transactions on Intelligent Transportation Systems, refType=null, unstructuredReference=ZHAO Chunqing, WANG Wenshuo, LI Shaopeng, et al. Influence of Cut-in Maneuvers for an Autonomous Car on Surrounding Drivers: Experiment and Analysis[J]. IEEE Transactions on Intelligent Transportation Systems, 2020(99):1-11., articleTitle=Influence of Cut-in Maneuvers for an Autonomous Car on Surrounding Drivers: Experiment and Analysis, refAbstract=null), Reference(id=1153978790054191610, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2014, volume=31, issue=6, pageStart=121, pageEnd=126, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=孟祥海, 郑来, 史永义, journalName=公路交通科技, refType=null, unstructuredReference=孟祥海, 郑来, 史永义. 考虑车道变换影响的高速公路交通事故预测模型研究[J]. 公路交通科技, 2014,31(6):121-126., articleTitle=考虑车道变换影响的高速公路交通事故预测模型研究, refAbstract=null), Reference(id=1153978790100328955, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2014, volume=31, issue=6, pageStart=121, pageEnd=126, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=MENG Xianghai, ZHENG Lai, SHI Yongyi, journalName=Journal of Highway and Transportation Research and Development, refType=null, unstructuredReference=MENG Xianghai, ZHENG Lai, SHI Yongyi. Research on Accident Prediction Models for Freeways Considering Effect of Lane Change Maneuvers[J]. Journal of Highway and Transportation Research and Development, 2014,31(6):121-126. (in Chinese), articleTitle=Research on Accident Prediction Models for Freeways Considering Effect of Lane Change Maneuvers, refAbstract=null), Reference(id=1153978790167437821, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2024, volume=9, issue=1, pageStart=1079, pageEnd=1093, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=LI Wenli, QIU Fanke, LI Lingxi, journalName=IEEE Trans-actions on Intelligent Vehicles, refType=null, unstructuredReference=LI Wenli, QIU Fanke, LI Lingxi, et al. Simulation of Vehicle Interaction Behavior in Merging Scenarios: A Deep Maximum Entropy-Inverse Reinforcement Learning Method Combined with Game Theory[J]. IEEE Trans-actions on Intelligent Vehicles, 2024,9(1):1079-1093., articleTitle=Simulation of Vehicle Interaction Behavior in Merging Scenarios: A Deep Maximum Entropy-Inverse Reinforcement Learning Method Combined with Game Theory, refAbstract=null), Reference(id=1153978790230352383, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2022, volume=35, issue=1, pageStart=316, pageEnd=333, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=邓伟文, 李江坤, 任秉韬, journalName=中国公路学报, refType=null, unstructuredReference=邓伟文, 李江坤, 任秉韬, 等. 面向自动驾驶的仿真场景自动生成方法综述[J]. 中国公路学报, 2022,35(1):316-333., articleTitle=面向自动驾驶的仿真场景自动生成方法综述, refAbstract=null), Reference(id=1153978790280684033, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2022, volume=35, issue=1, pageStart=316, pageEnd=333, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=DENG Weiwen, LI Jiangkun, REN Bingtao, journalName=China Journal of Highway and Transport, refType=null, unstructuredReference=DENG Weiwen, LI Jiangkun, REN Bingtao, et al. A Survey on Automatic Simulation Scenario Generation Methods for Autonomous Driving[J]. China Journal of Highway and Transport, 2022,35(1):316-333. (in Chinese), articleTitle=A Survey on Automatic Simulation Scenario Generation Methods for Autonomous Driving, refAbstract=null), Reference(id=1153978790351987203, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=夏芹, journalName=null, refType=null, unstructuredReference=夏芹. 面向智能驾驶系统的仿真场景生成及测试方法研究[D]. 重庆: 重庆大学, 2021., articleTitle=面向智能驾驶系统的仿真场景生成及测试方法研究, refAbstract=null), Reference(id=1153978790414901765, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=XIA Qin, journalName=null, refType=null, unstructuredReference=XIA Qin. Study on Simulation Scenario Generation and Test Method for Intelligent Driving System[D]. Chongqing: Chongqing University, 2021. (in Chinese), articleTitle=Study on Simulation Scenario Generation and Test Method for Intelligent Driving System, refAbstract=null), Reference(id=1153978790494593543, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2018, volume=46, issue=8, pageStart=1057, pageEnd=1063, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=王雪松, 杨敏明, journalName=同济大学学报(自然科学版), refType=null, unstructuredReference=王雪松, 杨敏明. 基于自然驾驶数据的变道切入行为分析[J]. 同济大学学报(自然科学版), 2018,46(8):1057-1063., articleTitle=基于自然驾驶数据的变道切入行为分析, refAbstract=null), Reference(id=1153978790582673929, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2018, volume=46, issue=8, pageStart=1057, pageEnd=1063, url=null, language=null, rfNumber=[7], rfOrder=10, authorNames=WANG Xuesong, YANG Minming, journalName=Journal of Tongji University (Natural Science), refType=null, unstructuredReference=WANG Xuesong, YANG Minming. Cut-in Behavior Analyses Based on Naturalistic Driving Data[J]. Journal of Tongji University (Natural Science), 2018,46(8):1057-1063. (in Chinese), articleTitle=Cut-in Behavior Analyses Based on Naturalistic Driving Data, refAbstract=null), Reference(id=1153978790653977099, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2020, volume=48, issue=1, pageStart=51, pageEnd=59, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=王雪松, 徐晓妍, journalName=同济大学学报(自然科学版), refType=null, unstructuredReference=王雪松, 徐晓妍. 基于自然驾驶数据的危险事件识别方法[J]. 同济大学学报(自然科学版), 2020,48(1):51-59., articleTitle=基于自然驾驶数据的危险事件识别方法, refAbstract=null), Reference(id=1153978790725280271, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2020, volume=48, issue=1, pageStart=51, pageEnd=59, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=WANG Xuesong, XU Xiaoyan, journalName=Journal of Tongji University (Natural Science), refType=null, unstructuredReference=WANG Xuesong, XU Xiaoyan. Detection of Safety-Critical Events Based on Naturalistic Driving Data[J]. Journal of Tongji University (Natural Science), 2020,48(1):51-59. (in Chinese), articleTitle=Detection of Safety-Critical Events Based on Naturalistic Driving Data, refAbstract=null), Reference(id=1153978790796583443, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2002, volume=46, issue=22, pageStart=1789, pageEnd=1793, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=OLSEN ECB, LEES E, WIERWILLE W W, journalName=Human Factors & Ergonomics Society Annual Meeting Proceedings, refType=null, unstructuredReference=OLSEN ECB, LEES E, WIERWILLE W W, et al. Analysis of Distribution, Frequency, and Duration of Naturalistic Lane Changes[J]. Human Factors & Ergonomics Society Annual Meeting Proceedings, 2002,46(22):1789-1793., articleTitle=Analysis of Distribution, Frequency, and Duration of Naturalistic Lane Changes, refAbstract=null), Reference(id=1153978790859498006, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2015, volume=55, issue=7, pageStart=769, pageEnd=774, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=丁洁云, 党睿娜, 王建强, journalName=清华大学学报(自然科学版), refType=null, unstructuredReference=丁洁云, 党睿娜, 王建强, 等. 驾驶人换道决策分析及意图识别算法设计[J]. 清华大学学报(自然科学版), 2015,55(7):769-774., articleTitle=驾驶人换道决策分析及意图识别算法设计, refAbstract=null), Reference(id=1153978790939189785, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2015, volume=55, issue=7, pageStart=769, pageEnd=774, url=null, language=null, rfNumber=[10], rfOrder=15, authorNames=DING Jieyun, DANG Ruina, WANG Jianqiang, journalName=Journal of Tsinghua University (Natural Science Edition), refType=null, unstructuredReference=DING Jieyun, DANG Ruina, WANG Jianqiang, et al. Driver Lane Change Decision Analysis and Intention Recognition Algorithm Design[J]. Journal of Tsinghua University (Natural Science Edition), 2015,55(7):769-774. (in Chinese), articleTitle=Driver Lane Change Decision Analysis and Intention Recognition Algorithm Design, refAbstract=null), Reference(id=1153978791002104348, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2007, volume=1999, issue=1, pageStart=71, pageEnd=78, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=TOLEDO T, ZOHAR D, journalName=Transportation Research Record: Journal of the Transportation Research Board, refType=null, unstructuredReference=TOLEDO T, ZOHAR D. Modeling Duration of Lane Changes[J]. Transportation Research Record: Journal of the Transportation Research Board, 2007,1999(1):71-78., articleTitle=Modeling Duration of Lane Changes, refAbstract=null), Reference(id=1153978791056630304, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2013, volume=null, issue=null, pageStart=1917, pageEnd=1922, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=DANG Ruina, ZHANG Fang, WANG Jianqiang, journalName=16th Inter-national IEEE Conference on Intelligent Transportation Systems (ITSC 2013), Oct. 6-9, 2013, The Hague, Netherlands.Piscataway NJ: IEEE, c2013, refType=null, unstructuredReference=DANG Ruina, ZHANG Fang, WANG Jianqiang, et al. Analysis of Chinese Driver's Lane Change Characteristic Based on Real Vehicle Tests in Highway[C]// 16th Inter-national IEEE Conference on Intelligent Transportation Systems (ITSC 2013), Oct. 6-9, 2013, The Hague, Netherlands.Piscataway NJ: IEEE, c2013, 2013:1917-1922., articleTitle=Analysis of Chinese Driver's Lane Change Characteristic Based on Real Vehicle Tests in Highway, refAbstract=null), Reference(id=1153978791132127779, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2021, volume=12, issue=1, pageStart=1, pageEnd=14, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=FENG Shuo, YAN Xintao, SUN Haowei, journalName=Nature Communications, refType=null, unstructuredReference=FENG Shuo, YAN Xintao, SUN Haowei, et al. Intelligent Driving Intelligence Test for Autonomous Vehicles with Naturalistic and Adversarial Environment[J]. Nature Communications, 2021,12(1):1-14., articleTitle=Intelligent Driving Intelligence Test for Autonomous Vehicles with Naturalistic and Adversarial Environment, refAbstract=null), Reference(id=1153978791190848038, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=1, pageEnd=8, url=null, language=null, rfNumber=[14], rfOrder=19, authorNames=PÜTZA, ZLOCKI A, KÜFEN J, journalName=Proceedings of the 25th International Technical Conference on the Enhanced Safety of Vehicles (ESV), June 5-8,2017, Detroit Michigan, US, refType=null, unstructuredReference=PÜTZA, ZLOCKI A, KÜFEN J, et al. Database Approach for the Sign-Off Process of Highly Automated Vehicles[C]// Proceedings of the 25th International Technical Conference on the Enhanced Safety of Vehicles (ESV), June 5-8,2017, Detroit Michigan, US, 2017:1-8., articleTitle=Database Approach for the Sign-Off Process of Highly Automated Vehicles, refAbstract=null), Reference(id=1153978791249568296, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=8, pageStart=10, pageEnd=22, url=null, language=null, rfNumber=[15], rfOrder=20, authorNames=蒋拯民, 党少博, 李慧云, journalName=汽车技术, refType=null, unstructuredReference=蒋拯民, 党少博, 李慧云, 等. 自动驾驶汽车场景测试研究进展综述[J]. 汽车技术, 2022(8):10-22., articleTitle=自动驾驶汽车场景测试研究进展综述, refAbstract=null), Reference(id=1153978791333454380, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=8, pageStart=10, pageEnd=22, url=null, language=null, rfNumber=[15], rfOrder=21, authorNames=JIANG Zhengmin, DANG Shaobo, LI Huiyun, journalName=Automobile Technology, refType=null, unstructuredReference=JIANG Zhengmin, DANG Shaobo, LI Huiyun, et al. A Survey on the Research Progress of Scenario-Based Testing for Autonomous Vehicles[J]. Automobile Technology, 2022(8):10-22. (in Chinese), articleTitle=A Survey on the Research Progress of Scenario-Based Testing for Autonomous Vehicles, refAbstract=null), Reference(id=1153978791413146157, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=22, authorNames=齐先婷, journalName=null, refType=null, unstructuredReference=齐先婷. 基于密度峰值优化的K-means文本聚类算法研究[D]. 武汉: 武汉理工大学, 2018., articleTitle=基于密度峰值优化的K-means文本聚类算法研究, refAbstract=null), Reference(id=1153978791492837935, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=23, authorNames=QI Xianting, journalName=null, refType=null, unstructuredReference=QI Xianting. Research on K-means Text Clustering Algorithm Based on Improved Density Peaks[D]. Wuhan: Wuhan University of Technology, 2018. (in Chinese), articleTitle=Research on K-means Text Clustering Algorithm Based on Improved Density Peaks, refAbstract=null), Reference(id=1153978791585112628, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2018, volume=29, issue=8, pageStart=252, pageEnd=253, url=null, language=null, rfNumber=[17], rfOrder=24, authorNames=郭昱, journalName=农村经济与科技, refType=null, unstructuredReference=郭昱. 权重确定方法综述[J]. 农村经济与科技, 2018,29(8):252-253., articleTitle=权重确定方法综述, refAbstract=null), Reference(id=1153978791652221494, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2018, volume=29, issue=8, pageStart=252, pageEnd=253, url=null, language=null, rfNumber=[17], rfOrder=25, authorNames=GUO Yu, journalName=Rural Economy and Technology, refType=null, unstructuredReference=GUO Yu. Overview of Weight Determination Methods[J]. Rural Economy and Technology, 2018,29(8):252-253. (in Chinese), articleTitle=Overview of Weight Determination Methods, refAbstract=null), Reference(id=1153978791710941753, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2021, volume=57, issue=12, pageStart=99, pageEnd=108, url=null, language=null, rfNumber=[18], rfOrder=26, authorNames=魏子茹, 卢延辉, 王鹏宇, journalName=机械工程学报, refType=null, unstructuredReference=魏子茹, 卢延辉, 王鹏宇, 等. 基于CRITIC法的灰色关联理论在无人驾驶车辆测试评价中的应用[J]. 机械工程学报, 2021,57(12):99-108., articleTitle=基于CRITIC法的灰色关联理论在无人驾驶车辆测试评价中的应用, refAbstract=null), Reference(id=1153978791769662014, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, doi=null, pmid=null, pmcid=null, year=2021, volume=57, issue=12, pageStart=99, pageEnd=108, url=null, language=null, rfNumber=[18], rfOrder=27, authorNames=WEI Ziru, LU Yanhui, WANG Pengyu, journalName=Journal of Mechanical Engineering, refType=null, unstructuredReference=WEI Ziru, LU Yanhui, WANG Pengyu, et al. Application of Grey Correlation Theory Based on CRITIC Method in Autonomous Vehicles Test and Evaluation[J]. Journal of Mechanical Engineering, 2021,57(12):99-108. (in Chinese), articleTitle=Application of Grey Correlation Theory Based on CRITIC Method in Autonomous Vehicles Test and Evaluation, refAbstract=null)], funds=[Fund(id=1153978789546680805, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, awardId=cstc2021jcyj-msxmX0183, language=CN, fundingSource=重庆市自然科学基金面上项目(cstc2021jcyj-msxmX0183), fundOrder=null, country=null), Fund(id=1153978789655732713, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, awardId=CX2021070, language=CN, fundingSource=重庆市留学人员回国创业创新支持计划资助项目(CX2021070), fundOrder=null, country=null), Fund(id=1153978789714452972, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, awardId=KJQN202201170, language=CN, fundingSource=重庆市教委科学技术研究项目(KJQN202201170), fundOrder=null, country=null), Fund(id=1153978789777367535, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, awardId=CSTB2022TIAD-STX0003, language=CN, fundingSource=重庆市技术创新与应用发展专项重大项目(CSTB2022TIAD-STX0003), fundOrder=null, country=null), Fund(id=1153978789848670707, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, awardId=gzlcx20242002, language=CN, fundingSource=重庆市研究生科研创新项目(gzlcx20242002), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1153978783183921383, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, xref=1, ext=[AuthorCompanyExt(id=1153978783192309992, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, companyId=1153978783183921383, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Key Laboratory of Advanced Manufacture Technology for Automobile Parts, Ministry of Education Chongqing University of Technology Chongqing 400054 China), AuthorCompanyExt(id=1153978783204892908, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, companyId=1153978783183921383, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 重庆理工大学 汽车零部件先进制造技术教育部重点实验室 重庆 400054)]), AuthorCompany(id=1153978783284584686, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, xref=2, ext=[AuthorCompanyExt(id=1153978783292973292, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, companyId=1153978783284584686, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 China Merchants Testing Vehicle Technology Research Institute Co., Ltd. Chongqing 401122 China), AuthorCompanyExt(id=1153978783297167597, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, companyId=1153978783284584686, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 招商局检测车辆技术研究院有限公司 重庆 401122)])], figs=[ArticleFig(id=1153978785901830494, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=D4OlRLFCh0Tlq4DOtQZWVg==, figureFileBig=phKOb3ZSjVfpPng9j5YJAA==, tableContent=null), ArticleFig(id=1153978785956356449, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=图 1, caption=自然驾驶数据采集车, figureFileSmall=D4OlRLFCh0Tlq4DOtQZWVg==, figureFileBig=phKOb3ZSjVfpPng9j5YJAA==, tableContent=null), ArticleFig(id=1153978786010882403, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=ADIFnZgRVYfnYlFJPd0Nrw==, figureFileBig=ccKImkQNkrSrVzRK6BDZTw==, tableContent=null), ArticleFig(id=1153978786073796967, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=图 2, caption=变道切入片段关键时刻, figureFileSmall=ADIFnZgRVYfnYlFJPd0Nrw==, figureFileBig=ccKImkQNkrSrVzRK6BDZTw==, tableContent=null), ArticleFig(id=1153978786128322922, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=7GchtdH/obavqXnsZZ6kGg==, figureFileBig=xVCZCbTnWguyEX5SM2Vvyw==, tableContent=null), ArticleFig(id=1153978786191237484, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=图 3, caption=数据预处理前后对比, figureFileSmall=7GchtdH/obavqXnsZZ6kGg==, figureFileBig=xVCZCbTnWguyEX5SM2Vvyw==, tableContent=null), ArticleFig(id=1153978786245763440, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=dChhJHbEiApRFIy1C6kJkQ==, figureFileBig=12h3Ln5MOlOg+r0SUgZ9Cw==, tableContent=null), ArticleFig(id=1153978786317066611, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=图 4, caption=切入车与后随车的相对横向速度, figureFileSmall=dChhJHbEiApRFIy1C6kJkQ==, figureFileBig=12h3Ln5MOlOg+r0SUgZ9Cw==, tableContent=null), ArticleFig(id=1153978786388369782, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=gwnsbjH1syMaTqSTqZC7dw==, figureFileBig=FlNzg87j/2n54OaARFu0mw==, tableContent=null), ArticleFig(id=1153978786438701434, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=图 5, caption=变道切入过程横向间距变化及关键时刻, figureFileSmall=gwnsbjH1syMaTqSTqZC7dw==, figureFileBig=FlNzg87j/2n54OaARFu0mw==, tableContent=null), ArticleFig(id=1153978786522587516, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=VnN2oD2kGgR0MXWe1rpX1Q==, figureFileBig=L9+Km6wXeKFRG5ss+qQLbQ==, tableContent=null), ArticleFig(id=1153978786585502077, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=图 6, caption=场景风险系数分布, figureFileSmall=VnN2oD2kGgR0MXWe1rpX1Q==, figureFileBig=L9+Km6wXeKFRG5ss+qQLbQ==, tableContent=null), ArticleFig(id=1153978786640028032, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=kp9H8+DdKEr7WSvcI0L/aA==, figureFileBig=wXgyGAcooIExzTGKpG8a5Q==, tableContent=null), ArticleFig(id=1153978786707136899, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=图 7, caption=变道切入持续时间分布, figureFileSmall=kp9H8+DdKEr7WSvcI0L/aA==, figureFileBig=wXgyGAcooIExzTGKpG8a5Q==, tableContent=null), ArticleFig(id=1153978786774245766, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=jZDxzBMKRVHPeaRkRcwpSw==, figureFileBig=qw0FJgBimQMXFaMN4dOk8g==, tableContent=null), ArticleFig(id=1153978786828771723, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=图 8, caption=后随车运动受限, figureFileSmall=jZDxzBMKRVHPeaRkRcwpSw==, figureFileBig=qw0FJgBimQMXFaMN4dOk8g==, tableContent=null), ArticleFig(id=1153978786929435022, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=gcN8eGP5bKZhyllpAf6yCA==, figureFileBig=HqpE0Rm46D6X2PPF0CCKDQ==, tableContent=null), ArticleFig(id=1153978786983960975, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=图 9, caption=连续型场景要素分析, figureFileSmall=gcN8eGP5bKZhyllpAf6yCA==, figureFileBig=HqpE0Rm46D6X2PPF0CCKDQ==, tableContent=null), ArticleFig(id=1153978787034292626, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=2E2etvEF2PH49oIBcKbntw==, figureFileBig=MDwdQC6hChUGcdOTZdkFxA==, tableContent=null), ArticleFig(id=1153978787105595796, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=图 10, caption=ADAS 系统评价指标体系, figureFileSmall=2E2etvEF2PH49oIBcKbntw==, figureFileBig=MDwdQC6hChUGcdOTZdkFxA==, tableContent=null), ArticleFig(id=1153978787155927446, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=BxyyBNz3yAlRNVz7MuNGPA==, figureFileBig=o8csVDcZqD9JOo2A1XaSVw==, tableContent=null), ArticleFig(id=1153978787214647704, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=图 11, caption=仿真测试试验, figureFileSmall=BxyyBNz3yAlRNVz7MuNGPA==, figureFileBig=o8csVDcZqD9JOo2A1XaSVw==, tableContent=null), ArticleFig(id=1153978787281756571, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
关键时刻 含义
开始时刻 $\left( {T}_{\text{start }}\right)$ 随着切入车辆横向速度增加,切入车与后随车相对横向速度绝对值达到 ${0.3}\mathrm{\;m}/\mathrm{s}$
切入时刻 $\left( {T}_{\text{cross }}\right)$ ${T}_{\text{start }}$ 时刻之后,切入车辆的几何中心覆盖目标车道边线时
结束时刻 $\left( {T}_{\text{end }}\right)$ 随着切入车辆横向速度减小,切入车与后随车相对横向速度绝对值达到 ${0.2}\mathrm{\;m}/\mathrm{s}$
), ArticleFig(id=1153978787357254045, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=表 1, caption=变道切入片段关键时刻, figureFileSmall=null, figureFileBig=null, tableContent=
关键时刻 含义
开始时刻 $\left( {T}_{\text{start }}\right)$ 随着切入车辆横向速度增加,切入车与后随车相对横向速度绝对值达到 ${0.3}\mathrm{\;m}/\mathrm{s}$
切入时刻 $\left( {T}_{\text{cross }}\right)$ ${T}_{\text{start }}$ 时刻之后,切入车辆的几何中心覆盖目标车道边线时
结束时刻 $\left( {T}_{\text{end }}\right)$ 随着切入车辆横向速度减小,切入车与后随车相对横向速度绝对值达到 ${0.2}\mathrm{\;m}/\mathrm{s}$
), ArticleFig(id=1153978787420168607, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
道路类型 场景数量
高速公路 10
内环快速 50
城市道路 32
), ArticleFig(id=1153978787483083170, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=表 2, caption=不同道路类型场景数量, figureFileSmall=null, figureFileBig=null, tableContent=
道路类型 场景数量
高速公路 10
内环快速 50
城市道路 32
), ArticleFig(id=1153978787545997732, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
TTC值 危险等级
${t}_{\text{TTC }} > 5\mathrm{\;s}$ 无危险
$3\mathrm{\;s} < {t}_{\mathrm{{TTC}}} \leq 5\mathrm{\;s}$ 紧急
$1\mathrm{\;s} < {t}_{\mathrm{{TTC}}} \leq 3\mathrm{\;s}$ 急迫
${t}_{\text{TTC }} \leq 1\mathrm{\;s}$ 濒临碰撞
), ArticleFig(id=1153978787604717991, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=表 3, caption=基于TTC的场景危险等级划分, figureFileSmall=null, figureFileBig=null, tableContent=
TTC值 危险等级
${t}_{\text{TTC }} > 5\mathrm{\;s}$ 无危险
$3\mathrm{\;s} < {t}_{\mathrm{{TTC}}} \leq 5\mathrm{\;s}$ 紧急
$1\mathrm{\;s} < {t}_{\mathrm{{TTC}}} \leq 3\mathrm{\;s}$ 急迫
${t}_{\text{TTC }} \leq 1\mathrm{\;s}$ 濒临碰撞
), ArticleFig(id=1153978787676021162, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
道路类型 切入车辆类型
高速公路 I类:4 II 类: 6
内环快速 I类:23 II类: 27
城市道路 I类: 15 II类: 17
), ArticleFig(id=1153978787743130030, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=表 4, caption=不同道路类型切入车辆类型, figureFileSmall=null, figureFileBig=null, tableContent=
道路类型 切入车辆类型
高速公路 I类:4 II 类: 6
内环快速 I类:23 II类: 27
城市道路 I类: 15 II类: 17
), ArticleFig(id=1153978787827016112, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
道路类型 左侧切入数量 右侧切入数量
高速公路 2 8
内环快速 12 38
城市道路 13 19
), ArticleFig(id=1153978787889930674, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=表 5, caption=不同道路类型切入方向, figureFileSmall=null, figureFileBig=null, tableContent=
道路类型 左侧切入数量 右侧切入数量
高速公路 2 8
内环快速 12 38
城市道路 13 19
), ArticleFig(id=1153978787948650931, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
道路类型 使用 未使用 使用比例/%
高速公路 4 6 40
内环快速 24 26 48
城市道路 17 15 53
), ArticleFig(id=1153978787994788276, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=表 6, caption=不同道路类型转向灯使用比例, figureFileSmall=null, figureFileBig=null, tableContent=
道路类型 使用 未使用 使用比例/%
高速公路 4 6 40
内环快速 24 26 48
城市道路 17 15 53
), ArticleFig(id=1153978788049314229, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
道路类型 左侧受限数量 右侧受限数量 双侧受限数量
高速公路 6 2 1
内环快速 21 9 13
城市道路 11 15 5
), ArticleFig(id=1153978788103840182, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=表 7, caption=不同道路类型后随车运动受限, figureFileSmall=null, figureFileBig=null, tableContent=
道路类型 左侧受限数量 右侧受限数量 双侧受限数量
高速公路 6 2 1
内环快速 21 9 13
城市道路 11 15 5
), ArticleFig(id=1153978788154171831, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
变道切入行为特征 显著性 齐次性
车辆类型 0.866
切入方向 0.017 不是
转向灯使用 0.095
后随车运动受限 0.465
), ArticleFig(id=1153978788204503480, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=表 8, caption=各因素方差齐次性检验结果, figureFileSmall=null, figureFileBig=null, tableContent=
变道切入行为特征 显著性 齐次性
车辆类型 0.866
切入方向 0.017 不是
转向灯使用 0.095
后随车运动受限 0.465
), ArticleFig(id=1153978788263223737, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
平方和 自由度 均方 F值 显著性
组间 6.432 1 6.432 0.029 0.866
组内 20 252.929 90 225.033
总计 20 259.360 91
), ArticleFig(id=1153978788317749690, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=表 9, caption=不同切入车辆类型下的 ANOVA 分析结果, figureFileSmall=null, figureFileBig=null, tableContent=
平方和 自由度 均方 F值 显著性
组间 6.432 1 6.432 0.029 0.866
组内 20 252.929 90 225.033
总计 20 259.360 91
), ArticleFig(id=1153978788363887035, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
平方和 自由度 均方 F值 显著性
组间 1 244.910 1 1 244.910 5.892 0.017
组内 19 014.451 90 211.272
总计 20 259.360 91
), ArticleFig(id=1153978788405830076, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=表 10, caption=不同切入方向下的 ANOVA 分析结果, figureFileSmall=null, figureFileBig=null, tableContent=
平方和 自由度 均方 F值 显著性
组间 1 244.910 1 1 244.910 5.892 0.017
组内 19 014.451 90 211.272
总计 20 259.360 91
), ArticleFig(id=1153978788477133246, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
平方和 自由度 均方 F值 显著性
组间 621.155 1 621.155 2.847 0.095
组内 19638.205 90 218.202
总计 20 259.360 91
), ArticleFig(id=1153978788548436416, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=表 11, caption=不同转向灯使用情况下的 ANOVA 分析结果, figureFileSmall=null, figureFileBig=null, tableContent=
平方和 自由度 均方 F值 显著性
组间 621.155 1 621.155 2.847 0.095
组内 19638.205 90 218.202
总计 20 259.360 91
), ArticleFig(id=1153978788590379458, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
平方和 自由度 均方 F值 显著性
组间 577.577 3 192.526 0.861 0.465
组内 19681.783 90 223.657
总计 20 259.360 91
), ArticleFig(id=1153978788640711108, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=表 12, caption=不同后随车运动受限情况下的 ANOVA 分析结果, figureFileSmall=null, figureFileBig=null, tableContent=
平方和 自由度 均方 F值 显著性
组间 577.577 3 192.526 0.861 0.465
组内 19681.783 90 223.657
总计 20 259.360 91
), ArticleFig(id=1153978788699431366, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
(m/s) (m/s) (m/s) (m/s) (m/s)
9.840 -1.170 1.246 0.309 7.478 -0.702
17.893 0.132 2.059 0.554 7.215 -0.726
15.759 -0.213 -0.498 -0.218 23.742 0.751
20.455 0.546 -1.229 -0.438 28.682 1.193
17.269 0.031 -0.753 -0.295 9.574 -0.515
20.742 0.593 3.222 0.906 3.804 -1.030
21.404 0.700 -5.610 -1.761 34.247 1.690
), ArticleFig(id=1153978788749763016, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=表 13, caption=标准化后的部分数据对比, figureFileSmall=null, figureFileBig=null, tableContent=
(m/s) (m/s) (m/s) (m/s) (m/s)
9.840 -1.170 1.246 0.309 7.478 -0.702
17.893 0.132 2.059 0.554 7.215 -0.726
15.759 -0.213 -0.498 -0.218 23.742 0.751
20.455 0.546 -1.229 -0.438 28.682 1.193
17.269 0.031 -0.753 -0.295 9.574 -0.515
20.742 0.593 3.222 0.906 3.804 -1.030
21.404 0.700 -5.610 -1.761 34.247 1.690
), ArticleFig(id=1153978788800094666, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
聚类 误差 F值 显著 性
均方 自由 度 均方 自由 度
后随车速度/( $\mathrm{m}/\mathrm{s}$ ) 704.597 3 15.560 88 45.282 0
相对纵向速度/(m/s) 111.287 3 7.552 88 14.737 0
纵向间距/m 3 213.497 3 19.958 88 161.013 0
), ArticleFig(id=1153978788858814924, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=表 14, caption=类簇间差异显著性检验, figureFileSmall=null, figureFileBig=null, tableContent=
聚类 误差 F值 显著 性
均方 自由 度 均方 自由 度
后随车速度/( $\mathrm{m}/\mathrm{s}$ ) 704.597 3 15.560 88 45.282 0
相对纵向速度/(m/s) 111.287 3 7.552 88 14.737 0
纵向间距/m 3 213.497 3 19.958 88 161.013 0
), ArticleFig(id=1153978788925923790, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
典型 场景 占比/% 后随车纵向 速度/(m/s) 相对纵向速 度/( ) 纵向间 距/m 切入 方向
1 30 17.2 -0.3 15.8
2 16 22.3 3.8 5.1
3 16 19.9 -2.2 25.7
4 10 22.7 -3.6 38.6
5 28 10.1 1.5 6.4
), ArticleFig(id=1153978788980449744, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=表 15, caption=典型变道切入场景要素数据, figureFileSmall=null, figureFileBig=null, tableContent=
典型 场景 占比/% 后随车纵向 速度/(m/s) 相对纵向速 度/( ) 纵向间 距/m 切入 方向
1 30 17.2 -0.3 15.8
2 16 22.3 3.8 5.1
3 16 19.9 -2.2 25.7
4 10 22.7 -3.6 38.6
5 28 10.1 1.5 6.4
), ArticleFig(id=1153978789043364306, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
总指标层指标 权重 指标层指标 权重
ADAS 系统评价 行驶安全性 0.48 RC 0.43
车道保持 0.57
乘坐舒适性 0.32 车速标准差 0.20
弯道横向力系数 0.34
纵向加速度峰值 0.24
横摆角速度峰值 0.22
智能性 0.20 感知到切入车的相对距离 0.44
偏移车道中心距最大值 0.56
), ArticleFig(id=1153978789093695957, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=表 16, caption=典型场景评价指标权重, figureFileSmall=null, figureFileBig=null, tableContent=
总指标层指标 权重 指标层指标 权重
ADAS 系统评价 行驶安全性 0.48 RC 0.43
车道保持 0.57
乘坐舒适性 0.32 车速标准差 0.20
弯道横向力系数 0.34
纵向加速度峰值 0.24
横摆角速度峰值 0.22
智能性 0.20 感知到切入车的相对距离 0.44
偏移车道中心距最大值 0.56
), ArticleFig(id=1153978789164999127, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
指标 指标值
典型场景 1 典型场景 2 典型场景 3 典型场景 4 典型场景 5
$\mathrm{{RC}}/\left( {1/\mathrm{s}}\right)$ 0.30 1.13 0.28 -0.34 2.91
车道保持 1 0 1 0 1
车速标准差/(m/s) 0.79 2.47 0.08 0.68 2.32
弯道横向力系数 0 0 0 0.058 0.035
纵向加速度峰值/ $\left( {\mathrm{m}/{\mathrm{s}}^{2}}\right)$ -5.46 -9.5 -0.62 -1.00 -7.68
横摆角速度峰值/(rad/s) 0.001 18 0.21 0.002 8 0.22 0.072
感知到切入车的相对距离/m 8.15 6.67 20.19 44.58 35.25
偏移车道中心距最大值/m 0.17 3.86 0.16 3.67 0.32
), ArticleFig(id=1153978789290828250, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=表 17, caption=典型场景测试中部分指标值, figureFileSmall=null, figureFileBig=null, tableContent=
指标 指标值
典型场景 1 典型场景 2 典型场景 3 典型场景 4 典型场景 5
$\mathrm{{RC}}/\left( {1/\mathrm{s}}\right)$ 0.30 1.13 0.28 -0.34 2.91
车道保持 1 0 1 0 1
车速标准差/(m/s) 0.79 2.47 0.08 0.68 2.32
弯道横向力系数 0 0 0 0.058 0.035
纵向加速度峰值/ $\left( {\mathrm{m}/{\mathrm{s}}^{2}}\right)$ -5.46 -9.5 -0.62 -1.00 -7.68
横摆角速度峰值/(rad/s) 0.001 18 0.21 0.002 8 0.22 0.072
感知到切入车的相对距离/m 8.15 6.67 20.19 44.58 35.25
偏移车道中心距最大值/m 0.17 3.86 0.16 3.67 0.32
), ArticleFig(id=1153978789391491549, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
车辆综 合得分 总指标 总指标 分值 指标 指标 分值
71.98 行驶安全性 74.72 RC 65.99
车道保持 81.30
乘坐舒适性 70.79 车速标准差 68.49
弯道横向力系数 75.73
纵向加速度峰值 71.21
横摆角速度峰值 64.80
智能性 63.55 感知到切入车的相对距离 55.66
偏移车道中心距最大值 69.74
), ArticleFig(id=1153978789441823200, tenantId=1146029695717560320, journalId=1152916057816748034, articleId=1153978731459764987, language=CN, label=表 18, caption=车辆综合得分及指标分值, figureFileSmall=null, figureFileBig=null, tableContent=
车辆综 合得分 总指标 总指标 分值 指标 指标 分值
71.98 行驶安全性 74.72 RC 65.99
车道保持 81.30
乘坐舒适性 70.79 车速标准差 68.49
弯道横向力系数 75.73
纵向加速度峰值 71.21
横摆角速度峰值 64.80
智能性 63.55 感知到切入车的相对距离 55.66
偏移车道中心距最大值 69.74
)], attaches=null, journal=Journal(id=1149663730306166798, delFlag=0, nameCn=汽车工程学报, nameEn=Chinese Journal of Automotive Engineering, nameHistory1=null, nameHistory2=null, issn=2095-1469, eissn=null, cn=50-1206/U, coden=null, periodic=1, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=jNBfZbtw0oWUAJwGjDXBiw==, journalPrice=null, startedYear=null, abbrevIsoEn=, journalRemark=null, publicationField=null, createdTime=1752030793026, updatedTime=1761730209297, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=Q, firstLetterEn=Q, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=jNBfZbtw0oWUAJwGjDXBiw==, picEn=AzxyR8a1Jh9nr4is1i+eyQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1190346030903296709, language=CN, name=汽车工程学报, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1761730209327, updatedTime=1761730209327, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://tougao.ijournals.cn/ch/index.aspx, submissionEditorUrl=http://tougao.ijournals.cn/ch/index.aspx, submissionReviewUrl=http://tougao.ijournals.cn/ch/index.aspx, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1190346030945239750, language=EN, name=Chinese Journal of Automotive Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1761730209337, updatedTime=1761730209337, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://tougao.ijournals.cn/ch/index.aspx, submissionEditorUrl=http://tougao.ijournals.cn/ch/index.aspx, submissionReviewUrl=http://tougao.ijournals.cn/ch/index.aspx, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1152916057816748034, websiteList=[Website(id=1153018156433002908, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1152916057816748034, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/qcgcxb/CN, language=CN, createTime=1752830550535, createBy=18614031015, updateTime=1752831104570, updateBy=18614031015, name=汽车工程学报, tplId=1146099689490845704, title=汽车工程学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1154109936599552608, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1153018156433002908, code=articleTextType, value=kx, createTime=1753090851211, updateTime=1753090851211, creator=18614031015, updator=18614031015), WebsiteProps(id=1154109936578581085, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1153018156433002908, code=banner, value=null, createTime=1753090851206, updateTime=1753090851206, creator=18614031015, updator=18614031015), WebsiteProps(id=1154109936561803868, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1153018156433002908, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=AAkd3aJi43D2QHSdjNHtbQ==, createTime=1753090851202, updateTime=1753090851202, creator=18614031015, updator=18614031015), WebsiteProps(id=1154109936591163999, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1153018156433002908, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753090851209, updateTime=1753090851209, creator=18614031015, updator=18614031015), WebsiteProps(id=1154109936586969694, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1153018156433002908, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753090851208, updateTime=1753090851208, creator=18614031015, updator=18614031015)]), Website(id=1153018156516888991, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1152916057816748034, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/qcgcxb/EN, language=EN, createTime=1752830550556, createBy=18614031015, updateTime=1752831098136, updateBy=18614031015, name=汽车工程学报, tplId=1146101810881728533, title=汽车工程学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1154109989737189989, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1153018156516888991, code=articleTextType, value=hep, createTime=1753090863880, updateTime=1753090863880, creator=18614031015, updator=18614031015), WebsiteProps(id=1154109989716218466, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1153018156516888991, code=banner, value=null, createTime=1753090863875, updateTime=1753090863875, creator=18614031015, updator=18614031015), WebsiteProps(id=1154109989695246945, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1153018156516888991, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/EN/file/pic?fileId=AAkd3aJi43D2QHSdjNHtbQ==, createTime=1753090863870, updateTime=1753090863870, creator=18614031015, updator=18614031015), WebsiteProps(id=1154109989732995684, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1153018156516888991, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/EN/file/pic, createTime=1753090863879, updateTime=1753090863879, creator=18614031015, updator=18614031015), WebsiteProps(id=1154109989724607075, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1153018156516888991, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1753090863877, updateTime=1753090863877, creator=18614031015, updator=18614031015)])], journalTitle=汽车工程学报, weixinUrl=null, journalUrl=null, iacademicId=null, status=1, seqNo=null, journalTitleEn=Chinese Journal of Automotive Engineering, journalPhotoCn=jNBfZbtw0oWUAJwGjDXBiw==, journalPhotoEn=AzxyR8a1Jh9nr4is1i+eyQ==, journalFirstLetter=Q, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/qcgcxb/CN/10.3969/j.issn.2095-1469.2024.03.04, detailUrlEn=https://castjournals.cast.org.cn/joweb/qcgcxb/EN/10.3969/j.issn.2095-1469.2024.03.04, pdfUrlCn=https://castjournals.cast.org.cn/joweb/qcgcxb/CN/PDF/10.3969/j.issn.2095-1469.2024.03.04, pdfUrlEn=https://castjournals.cast.org.cn/joweb/qcgcxb/EN/PDF/10.3969/j.issn.2095-1469.2024.03.04, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
变道切入场景下ADAS 系统测试与评价研究
收藏切换
PDF下载
宋越 1 , 曾杰 2 , 胡雄 2 , 刘维镇 1 , 李文礼 1
汽车工程学报 | 智能安全技术及其测评 2024,14(3): 363-375
收起
收藏切换
汽车工程学报 | 智能安全技术及其测评 2024, 14(3): 363-375
变道切入场景下ADAS 系统测试与评价研究
全屏
宋越1 , 曾杰2, 胡雄2, 刘维镇1, 李文礼1
作者信息
  • 1 重庆理工大学 汽车零部件先进制造技术教育部重点实验室 重庆 400054
  • 2 招商局检测车辆技术研究院有限公司 重庆 401122
  • 宋越(1999-),男,河南开封人,硕士研究生,主要研究方向为智能网联汽车测试与评价。Tel: 13693783908 E-mail:

通讯作者:


李文礼(1983-),男,河南驻马店人,博士,副教授,主要研究方向为智能网联汽车测试与评价。Tel: 023-68667370 E-mail:
Research on Testing and Evaluation of ADAS Systems in Lane Change Cut-in Scenarios
Yue SONG1 , Jie ZENG2, Xiong HU2, Weizhen LIU1, Wenli LI1
Affiliations
  • 1 Key Laboratory of Advanced Manufacture Technology for Automobile Parts, Ministry of Education Chongqing University of Technology Chongqing 400054 China
  • 2 China Merchants Testing Vehicle Technology Research Institute Co., Ltd. Chongqing 401122 China
doi: 10.3969/j.issn.2095-1469.2024.03.04
文章导航
收藏切换

为了满足变道切入场景下的ADAS系统测试评价需求,提出一种考虑场景风险系数的变道切入场景生成方法和客观综合评价模型。通过采集自然驾驶数据,采用阈值法自动提取变道切入功能场景并深入分析变道切入行为特征。使用单因素方差分析法与皮尔逊相关性检验法共同分析场景风险系数与场景要素的相关性来确定关键场景要素。结合Kmeans算法对离散逻辑场景参数进行聚类,从而得到5个典型测试场景。基于场景风险系数,采用AHP与CRITIC法构建多层次综合评价模型,采用灰色关联理论对ADAS系统进行客观评价。借助VTD仿真软件构建变道切入虚拟测试场景库,进行仿真试验验证。结果表明,相关性分析使场景要素维度降低了60%,生成的测试场景可以有效验证ADAS系统的综合性能,综合评价模型可对ADAS系统表现进行客观有效的评价,为智能驾驶系统开发提供有效参考。

变道切入场景  /  ADAS系统  /  自然驾驶数据  /  灰色关联理论  /  客观评价

To meet the requirements for testing and evaluating ADAS systems in lane change cutin scenarios, the paper proposes a method for generating such scenarios and an objective, comprehensive evaluation model considering the scenario risk coefficients. By collecting natural driving data, the threshold method is used to automatically extract lane change cutin function scenarios and deeply analyze the lane change cutin behavior characteristics. The correlation between scenario risk coefficients and scenario elements is jointly analyzed using oneway ANOVA and Pearson's correlation test to identify key scenario elements. Furthermore, by applying the Kmeans clustering method to the parameters of discrete logic scenarios, five typical test scenarios are obtained. Based on the scenario risk coefficient, the AHP and CRITIC methods are used to construct a multilevel comprehensive evaluation model. The ADAS system is objectively evaluated using the gray correlation theory. Finally, the VTD simulation software is used to create a virtual test scene library for lane change cutin scenarios for simulation testing and validation. The results show that correlation analysis reduces the dimensionality of scenario elements by 60%. The generated test scenarios can effectively validate the comprehensive performance of the ADAS system. Moreover, the comprehensive evaluation model can objectively and effectively evaluate the performance of the ADAS system, providing a valuable reference for the development of intelligent driving systems.

lane change cut-in scenario  /  ADAS system  /  natural driving data  /  gray correlation theory  /  objective evaluation
宋越, 曾杰, 胡雄, 刘维镇, 李文礼. 变道切入场景下ADAS 系统测试与评价研究. 汽车工程学报, 2024 , 14 (3) : 363 -375 . DOI: 10.3969/j.issn.2095-1469.2024.03.04
Yue SONG, Jie ZENG, Xiong HU, Weizhen LIU, Wenli LI. Research on Testing and Evaluation of ADAS Systems in Lane Change Cut-in Scenarios[J]. Chinese Journal of Automotive Engineering, 2024 , 14 (3) : 363 -375 . DOI: 10.3969/j.issn.2095-1469.2024.03.04
变道是自然驾驶行为中出现频率很高的驾驶操作, 作为一种典型的交通场景, 变道切入在道路上发生的概率很高,其发生频率为 ${12.3}\mathrm{\;{km}}$ /次 [ 1 ] 。同时, 车辆变道切入造成的交通事故在生活中也十分常见,与变道切入相关的事故占交通事故总数的 5%,其所延误的时间占所有交通事故总延误时间的 10% [ 2 ] 。孟祥海等 [ 3 ] 对北京、上海、杭州等大型城市的交通事故进行研究, 结果表明, 在交警记录的事故中, 变道超车事故占所有交通事故总数的 30%。变道切入是指后随车在正常行驶过程中,相邻车道前车变换至其所在车道的变道行为。与变道定义略有区别, 变道切入要求目标车道必须有后随车,而一般的变道则对此并无要求。
近年来, 越来越多的车辆装备了高级驾驶辅助系统 (ADAS), 利用安装在车辆上的传感、通信、 决策及执行等装置, 实时监测驾驶员、车辆及其行驶环境, 并通过信息和运动控制等方式辅助驾驶员执行驾驶任务, 减轻驾驶员的驾驶负担, 甚至可以主动避免或减轻碰撞危害, 有效增加了汽车的驾驶舒适性和安全性。基于虚拟场景的仿真测试可以模拟虚拟场景中车辆的交互行为, 提高自动驾驶汽车的安全测试效率 [ 4 ] 。然而,中国的道路交通环境复杂多变, 经常出现行人、非机动车与机动车混行的场景, 传统的仿真场景数据大多来自国外开放数据集, 无法满足国内测试需求。现有虚拟场景在组合生成过程中, 由于对参数空间进行全量组合, 虽然场景覆盖度较高, 但是会导致场景维度过大, 生成的场景库中有大量相似场景 [ 5 ] 。同时,在场景生成时需要考虑我国自然驾驶数据, 使场景要素取值具备典型性和真实性 [ 6 ]
本文采集符合中国道路交通特点的自然驾驶数据, 并提取不同道路类型中的变道切入片段, 采用场景风险系数 (Risk Coefficient, RC) 表征场景的危险程度, 采用单因素方差分析和皮尔逊相关性检验确定场景关键要素, 以降低场景维度, 基于场景风险系数构建多层次综合评价模型。最终聚类生成典型测试场景, 并在 VTD 仿真软件中进行试验验证。
本文中数据来源于某公司场景采集车采集的自然驾驶数据。采集车配备一台安装在车顶的 80 线机械式激光雷达、4个固态激光雷达、2个毫米波雷达,环视车辆周边目标;2 个 Mobileye 摄像头识别前后车辆目标; 6 个 360°环视摄像头, 无死角记录采集车周围图像视频;2 个车道线摄像头,识别前后车辆目标、车道线长度和车道边界;IMU/ GNSS 组合惯导系统获取采集车定位信息及行驶状态, 以及雨量与光照传感器。在满足冗余法则的同时,囊括了构建完整场景动态要素所需的全部信息。 驾驶员被告知按照日常的驾驶行为和习惯进行驾驶, 采集驾驶员在自然状态下的真实驾驶行为。自然驾驶数据集采集时长 2 个月, 采集地点为重庆市主城区范围内的部分高速公路、内环快速路及城市道路, 总行驶时间近 ${80}\mathrm{\;h}$ ,总行驶里程约 ${4176}\mathrm{\;{km}}$
参考文献 [ 1 ] 中的取值, 本文定义了 3 个切入过程中的关键时刻, 分别为开始时刻、切入时刻和结束时刻,并分别用 ${T}_{\text{start }}\text{、}{T}_{\text{cross }}\text{、}{T}_{\text{end }}$ 表示,变道切入片段如 图 2 所示。关键时刻的含义见 表 1
由于数据采集设备可能受到信号干扰且各传感器的采集频率不同, 导致采集的数据有异常值或数据缺失。因此, 在进行变道切入行为自动化提取之前, 需要先对数据进行预处理, 即数据插值、去除异常值并进行滤波处理。 图 3 为某个变道切入片段中相对横向速度预处理前后的对比。
以后随车为基准,定义后随车行驶方向为 $X$ 轴正方向, $Y$ 轴在水平面内且与 $X$ 轴垂直,正方向指向驾驶员左侧。相对横向速度、横向间距定义为左正右负。某次变道切入片段中, 切入车与后随车的相对横向速度折线图, 如 图 4 所示。
本次数据采集过程中, 搭载自然驾驶数据采集设备的测试车辆作为变道切入场景的后随车观察记录整个变道切入行为, 在前车变道切入过程中, 后随车必须保持在同一车道内, 不得进行变道。
后随车搭载的 ASEva 数据采集系统可实时记录自车与变道切入车的车辆速度、加速度以及二者的相对距离、相对速度等信息。
然后需要确定变道切入场景中关键变量取值的阈值范围。为了确保提取符合切入特征的场景片段, 结合前向视频、激光雷达点云特征以及车辆总线数据,参考王雪松等 [ 7 ] 提出的阈值设定范围, 最终制定以下自动化提取准则。
1)横向间距阈值。为了确保切入车辆跨越车道完成变道动作,应保证切入车辆在 ${T}_{\text{start }}$ 时刻,与后随车的横向间距(绝对值)大于 ${1.75}\mathrm{\;m}$ 且不超过 ${5.25}\mathrm{\;m}$ ,在 ${T}_{\text{end }}$ 时刻与后随车横向间距小于 ${1.2}\mathrm{\;m}$
2)纵向间距阈值。变道切入车与后随车的纵向间距不宜大于 ${120}\mathrm{\;m}$ ,否则变道切入将无法影响后随车的驾驶行为 [ 7 ] ,同时根据观察到切入车辆的点云密度特征,将 ${T}_{\text{start }}$ 时刻两车纵向距离阈值定为不大于 ${70}\mathrm{\;m}$
3) 车头时距 (THW)。在 ${T}_{\text{cross }}$ 时刻,后随车的 THW最小, 为了进一步确保切入车辆对后随车正常行驶产生影响, 二者有一定的交互行为, 将标准定为在 ${T}_{\text{cross }}$ 时刻 $\mathrm{{THW}} < 2\mathrm{\;s}$
基于阈值法的目标场景自动提取方法可有效控制漏报率, 但其误报率较大 [ 8 ] 。因此, 在自动化提取之前, 先通过数据回放窗口对变道切入场景视频进行人工筛选,剔除了非目标场景。
依据上节所述标准, 从人工筛选后的 500 个变道切入场景中进行自动化提取,共计得到 92 个切入场景, 不同道路类型采集变道切入场景数量见 表 2
某次切入片段中切入车与后随车的横向间距变化及关键时刻,如 图 5 所示。
由于变道切入场景中切入车会对后随车的正常行驶造成一定的干扰, 因此, 需要对该场景下的安全性进行量化。
碰撞时间 TTC 常被用于评估驾驶安全性, 特别是对于追尾与侧碰场景。对于变道切入场景, 碰撞时间是衡量其危险程度的重要指标, 其值越小, 危险程度越高。
OLSEN 等 [ 9 ] 基于TTC值,将变道切入片段划分为 4 个危险等级,见 表 3
但是 TTC 的值并不能完全表征危险的程度。比如当切入车辆从后随车前方较近位置切入时, 两车速度很高并且相对速度接近于 0 ,虽然此时计算得到的 TTC 值很大, 但由于两车车速都很高且切入时刻纵向间距较小, 十分危险。因此, 需要引入车头时距THW的值作为TTC的补充。
综上所述, 本文中采用的场景风险系数可兼顾 TTC 和 THW 的影响 [ 10 ] ,用以量化表征变道切入场景的危险程度。其由 TTC 和 THW 的倒数加权得到, 如式 (1) 所示。
$ \mathrm{{RC}} = \frac{5}{{t}_{\mathrm{{TTC}}}} + \frac{1}{{t}_{\mathrm{{THW}}}} = \frac{5{V}_{\mathrm{{rel}}} + {V}_{\mathrm{{lv}}}}{{X}_{\mathrm{{rel}}}}。 $
式中: ${t}_{\mathrm{{TTC}}}\text{、}{t}_{\mathrm{{THW}}}$ 分别为 $\mathrm{{TTC}}$$\mathrm{{THW}}$ 的值; $\mathrm{{RC}}$ 为场景风险系数; ${X}_{\mathrm{{rel}}}$${V}_{\mathrm{{rel}}}$ 分别为后随车与变道切入车的纵向间距和纵向相对速度; ${V}_{\mathrm{{lv}}}$ 为后随车纵向速度。自动提取的变道切入场景中, 场景风险系数概率密度分布及正态分布拟合曲线如 图 6 所示。
在本次采集得到的自然驾驶数据中, 将变道切入车辆类型分为轿车、小型 SUV(I类)和中、大型SUV、MPV、面包车、货车、公交车 (II类)。 不同道路类型中切入车辆的类型数量见 表 4
切入持续时间 $t$ 定义为开始时刻 ${T}_{\text{start }}$ 到结束时刻 ${T}_{\text{end }}$ 所经历的时间长度,即 $t = {T}_{\text{end }} - {T}_{\text{start }}$ 。此定义与 TOLEDO 等 [ 11 ] 关于一般变道持续时间的定义相似, 其规定变道车辆横向运动开始时间点和结束时间点所经历时长为持续时间。
本次采集的自然驾驶数据所记录的切入持续时间概率密度分布及 Gamma 拟合曲线, 如 图 7 所示, 所有 92 个切入片段的持续时间最小值为 ${2.8}\mathrm{\;s}$ ,最大值为 ${16.4}\mathrm{\;s}$ ,均值 ${6.55}\mathrm{\;s}$ ,标准差 ${2.69}\mathrm{\;s}$ 。对不同道路类型的切入持续时间进行差异性检验, 结果表明差异不显著 (P = 0.746 > 0.05)。
TOLEDO 等 [ 11 ] 基于美国 1790 个一般变道行为,得到样本均值为 ${5.5}\mathrm{\;s},\mu = {1.376},\sigma = {0.550}$ ,相较于本文的研究结果更小。对此可能的解释, 一是由于自动提取的场景中快速路(内环快速、高速公路)的占比更高,变道切入车辆车速普遍较快,部分驾驶员会刻意拉长变道时间,主动减小车辆的横向加速度与横摆角速度以追求高速变道过程的舒适性;二是可能在变道切入过程中出现某些特殊情况, 导致切入车长时间压线行驶, 从而拉长变道切入持续时间。
在典型变道切入场景中, 变道切入车辆的切入方向有从左侧切入和从右侧切入两种。不同道路类型中的切入方向分布见 表 5
变道切入车辆在执行变道切入动作前, 需要开启转向灯提示后随车。在筛选出的变道切入场景中, 不同道路类型转向灯的使用比例见 表 6 。 OLSEN 等 [ 9 ] 研究得到美国紧急情况变道转向灯使用率为 53.3%,王建强等 [ 12 ] 研究得到中国高速公路一般变道的转向灯使用率为 65.0%
从本次采集得到的自然驾驶数据可以看出, 在 3 种不同道路上中国驾驶员的转向灯使用比例均低于文献 [ 9 ] 与文献 [ 12 ] 的研究结果, 且随着道路等级的升高, 所允许的行驶速度越来越高, 转向灯的使用比例反而降低。对此可能的解释是驾驶员在市区低速行驶时, 由于车距普遍较近, 变道如果不使用转向灯往往会引起后方驾驶员的反感,从而不礼让前车, 所以多数驾驶员会选择使用转向灯;而在内环快速以及高速公路行驶时,由于车距普遍较大且车速较快, 驾驶员会更加频繁地进行变道以进行超车, 此时驾驶员往往忘记使用转向灯或主观认为车距较大, 不会对后方车辆造成太大干扰从而选择不使用转向灯。这体现出中国的道路交通状况、驾驶风格与国外的差别。
在前车变道切入的过程中, 后随车可能受周围交通车、标志标线的影响而无法进行正常的横向运动。其运动受限分为左侧受限、右侧受限以及双侧受限 3 种, 如 图 8 所示。本文定义的运动受限是指在整个变道切入过程中, 后随车横向运动在其中任一时刻受到限制。不同道路类型中的后随车运动受限分布见 表 7
使用单因素方差分析对变道切入场景中的切入车辆类型、切入方向、转向灯使用情况、后随车运动是否受限等分类型场景要素进行分析, 以确定其对前车切入时场景危险程度的影响是否显著。
进行单因素方差分析前, 需要对数据的独立性、齐次性和正态性进行检验。本文所用数据是通过自然驾驶采集获得的随机样本, 因此, 其满足独立性要求。分别对不同因素下各水平数据的齐次性进行检验, 检验结果见 表 8 , 均满足方差齐次性。 经柯尔莫可洛夫-斯米洛夫检验(K-S test)验证, 场景风险系数在 95% 置信度水平下服从正态分布。不同车辆类型、切入方向、转向灯使用情况、 后随车运动受限情况下的单因素方差分析结果见 表 9 ~12。
根据单因素方差分析的结果, 在显著性水平为 0.05 时, 分类型场景要素中切入方向与场景危险程度显著相关, 其余场景要素对切入初始时刻的场景危险程度无显著影响。因此, 可在聚类分析时不考虑这些场景要素, 以降低场景维度。
相关研究表明, 场景要素的维度越高, 测试效率越低 [ 13 ] 。因此,在进行聚类生成典型场景之前, 对场景要素的相关性进行分析, 降低场景维度。
变道切入场景是一种典型的危险场景, 选取变道切入过程中开始时刻后随车纵向速度、后随车纵向加速度、两车相对纵向速度、纵向间距、横向间距和切入持续时间等连续型场景要素与前车切入时场景的危险程度之间的相关性进行分析。
使用皮尔逊相关性检验来对上述连续型场景要素与前车切入场景的风险系数之间的相关性进行分析。皮尔逊相关性系数常用 $r$ 表示, ${r\epsilon }\left\lbrack {-1,1}\right\rbrack$ 。与此同时, 判断两变量之间的相关性是否显著还需要参考显著性系数 $p$ ,当 $p$ 值小于 0.05 时,通常认为两变量相关性显著。
开始时刻上述连续型场景要素与场景风险系数之间的散点图及线性拟合, 如 图 9 所示。
经皮尔逊相关性检验法验证, 后随车纵向速度与场景风险系数 $\mathrm{{RC}}$ 呈负相关,相关系数 $r = - {0.184}$ , 显著性系数 $p = {0.047} < {0.05}$ ,与 $\mathrm{{RC}}$ 值之间的相关性显著;后随车纵向加速度与场景风险系数 $\mathrm{{RC}}$ 呈正相关,相关系数 $r = {0.011}$ ,显著性系数 $p = {0.920} >$ 0.05,与 $\mathrm{{RC}}$ 值之间的相关性不显著;相对纵向速度与场景风险系数 $\mathrm{{RC}}$ 呈正相关,相关系数 $r =$ 0.340,显著性系数 $p = {0.001} < {0.05}$ ,与 $\mathrm{{RC}}$ 值之间的相关性显著; 纵向间距与场景风险系数 $\mathrm{{RC}}$ 呈负相关,相关系数 $r = - {0.210}$ ,显著性系数 $p = {0.045}$ $< {0.05}$ ,与 $\mathrm{{RC}}$ 值之间的相关性显著; 横向间距的绝对值与场景风险系数 $\mathrm{{RC}}$ 呈负相关,相关系数 $r =$ -0.002,显著性系数 $p = {0.988} > {0.05}$ ,与 $\mathrm{{RC}}$ 值之间的相关性不显著; 切入持续时间与场景风险系数 $\mathrm{{RC}}$ 呈负相关,相关系数 $r = - {0.030}$ ,显著性系数 $p =$ 0.779> 0.05,与 RC 值之间的相关性不显著。
综上所述, 在前车变道切入场景的连续型场景要素中, 开始时刻后随车的纵向速度、两车的相对纵向速度、纵向间距与该场景的危险程度显著相关; 而后随车的纵向加速度、两车横向间距、变道切入持续时间与场景的危险程度相关性并不显著, 因此, 在后续的聚类中应该予以排除, 从而降低场景要素维度, 提高聚类效果。
聚类是一种利用特征区分不同场景, 并从中挖掘典型场景的有效方式 [ 14 ] 。它在场景理解、要素特征提取与降维的基础上, 将原始数据集划分为若干类测试场景 [ 15 ] 。聚类算法具备从高维自然驾驶数据中提取典型场景的能力, 可以依据数据集的内在特征实现典型场景的自动快速生成。
在对数据进行聚类处理之前, 需要对其进行标准化处理, 以消除不同参数的量纲和数量级对结果产生的影响。使用Z-score标准化方法对后随车纵向速度 ${V}_{\mathrm{{lv}}}$ 、相对纵向速度 ${V}_{\mathrm{{rel}}}$ 、纵向间距 ${X}_{\mathrm{{rel}}}$ 进行处理,经过 $\mathrm{Z}$ -score标准化后的部分数据对比见 表 13
K-means 算法简单易懂, 便于实现, 同时相较于其他大部分聚类算法,聚类效果较优 [ 16 ] 。所以选择 $\mathrm{K}$ 均值聚类方法对变道切入样本数据进行分析, 生成关键测试用例。为确保聚类结果类簇之间存在显著性差异, 对聚类结果进行单因素方差分析,若显著性系数 $p < {0.05}$ ,则说明差异性显著, 检验结果见 表 14 , $p$ 值均小于 0.05,类簇间差异性显著。整理各类簇下的场景要素平均值, 生成 5 个典型切入场景, 其场景要素见 表 15
综合评价模型包括三部分:确定评价指标、基于 AHP 法和 CRITIC 法确定指标权重、确定评价方法。
无人驾驶车辆的评价指标应综合考察无人驾驶车辆对周围车辆、障碍物以及交通标志的感知能力;对传感器信息的处理和基于信息的决策能力; 对减速停车、换道避让、超车等不同驾驶行为的规划能力; 对自身车辆转向、制动以及加速的控制能力,综合体现无人驾驶车辆的各项性能 [ 17 ]
依据车辆在测试过程中的速度变化、加速度的波动, 最终确定将车辆的行驶安全性、乘坐舒适性、智能性作为评价模型的总指标层, 对其分层次进行评价, 每个总指标层下有对应的细化指标层, ADAS 系统综合评价模型如 图 10 所示。
在确定评价指标后, 接下来用层次分析法 (AHP)和基于层间相关性的客观赋权法 (CRITIC)分别确定总指标层和指标层的评价指标权重。最后,使用灰色关联法对 ADAS 系统功能进行评价。
行驶安全性中, 计算场景风险系数指标时, 数据均取自切入时刻 ${T}_{\text{cross }}$ ; 车道保持指标考察后随车在前车切入过程中有无越过车道线, 没有越过车道线则该指标值取 1 ,反之取 0 。
乘坐舒适性中, 横摆角速度峰值是整个切入片段中后随车横摆角速度绝对值的最大值, 其余指标值可由车速、加速度等数据处理得到, 弯道行驶横向力系数计算式为:
$ \mu = \frac{{v}^{2}}{127R} - {i}_{\mathrm{h}} \circ $
式中: $v$ 为切入时刻 ${T}_{\text{cross }}$ 车辆行驶速度,单位 $\mathrm{{km}}/\mathrm{h}$ ; $R$ 为道路圆曲线半径,单位 $\mathrm{m};{i}_{\mathrm{h}}$ 为路面坡度。
智能性中, 感知到切入车的相对距离根据传感器首次感知到切入车时两车的相对距离来确定; 车辆偏移车道中心距最大值是指后随车在车道内稳定行驶时,车辆中心偏移车道中心线的最大横向距离,通过车辆的坐标值确定。
由于各项指标的计量单位并不统一, 所以在计算这些指标前, 要先对指标进行标准化处理。首先区分指标的正负性, 正向指标也称效益指标, 指标值越大越好;负向指标也称成本指标,指标值越小越好。正负向指标标准化公式为:
正向指标
$ {x}_{ij}^{+\prime } = \frac{{x}_{ij} - \min \left\{ {x}_{ij}\right\} }{\max \left\{ {x}_{ij}\right\} - \min \left\{ {x}_{ij}\right\} } \circ $
负向指标
$ {x}_{ij}^{-\prime } = \frac{\max \left\{ {x}_{ij}\right\} - {x}_{ij}}{\max \left\{ {x}_{ij}\right\} - \min \left\{ {x}_{ij}\right\} } \circ $
ADAS 系统评价指标确定后, 要对其进行定量评价, 需要先确定指标的权重, 指标权重的确定方法有主观赋权法和客观赋权法 [ 17 ] 。主观赋权法可由专家根据其主观经验直接获得指标的权重, 也可由专家或业内有经验的人员按照一定的标准对指标进行评分, 并通过一定的方法对专家评分结果进行计算和处理, 得到指标的权重值。客观赋权法通过分析评价指标的实际属性值, 得到指标的权重系数。
由于主观赋权法容易带有专家意识, 实际应用中客观性较差。此外, ADAS 系统评价指标层多为可量化的指标, CRITIC 法可同时考虑数据的波动性和数据间的相关关系。同时, 由于总指标层指标不易量化, 所以使用层次分析法 (AHP) 和基于层间相关性的客观赋权法(CRITIC)分别确定总指标层和指标层的评价指标权重,指标权重值见 表 16
ADAS 系统评价模型可以看成一个灰色系统, 评价指标纷繁复杂, 且其中关系不完全明确, 因此, 选择灰色关联法对 ADAS 系统进行评价。
灰色关联是指参考序列与比较序列之间、指标与上层指标之间的不确定性关联。其基本思想是根据序列变化或指标变化曲线几何形状的相似程度来判断相关性的紧密程度。曲线的相似性越高,序列或指数的相关性越强。具体步骤如下。
1)确定评价指标, 整理指标值得到待评价矩阵。车辆在 $m$ 个测试场景完成试验,对测试数据处理得到 $n$ 个评价指标值,得到待评价矩阵 $\left( {\mathbf{C}}_{ij}\right) m \times n,{\mathbf{C}}_{ij}$ 为第 $i$ 个测试场景中第 $j$ 个指标的值。
2) 确定参考序列 ${C}_{0}$ ,参考序列值由各指标中的最优值组成。通常情况下, 对于正向指标, 最优值取该指标在不同测试场景中的最大值; 对于负向指标, 最优值取该指标在不同测试场景中的最小值; 对于存在临界值的指标, 最优值取该指标的临界值。
3)对评价指标值进行无量纲处理。用均值法对各指标值进行无量纲处理。
$ {X}_{i}\left( j\right) = \frac{{C}_{i}\left( j\right) }{{C}_{j}}i = 1,2,\ldots ,{m}_{ \circ } $
$ {C}_{j} = \frac{1}{m + 1}\mathop{\sum }\limits_{{i = 0}}^{m}{C}_{i}\left( j\right) j = 1,2,\ldots , n\text{。} $
4)计算比较序列与参考序列的关联系数及指标分值。
$ {\xi }_{i}\left( j\right) = \\ \frac{\mathop{\min }\limits_{i}\mathop{\min }\limits_{j}\left| {{X}_{0}\left( j\right) - {X}_{i}\left( j\right) }\right| + \rho \mathop{\max }\limits_{i}\mathop{\max }\limits_{j}\left| {{X}_{0}\left( j\right) - {X}_{i}\left( j\right) }\right| }{\left| {{X}_{0}\left( j\right) - {X}_{i}\left( j\right) }\right| + \rho \mathop{\max }\limits_{i}\mathop{\max }\limits_{j}\left| {{X}_{0}\left( j\right) - {X}_{i}\left( j\right) }\right| } $
。(7)
式中: $\rho$ 为分辨系数,取(0,1)之间,一般取0.5。 计算完成得到关联系数矩阵 $\left( {\xi }_{ij}\right) m \times n,{\xi }_{ij}$ 为第 $i$ 个测试场景中第 $j$ 个指标的关联系数。假设不同测试场景的权重都一致, 将同一指标在不同场景中的指标分值求均值, 得到该指标的分值。
$ {S}_{j} = \frac{1}{m}\mathop{\sum }\limits_{{i = 1}}^{m}{\xi }_{i}\left( j\right) \text{。} $
5)计算灰色关联度(总指标分值)。将指标分值与指标权重进行加权运算, 得到对应总指标层的指标分值。
$ {\gamma }_{h} = \sum {S}_{j}{W}_{j}h = 1,2,3,4\text{ 。 } $
乘坐舒适性指标中, 纵向加速度峰值及横摆角速度峰值存在舒适性临界值,参考魏子茹等 [ 18 ] 的分析,将纵向加速度峰值的最优值取 ${1.176}\mathrm{\;m}/{\mathrm{s}}^{2}$ ; 横摆角速度峰值的最优值取 ${0.1}\mathrm{{rad}}/\mathrm{s}$ ;其他指标按正负性不同取测试数据中的最大最小值。
对 ADAS 系统的评价应综合考察车辆的感知、 决策规划以及控制能力, ADAS 系统涉及的功能众多,结构比较复杂,因此,需要对其功能进行全方面的测试。基于上节聚类生成的 5 个典型变道切入场景, 在仿真软件 VTD 中搭建相应的虚拟场景对 ADAS 系统进行测试。所搭建的典型场景如 图 11 所示。5 个典型场景片段均为水平干燥的单向 2 车道结构化道路, 天气晴朗, 光照条件良好, 没有外界环境干扰。其中,场景 1、2、3 为直路,场景 4、5 分别是半径为 ${600}\mathrm{\;m}$${300}\mathrm{\;m}$ 的弯道,变道切入持续时间均设置为 ${6.55}\mathrm{\;s}$
本次仿真测试中后随车搭载一颗前视摄像头,有效探测距离为 ${60}\mathrm{\;m}$ ,最大水平视场为 ${90}^{ \circ }$ , 配置在前挡风玻璃车内后视镜处。使用 VTD 软件自带的 ADAS 算法对后随车进行相应配置, 后随车配置为保持在车道内不允许变道, 但可以在同一车道内进行横向运动。对 ADAS 系统进行测试。5 个典型场景中后随车的部分指标值见 表 17
利用基于灰色关联理论的评价模型计算得到各指标分值以及车辆综合得分, 见 表 18
观察测试结果, 后随车在典型切入场景下均未与切入车发生碰撞, 且 ADAS 系统能在较短时间内通过摄像头识别到切入车, 说明安全性满足要求; 在乘坐舒适性方面, 由 表 18 可知, 除场景 2 、场景 4 后随车横摆角速度峰值超过了舒适性临界值外, 其余场景下都可保持在车道内稳定行驶且横摆角速度峰值较小, 满足乘坐舒适性要求; 在智能性方面, 由于后随车仅配置了一颗前视摄像头对周围物体进行感知,且最大视场角仅为 ${90}^{ \circ }$ ,导致感知到切入车时的相对距离较近, 车辆自带 ADAS 算法对车辆横向控制的精准性有待提高。从整体看, 场景风险系数越大, 纵向加速度峰值及车速标准差越大, 说明 ADAS 系统在风险系数更大的场景中表现有待提高。
本文通过采集不同道路类型下的自然驾驶数据, 采用阈值法自动提取变道切入功能场景, 深入分析变道切入行为特征。基于 AHP 和 CRITIC 法利用灰色关联分析模型对 ADAS 系统进行客观综合评价, 有效降低了评价过程中的主观性影响, 主要结论如下。
1)引入场景风险系数并对其与分类型和连续型场景要素的相关性进行深入分析, 将场景要素维度降低了 60%。最终使用 K-means 法聚类得到 5 例典型切入场景, 避免了测试用例的场景要素参数由主观设定, 确保仿真场景与真实场景的一致性。并在 VTD 仿真软件中对 ADAS 系统进行了试验验证。
2)在评价过程中有效降低了评价指标权重设置的主观性, 同时灰色关联评价模型中参考序列最优值的选取也发挥了灰色关联法对底层指标客观描述的优势, 使该评价模型对 ADAS 系统的定量评价更加客观合理, 为后续 ADAS 系统的改进提供了可靠的参考。
  • 重庆市自然科学基金面上项目(cstc2021jcyj-msxmX0183)
  • 重庆市留学人员回国创业创新支持计划资助项目(CX2021070)
  • 重庆市教委科学技术研究项目(KJQN202201170)
  • 重庆市技术创新与应用发展专项重大项目(CSTB2022TIAD-STX0003)
  • 重庆市研究生科研创新项目(gzlcx20242002)
参考文献 引证文献
排序方式:
[1]
ZHAO Ding, LAM H, PENG H, et al. Accelerated Evaluation of Automated Vehicles Safety in Lane-Change Scenarios Based on Importance Sampling Techniques[J]. IEEE Transactions on Intelligent Transportation Systems, 2017,18(3):595-607.
[2]
ZHAO Chunqing, WANG Wenshuo, LI Shaopeng, et al. Influence of Cut-in Maneuvers for an Autonomous Car on Surrounding Drivers: Experiment and Analysis[J]. IEEE Transactions on Intelligent Transportation Systems, 2020(99):1-11.
[3]
孟祥海, 郑来, 史永义. 考虑车道变换影响的高速公路交通事故预测模型研究[J]. 公路交通科技, 2014,31(6):121-126.
MENG Xianghai, ZHENG Lai, SHI Yongyi. Research on Accident Prediction Models for Freeways Considering Effect of Lane Change Maneuvers[J]. Journal of Highway and Transportation Research and Development, 2014,31(6):121-126. (in Chinese)
[4]
LI Wenli, QIU Fanke, LI Lingxi, et al. Simulation of Vehicle Interaction Behavior in Merging Scenarios: A Deep Maximum Entropy-Inverse Reinforcement Learning Method Combined with Game Theory[J]. IEEE Trans-actions on Intelligent Vehicles, 2024,9(1):1079-1093.
[5]
邓伟文, 李江坤, 任秉韬, 等. 面向自动驾驶的仿真场景自动生成方法综述[J]. 中国公路学报, 2022,35(1):316-333.
DENG Weiwen, LI Jiangkun, REN Bingtao, et al. A Survey on Automatic Simulation Scenario Generation Methods for Autonomous Driving[J]. China Journal of Highway and Transport, 2022,35(1):316-333. (in Chinese)
[6]
夏芹. 面向智能驾驶系统的仿真场景生成及测试方法研究[D]. 重庆: 重庆大学, 2021.
XIA Qin. Study on Simulation Scenario Generation and Test Method for Intelligent Driving System[D]. Chongqing: Chongqing University, 2021. (in Chinese)
[7]
王雪松, 杨敏明. 基于自然驾驶数据的变道切入行为分析[J]. 同济大学学报(自然科学版), 2018,46(8):1057-1063.
WANG Xuesong, YANG Minming. Cut-in Behavior Analyses Based on Naturalistic Driving Data[J]. Journal of Tongji University (Natural Science), 2018,46(8):1057-1063. (in Chinese)
[8]
王雪松, 徐晓妍. 基于自然驾驶数据的危险事件识别方法[J]. 同济大学学报(自然科学版), 2020,48(1):51-59.
WANG Xuesong, XU Xiaoyan. Detection of Safety-Critical Events Based on Naturalistic Driving Data[J]. Journal of Tongji University (Natural Science), 2020,48(1):51-59. (in Chinese)
[9]
OLSEN ECB, LEES E, WIERWILLE W W, et al. Analysis of Distribution, Frequency, and Duration of Naturalistic Lane Changes[J]. Human Factors & Ergonomics Society Annual Meeting Proceedings, 2002,46(22):1789-1793.
[10]
丁洁云, 党睿娜, 王建强, 等. 驾驶人换道决策分析及意图识别算法设计[J]. 清华大学学报(自然科学版), 2015,55(7):769-774.
DING Jieyun, DANG Ruina, WANG Jianqiang, et al. Driver Lane Change Decision Analysis and Intention Recognition Algorithm Design[J]. Journal of Tsinghua University (Natural Science Edition), 2015,55(7):769-774. (in Chinese)
[11]
TOLEDO T, ZOHAR D. Modeling Duration of Lane Changes[J]. Transportation Research Record: Journal of the Transportation Research Board, 2007,1999(1):71-78.
[12]
DANG Ruina, ZHANG Fang, WANG Jianqiang, et al. Analysis of Chinese Driver's Lane Change Characteristic Based on Real Vehicle Tests in Highway[C]// 16th Inter-national IEEE Conference on Intelligent Transportation Systems (ITSC 2013), Oct. 6-9, 2013, The Hague, Netherlands.Piscataway NJ: IEEE, c2013, 2013:1917-1922.
[13]
FENG Shuo, YAN Xintao, SUN Haowei, et al. Intelligent Driving Intelligence Test for Autonomous Vehicles with Naturalistic and Adversarial Environment[J]. Nature Communications, 2021,12(1):1-14.
[14]
PÜTZA, ZLOCKI A, KÜFEN J, et al. Database Approach for the Sign-Off Process of Highly Automated Vehicles[C]// Proceedings of the 25th International Technical Conference on the Enhanced Safety of Vehicles (ESV), June 5-8,2017, Detroit Michigan, US, 2017:1-8.
[15]
蒋拯民, 党少博, 李慧云, 等. 自动驾驶汽车场景测试研究进展综述[J]. 汽车技术, 2022(8):10-22.
JIANG Zhengmin, DANG Shaobo, LI Huiyun, et al. A Survey on the Research Progress of Scenario-Based Testing for Autonomous Vehicles[J]. Automobile Technology, 2022(8):10-22. (in Chinese)
[16]
齐先婷. 基于密度峰值优化的K-means文本聚类算法研究[D]. 武汉: 武汉理工大学, 2018.
QI Xianting. Research on K-means Text Clustering Algorithm Based on Improved Density Peaks[D]. Wuhan: Wuhan University of Technology, 2018. (in Chinese)
[17]
郭昱. 权重确定方法综述[J]. 农村经济与科技, 2018,29(8):252-253.
GUO Yu. Overview of Weight Determination Methods[J]. Rural Economy and Technology, 2018,29(8):252-253. (in Chinese)
[18]
魏子茹, 卢延辉, 王鹏宇, 等. 基于CRITIC法的灰色关联理论在无人驾驶车辆测试评价中的应用[J]. 机械工程学报, 2021,57(12):99-108.
WEI Ziru, LU Yanhui, WANG Pengyu, et al. Application of Grey Correlation Theory Based on CRITIC Method in Autonomous Vehicles Test and Evaluation[J]. Journal of Mechanical Engineering, 2021,57(12):99-108. (in Chinese)
2024年第14卷第3期
PDF下载
303
109
引用本文
BibTeX
文章信息
doi: 10.3969/j.issn.2095-1469.2024.03.04
  • 接收时间:2023-12-19
  • 首发时间:2025-07-21
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2023-12-19
  • 修回日期:2024-03-26
基金
重庆市自然科学基金面上项目(cstc2021jcyj-msxmX0183)
重庆市留学人员回国创业创新支持计划资助项目(CX2021070)
重庆市教委科学技术研究项目(KJQN202201170)
重庆市技术创新与应用发展专项重大项目(CSTB2022TIAD-STX0003)
重庆市研究生科研创新项目(gzlcx20242002)
作者信息
    1 重庆理工大学 汽车零部件先进制造技术教育部重点实验室 重庆 400054
    2 招商局检测车辆技术研究院有限公司 重庆 401122

通讯作者:


李文礼(1983-),男,河南驻马店人,博士,副教授,主要研究方向为智能网联汽车测试与评价。Tel: 023-68667370 E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/qcgcxb/CN/10.3969/j.issn.2095-1469.2024.03.04
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏