Article(id=1153780686294081765, tenantId=1146029695717560320, journalId=1146120084050784272, issueId=1153780685195170113, articleNumber=null, orderNo=null, doi=10.19562/j.chinasae.qcgc.2024.02.005, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1687536000000, receivedDateStr=2023-06-24, revisedDate=1689177600000, revisedDateStr=2023-07-13, acceptedDate=null, acceptedDateStr=null, onlineDate=1753012351820, onlineDateStr=2025-07-20, pubDate=1708790400000, pubDateStr=2024-02-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1753012351820, onlineIssueDateStr=2025-07-20, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1753012351820, creator=13701087609, updateTime=1753012351820, updator=13701087609, issue=Issue{id=1153780685195170113, tenantId=1146029695717560320, journalId=1146120084050784272, year='2024', volume='46', issue='2', pageStart='187', pageEnd='374', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=0, articleOrder=1, issueType=-1, specialIssue=null, createTime=1753012351559, creator=13701087609, updateTime=1753058330907, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1153973536604541183, tenantId=1146029695717560320, journalId=1146120084050784272, issueId=1153780685195170113, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1153973536604541184, tenantId=1146029695717560320, journalId=1146120084050784272, issueId=1153780685195170113, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=230, endPage=240, ext={EN=ArticleExt(id=1153780686646403302, articleId=1153780686294081765, tenantId=1146029695717560320, journalId=1146120084050784272, language=EN, title=Extraction and Application of Key Utility Term for Social Driving Interaction, columnId=1149809888211198868, journalTitle=Automotive Engineering, columnName=Feature Topic:Key Technologies on Intelligent and Connected Vehicles, runingTitle=null, highlight=null, articleAbstract=

In shared road space,human driving interaction behavior has the social characteristics of considering the impact on surrounding vehicles. Lacking the understanding of such social characteristics,autonomous vehicles often struggle to estimate the potential impact of their behavior on surrounding vehicles,thus falling into over conservativeness of decision-making dilemma. A game-theory-based social driving interaction model is constructed by introducing in the behavioral characteristics of drivers considering the impact on surrounding vehicles to capture the action dependencies among road users. With this model,a generalized measurement,utility term of interaction activeness (UTIA),is proposed to quantify the potential impact of the host vehicle's anticipated behavior on its interactants. By introducing the UTIA into the planning objective,the interaction activeness of motion planning algorithm can be directionally adjusted. The results of highway exit experiments show that without compromising safety,enhancing interaction activeness can improve the success rate of the exit task within a given distance by 3.9% and 5.2% for optimization-based and sampling-based motion planning algorithm,respectively.

, 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=Xiaocong Zhao, Shiyu Fang, Zirui Li, Jian Sun), CN=ArticleExt(id=1153780733165429320, articleId=1153780686294081765, tenantId=1146029695717560320, journalId=1146120084050784272, language=CN, title=社会性驾驶交互关键效用析取与应用*, columnId=1149809888341222293, journalTitle=汽车工程, columnName=专题:汽车智能化关键技术, runingTitle=null, highlight=null, articleAbstract=

共享道路空间中的人类驾驶交互行为具有兼顾伴行车损益的社会性特征。由于对驾驶交互社会性的理解缺失,自动驾驶车辆往往难以估计自身行为对伴行车辆的潜在影响,因而陷入“被迫保守”的决策困境。本文在博弈论框架中引入驾驶人兼顾伴行车损益的行为特征,构建社会性驾驶交互行为模型,刻画了驾驶交互中个体间的动作依赖关系。结合该模型,提出主车预期行为对其交互对象所造成潜在影响的通用定量表达——交互效用项。通过在规划目标中引入交互效用项,可定向调整运动规划算法的交互主动性。高速路出匝道实验结果表明,在对安全性无显著影响的前提下,通过提升交互主动性,基于优化和基于采样的运动规划算法在给定距离内出匝道任务成功率可分别提升3.9%与5.2%。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
孙剑,教授,博士,E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=fCKLfRwtnPCB/+Fy+gnzEQ==, magXml=0R1rHrqyiz97v84yW+WURg==, pdfUrl=null, pdf=TMaslJWPKGr2W5nEVLU+tA==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=EvLNskFu/zehno8v8T8fJA==, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=赵晓聪, 房世玉, 李子睿, 孙剑)}, authors=[Author(id=1173315897713377753, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, orderNo=0, 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=1173315897788875227, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, authorId=1173315897713377753, language=EN, stringName=Xiaocong Zhao, firstName=Xiaocong, middleName=null, lastName=Zhao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. Tongji University,The Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Shanghai 201804, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1173315897851789788, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, authorId=1173315897713377753, language=CN, stringName=赵晓聪, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. 同济大学,道路与交通工程教育部重点实验室,上海 201804, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1173315897528828369, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, xref=1., ext=[AuthorCompanyExt(id=1173315897541411282, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, companyId=1173315897528828369, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. Tongji University,The Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Shanghai 201804), AuthorCompanyExt(id=1173315897553994195, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, companyId=1173315897528828369, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. 同济大学,道路与交通工程教育部重点实验室,上海 201804)])]), Author(id=1173315897918898654, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, 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=1173315898065699296, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, authorId=1173315897918898654, language=EN, stringName=Shiyu Fang, firstName=Shiyu, middleName=null, lastName=Fang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. Tongji University,The Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Shanghai 201804, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1173315898124419553, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, authorId=1173315897918898654, language=CN, stringName=房世玉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. 同济大学,道路与交通工程教育部重点实验室,上海 201804, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1173315897528828369, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, xref=1., ext=[AuthorCompanyExt(id=1173315897541411282, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, companyId=1173315897528828369, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. Tongji University,The Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Shanghai 201804), AuthorCompanyExt(id=1173315897553994195, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, companyId=1173315897528828369, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. 同济大学,道路与交通工程教育部重点实验室,上海 201804)])]), Author(id=1173315898183139811, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, 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=1173315898246054373, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, authorId=1173315898183139811, language=EN, stringName=Zirui Li, firstName=Zirui, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2. School of Mechanical Engineering,Beijing Institute of Technology,Beijing 100081, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1173315898308968934, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, authorId=1173315898183139811, language=CN, stringName=李子睿, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2. 北京理工大学机械与车辆学院,北京 100081, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1173315897616908756, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, xref=2., ext=[AuthorCompanyExt(id=1173315897625297365, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, companyId=1173315897616908756, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. School of Mechanical Engineering,Beijing Institute of Technology,Beijing 100081), AuthorCompanyExt(id=1173315897637880278, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, companyId=1173315897616908756, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. 北京理工大学机械与车辆学院,北京 100081)])]), Author(id=1173315898388660712, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=sunjian@tongji.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1173315898455769578, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, authorId=1173315898388660712, language=EN, stringName=Jian Sun, firstName=Jian, middleName=null, lastName=Sun, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. Tongji University,The Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Shanghai 201804, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1173315898531267051, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, authorId=1173315898388660712, language=CN, stringName=孙剑, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. 同济大学,道路与交通工程教育部重点实验室,上海 201804, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1173315897528828369, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, xref=1., ext=[AuthorCompanyExt(id=1173315897541411282, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, companyId=1173315897528828369, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. Tongji University,The Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Shanghai 201804), AuthorCompanyExt(id=1173315897553994195, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, companyId=1173315897528828369, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. 同济大学,道路与交通工程教育部重点实验室,上海 201804)])])], keywords=[Keyword(id=1173315898648707564, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=EN, orderNo=1, keyword=autonomous driving), Keyword(id=1173315898711622125, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=EN, orderNo=2, keyword=motion planning), Keyword(id=1173315898778730990, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=EN, orderNo=3, keyword=social driving interaction), Keyword(id=1173315898862617071, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=EN, orderNo=4, keyword=game theory), Keyword(id=1173315898929725936, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=EN, orderNo=5, keyword=highway exiting), Keyword(id=1173315898988446193, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=CN, orderNo=1, keyword=自动驾驶), Keyword(id=1173315899042972146, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=CN, orderNo=2, keyword=运动规划), Keyword(id=1173315899101692403, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=CN, orderNo=3, keyword=社会性驾驶交互), Keyword(id=1173315899160412660, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=CN, orderNo=4, keyword=博弈论), Keyword(id=1173315899214938613, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=CN, orderNo=5, keyword=高速路出匝道)], refs=[Reference(id=1173315901786046994, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=SCHIEBEN A,WILBRINK M,KETTWICH C,et al. Designing the interaction of automated vehicles with other traffic participants: design considerations based on human needs and expectations[J]. Cognition,Technology & Work,2019,21(1): 69-85., articleTitle=null, refAbstract=null), Reference(id=1173315901861544467, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=彭理群,王依婷,马育林,等. 面向混合自动驾驶车流的协同自适应巡航控制[J]. 汽车工程,2022,44(8): 1153–1161., articleTitle=null, refAbstract=null), Reference(id=1173315901924459028, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=PENG L Q,WANG Y T,MA Y L,et al. Cooperated adaptive cruise control for mixed autonomous traffic flow[J]. Automotive Engineering,2022,44(8): 1153-1161., articleTitle=null, refAbstract=null), Reference(id=1173315901983179285, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=WANG H,WANG W,YUAN S,et al. On social interactions of merging behaviors at highway on-ramps in congested traffic[J]. IEEE Transactions on Intelligent Transportation Systems,2021,23(8): 11237-11248., articleTitle=null, refAbstract=null), Reference(id=1173315902050288150, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHAN W,LIU C,CHAN C,et al. A non-conservatively defensive strategy for urban autonomous driving[C]. 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC). IEEE,2016: 459-464., articleTitle=null, refAbstract=null), Reference(id=1173315902117397015, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=NOH S. Decision-making framework for autonomous driving at road intersections: safeguarding against collision,overly conservative behavior,and violation vehicles[J]. IEEE Transactions on Industrial Electronics,2019,66(4): 3275-3286., articleTitle=null, refAbstract=null), Reference(id=1173315902171922968, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=POKORNY P,HØYE A. Descriptive analysis of reports on autonomous vehicle collisions in California: January 2021-June 2022[J]. Traffic Safety Research,2022,2: 000011-000011., articleTitle=null, refAbstract=null), Reference(id=1173315902239031833, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=PETROVIĆ Đ,MIJAILOVIĆ R,PEŠIĆ D. Traffic accidents with autonomous vehicles: type of collisions,manoeuvres and errors of conventional vehicles’ drivers[J]. Transportation Research Procedia,2020,45: 161-168., articleTitle=null, refAbstract=null), Reference(id=1173315902306140698, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=胡益凯,庄瀚洋,王春香,等. 基于主从博弈的智能车汇流场景决策方法[J]. 上海交通大学学报,2021,55(8): 1027-1034., articleTitle=null, refAbstract=null), Reference(id=1173315902356472347, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=HU Y K,ZHUANG H Y,WANG C X,et al. Stackelberg-game-based intelligent vehicle decision method for merging scenarios[J],Journal of Shanghai Jiao Tong University,2021,55(8): 1027-1034., articleTitle=null, refAbstract=null), Reference(id=1173315902419386908, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=YU H,TSENG H E,LANGARI R. A human-like game theory-based controller for automatic lane changing[J]. Transportation Research Part C: Emerging Technologies,2018,88: 140-158., articleTitle=null, refAbstract=null), Reference(id=1173315902486495773, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=REN Y,ELLIOTT S,WANG Y,et al. How shall I drive? interaction modeling and motion planning towards empathetic and socially-graceful driving[C]. 2019 International Conference on Robotics and Automation (ICRA). IEEE,2019: 4325-4331., articleTitle=null, refAbstract=null), Reference(id=1173315902553604638, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=LINIGER A,LYGEROS J. A noncooperative game approach to autonomous racing[J]. IEEE Transactions on Control Systems Technology,2020,28(3): 884-897., articleTitle=null, refAbstract=null), Reference(id=1173315902633296415, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHOU D,MA Z,ZHANG X,et al. Autonomous vehicles’ intended cooperative motion planning for unprotected turning at intersections[J]. IET Intelligent Transport Systems,2022,16(8): 1058-1073., articleTitle=null, refAbstract=null), Reference(id=1173315902700405280, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHOU D,MA Z,ZHAO X,et al. Reasoning graph: a situation-aware framework for cooperating unprotected turns under mixed connected and autonomous traffic environments[J]. Transportation Research Part C: Emerging Technologies,2022,143: 103815., articleTitle=null, refAbstract=null), Reference(id=1173315902780097057, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=SADIGH D,LANDOLFI N,SASTRY S S,et al. Planning for cars that coordinate with people: leveraging effects on human actions for planning and active information gathering over human internal state[J]. Autonomous Robots,2018,42(7): 1405-1426., articleTitle=null, refAbstract=null), Reference(id=1173315902830428706, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=LIU X,PETERS L,ALONSO-MORA J. Learning to play trajectory games against opponents with unknown objectives[J]. arXiv Preprint arXiv: 2023., articleTitle=null, refAbstract=null), Reference(id=1173315902901731875, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=SPICA R,CRISTOFALO E,WANG Z,et al. A real-time game theoretic planner for autonomous two-player drone racing[J]. IEEE Transactions on Robotics,2020,36(5): 1389-1403., articleTitle=null, refAbstract=null), Reference(id=1173315902989812260, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=兰凤崇,刘迎节,陈吉清,等. 基于动态博弈算法的切入场景下自动驾驶车辆运动规划研究[J]. 汽车工程,2023,45(1): 9-19., articleTitle=null, refAbstract=null), Reference(id=1173315903052726821, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=LAN F C,LIU Y J,CHEN J Q,et al. Study on motion planning of autonomous vehicles in cut-in scenes based on dynamic game algorithm[J]. Automotive Engineering,2023,45(1): 9-19., articleTitle=null, refAbstract=null), Reference(id=1173315903124029990, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=FIACCO A V. Introduction to sensitivity and stability analysis in nonlinear programming[M]. New York: Academic Press,1983., articleTitle=null, refAbstract=null), Reference(id=1173315903186944551, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=CAO Z,YANG D,XU S,et al. Highway exiting planner for automated vehicles using reinforcement learning[J]. IEEE Transactions on Intelligent Transportation Systems,2021,22(2): 990-1000., articleTitle=null, refAbstract=null), Reference(id=1173315903258247720, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=ISELE D. Interactive decision making for autonomous vehicles in dense traffic[C]. 2019 IEEE Intelligent Transportation Systems Conference (ITSC). IEEE,2019: 3981-3986., articleTitle=null, refAbstract=null), Reference(id=1173315903308579369, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHAO X,TIAN Y,SUN J. Yield or rush? social-preference-aware driving interaction modeling using game-theoretic framework[C]. 2021 IEEE International Intelligent Transportation Systems Conference (ITSC). IEEE,2021: 453-459., articleTitle=null, refAbstract=null), Reference(id=1173315903367299626, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=SCHWARTING W,PIERSON A,ALONSO-MORA J,et al. Social behavior for autonomous vehicles[J]. Proceedings of the National Academy of Sciences,2019: 201820676., articleTitle=null, refAbstract=null), Reference(id=1173315903426019883, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=张晓彤,王嘉诚,何景涛,等. 面向不确定性环境的自动驾驶运动规划:机遇与挑战[J]. 模式识别与人工智能,2023,36(1): 1-21., articleTitle=null, refAbstract=null), Reference(id=1173315903493128748, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHANG X T,WANG J C,HE J T,et al. Motion planning under uncertainty for autonomous driving: opportunities and challenges[J]. Pattern Recognition and Artificial Intelligence,2023,36(1): 1-21., articleTitle=null, refAbstract=null), Reference(id=1173315903551849005, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[24], rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=叶颖俊,倪颖,孙剑. 高密度瓶颈交通流主动-回应汇入行为定义与建模[J]. 中国公路学报,2022,35(8): 278-290., articleTitle=null, refAbstract=null), Reference(id=1173315903610569262, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[24], rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=YE Y J,NI Y,SUN J. Defining and modeling active-responsive merging behavior at high-density expressway on-ramp bottlenecks[J]. China Journal of Highway and Transport,2022,35(8): 278-290., articleTitle=null, refAbstract=null)], funds=[Fund(id=1173315901551165968, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, awardId=52232015, language=CN, fundingSource=*国家自然科学基金重点项目(52232015), fundOrder=null, country=null), Fund(id=1173315901635052049, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, awardId=52125208, language=CN, fundingSource=国家自然科学基金杰出青年基金(52125208), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1173315897528828369, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, xref=1., ext=[AuthorCompanyExt(id=1173315897541411282, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, companyId=1173315897528828369, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. Tongji University,The Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Shanghai 201804), AuthorCompanyExt(id=1173315897553994195, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, companyId=1173315897528828369, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. 同济大学,道路与交通工程教育部重点实验室,上海 201804)]), AuthorCompany(id=1173315897616908756, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, xref=2., ext=[AuthorCompanyExt(id=1173315897625297365, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, companyId=1173315897616908756, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. School of Mechanical Engineering,Beijing Institute of Technology,Beijing 100081), AuthorCompanyExt(id=1173315897637880278, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, companyId=1173315897616908756, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. 北京理工大学机械与车辆学院,北京 100081)])], figs=[ArticleFig(id=1173315899382710774, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=EN, label=null, caption=null, figureFileSmall=R8A1xHnX41w0eDPFvJQ4dg==, figureFileBig=hgOpUsO68L41WN9pfiBHAg==, tableContent=null), ArticleFig(id=1173315899437236727, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=CN, label=图1, caption=典型驾驶冲突场景

(a)无保护左转;(b)合流;(c)无信号交叉口直行冲突;(d)对向冲突

, figureFileSmall=R8A1xHnX41w0eDPFvJQ4dg==, figureFileBig=hgOpUsO68L41WN9pfiBHAg==, tableContent=null), ArticleFig(id=1173315899487568376, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=EN, label=null, caption=null, figureFileSmall=uxOrqWIYIfFmyMgd07Kp+w==, figureFileBig=6kzLL2EflyQZ1Vu1RSqPbQ==, tableContent=null), ArticleFig(id=1173315899546288633, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=CN, label=图2, caption=交互效用项示意, figureFileSmall=uxOrqWIYIfFmyMgd07Kp+w==, figureFileBig=6kzLL2EflyQZ1Vu1RSqPbQ==, tableContent=null), ArticleFig(id=1173315899600814586, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=EN, label=null, caption=null, figureFileSmall=LiIH4JCNGM9y13tqg8YmUw==, figureFileBig=QXOEHpAku4xKUfHmwdiEGw==, tableContent=null), ArticleFig(id=1173315899659534843, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=CN, label=图3, caption=高速路出匝道场景, figureFileSmall=LiIH4JCNGM9y13tqg8YmUw==, figureFileBig=QXOEHpAku4xKUfHmwdiEGw==, tableContent=null), ArticleFig(id=1173315899726643708, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=EN, label=null, caption=null, figureFileSmall=eV+nFuVcO57ff0Bl5/B2bA==, figureFileBig=8OV2owgLZFLAlZWqNUr81g==, tableContent=null), ArticleFig(id=1173315899789558269, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=CN, label=图4, caption=背景车的随机横向响应特性

(a)保守背景车;(b)激进背景车

, figureFileSmall=eV+nFuVcO57ff0Bl5/B2bA==, figureFileBig=8OV2owgLZFLAlZWqNUr81g==, tableContent=null), ArticleFig(id=1173315899865055742, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=EN, label=null, caption=null, figureFileSmall=mW/WrPSxMPYtIsWxgjAysw==, figureFileBig=mXK8eb7KJXevthZmMtozFw==, tableContent=null), ArticleFig(id=1173315899940553215, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=CN, label=图5, caption=匝道汇出任务成功率累积曲线, figureFileSmall=mW/WrPSxMPYtIsWxgjAysw==, figureFileBig=mXK8eb7KJXevthZmMtozFw==, tableContent=null), ArticleFig(id=1173315900066382336, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=EN, label=null, caption=null, figureFileSmall=00B8ujNfbMf4CXN4FMqcYA==, figureFileBig=GTdn0EP1LyN/RhMKEiO5sA==, tableContent=null), ArticleFig(id=1173315900154462721, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=CN, label=图6, caption=换道后与前后车的碰撞时间, figureFileSmall=00B8ujNfbMf4CXN4FMqcYA==, figureFileBig=GTdn0EP1LyN/RhMKEiO5sA==, tableContent=null), ArticleFig(id=1173315900213182978, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=EN, label=null, caption=null, figureFileSmall=vDl12/pXczv/52toil3Ppw==, figureFileBig=U/Z7+RM/K92vz0fn0WGeSg==, tableContent=null), ArticleFig(id=1173315900288680451, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=CN, label=图7, caption=不同交互效用项权重下的TTC均值

注:*根据双尾T检验,相较于基线规划算法( θ = 0)的差异在 α = 0.01的置信度水平下具有显著性。

, figureFileSmall=vDl12/pXczv/52toil3Ppw==, figureFileBig=U/Z7+RM/K92vz0fn0WGeSg==, tableContent=null), ArticleFig(id=1173315900355789316, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=EN, label=null, caption=null, figureFileSmall=QW/MJ7zBRXZoLyOcm5i/TA==, figureFileBig=b/kLSJkho4wJRFtrplnHDQ==, tableContent=null), ArticleFig(id=1173315900452258309, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=CN, label=图8, caption=换道规划轨迹, figureFileSmall=QW/MJ7zBRXZoLyOcm5i/TA==, figureFileBig=b/kLSJkho4wJRFtrplnHDQ==, tableContent=null), ArticleFig(id=1173315900557115910, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=EN, label=null, caption=null, figureFileSmall=Hzvf+A9ZgG+de5+TWhCrcQ==, figureFileBig=YjgO6OukHMpM3k7iJPwMtA==, tableContent=null), ArticleFig(id=1173315900624224775, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=CN, label=图9, caption=高速路换道场景试探行为:(a)面对保守型背景车的协作响应案例;(b)面对激进型背景车的无响应退回案例, figureFileSmall=Hzvf+A9ZgG+de5+TWhCrcQ==, figureFileBig=YjgO6OukHMpM3k7iJPwMtA==, tableContent=null), ArticleFig(id=1173315900687139336, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
参数 均值 范围 单位
期望速度 v ˜ 120 ± 20 k m / h
最大加速度 a m a x 5 m / s 2
舒适加速度 a c o m f 2 ± 1 m / s 2
最小停车间距 s 0 2 m
期望车头时距 T ˜ 2 ± 0.5 s
常参数 β 5
), ArticleFig(id=1173315900754248201, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=CN, label=表1, caption=

IDM模型参数

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 均值 范围 单位
期望速度 v ˜ 120 ± 20 k m / h
最大加速度 a m a x 5 m / s 2
舒适加速度 a c o m f 2 ± 1 m / s 2
最小停车间距 s 0 2 m
期望车头时距 T ˜ 2 ± 0.5 s
常参数 β 5
), ArticleFig(id=1173315900863300106, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=

算法1:最优迭代响应法求解纳什均衡

输入:

主车上一时刻最优轨迹解 p e ( t - 1 )

主车的当前位置 p e和速度 v e

目标车道前、后车的当前位置 p f p b和速度 v f v b

输出:规划轨迹 p e ( t )

1

初始化:

迭代序号 k 0

主车轨迹解 p e [ k ] , * O ( N + 1 ) × 2

目标车道后车轨迹解

p ̂ b [ k ] , * a r g   m a x p b [ k ] P b p b , v b , p e [ 0 ] , *   R p b [ k ]

2

while k = 0 or p e [ k ] , * - p e [ k - 1 ] , * ϵ do

3

set k k + 1

4

迭代主车轨迹解

p e [ k ] , * a r g m a x p e [ k ] P e p e , v e , p b [ k - 1 ] , *   R p e [ k ] + θ · U a p e [ k ]

5

迭代目标车道后车轨迹解

p ̂ b [ k ] , * a r g m a x p b [ k ] P b p b , v b , p e [ k ] , *   R p b [ k ]   p e [ k ] , *

6

保存迭代最优轨迹解 p e * p e [ k ] , * p ̂ b * p ̂ b [ k ] , *

7

end while

8

if ( p e * , p f , v f )不满足碰撞约束 do

9

保留上一时刻最优规划轨迹解 p e * p e ( t - 1 )

10

end if

11

输出规划轨迹解 p e ( t ) p e *

), ArticleFig(id=1173315901014295051, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=CN, label=表2, caption=

纳什博弈规划算法

, figureFileSmall=null, figureFileBig=null, tableContent=

算法1:最优迭代响应法求解纳什均衡

输入:

主车上一时刻最优轨迹解 p e ( t - 1 )

主车的当前位置 p e和速度 v e

目标车道前、后车的当前位置 p f p b和速度 v f v b

输出:规划轨迹 p e ( t )

1

初始化:

迭代序号 k 0

主车轨迹解 p e [ k ] , * O ( N + 1 ) × 2

目标车道后车轨迹解

p ̂ b [ k ] , * a r g   m a x p b [ k ] P b p b , v b , p e [ 0 ] , *   R p b [ k ]

2

while k = 0 or p e [ k ] , * - p e [ k - 1 ] , * ϵ do

3

set k k + 1

4

迭代主车轨迹解

p e [ k ] , * a r g m a x p e [ k ] P e p e , v e , p b [ k - 1 ] , *   R p e [ k ] + θ · U a p e [ k ]

5

迭代目标车道后车轨迹解

p ̂ b [ k ] , * a r g m a x p b [ k ] P b p b , v b , p e [ k ] , *   R p b [ k ]   p e [ k ] , *

6

保存迭代最优轨迹解 p e * p e [ k ] , * p ̂ b * p ̂ b [ k ] , *

7

end while

8

if ( p e * , p f , v f )不满足碰撞约束 do

9

保留上一时刻最优规划轨迹解 p e * p e ( t - 1 )

10

end if

11

输出规划轨迹解 p e ( t ) p e *

), ArticleFig(id=1173315901152707084, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=

算法2:Frenet最优规划

输入:

目标车道前后车当前位置 p f p b和速度 v f v b

主车当前位置 p e和速度 v e

参考路径特征参数备选集 S

输出:规划轨迹 p e ( t )

1

初始化效用列表 U l i s t与备选轨迹列表 P l i s t

2

for s e in S do

3

生成特征参数为 s e的Sigmoid参考路径

4

基于参考路径构建Frenet坐标系

5

将初始状态投影至Frenet坐标系

p f F p b F p e F v f F v b F v e F)←( p f p b p e v f v b v e

6

计算目标前瞻点位置

p t p F←( p f F p b F p e F v f F v b F v e F

7

生成横向和纵向的五次多项式位移函数并插值获得备选轨迹 p e F←( p e F v e F p t p F

8

if p e F符合动力学约束与碰撞约束 do

9

计算横、纵向收益 R l a t R l o n和交互效用项 U a

10

计算整体轨迹效用 U i R l a t + R l o n + θ · U a

11

记录备选轨迹效用 U l i s t i U i

12

将备选轨迹投影至笛卡尔坐标系 p e

13

记录备选轨迹 P l i s t i p e

14

end if

15

end for

16

遍历 U l i s t获取最大项及其对应序号 i m a x

17

输出最大效用轨迹 p e ( t ) P l i s t i m a x

), ArticleFig(id=1173315901236593165, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=CN, label=表3, caption=

Frenet最优规划算法

, figureFileSmall=null, figureFileBig=null, tableContent=

算法2:Frenet最优规划

输入:

目标车道前后车当前位置 p f p b和速度 v f v b

主车当前位置 p e和速度 v e

参考路径特征参数备选集 S

输出:规划轨迹 p e ( t )

1

初始化效用列表 U l i s t与备选轨迹列表 P l i s t

2

for s e in S do

3

生成特征参数为 s e的Sigmoid参考路径

4

基于参考路径构建Frenet坐标系

5

将初始状态投影至Frenet坐标系

p f F p b F p e F v f F v b F v e F)←( p f p b p e v f v b v e

6

计算目标前瞻点位置

p t p F←( p f F p b F p e F v f F v b F v e F

7

生成横向和纵向的五次多项式位移函数并插值获得备选轨迹 p e F←( p e F v e F p t p F

8

if p e F符合动力学约束与碰撞约束 do

9

计算横、纵向收益 R l a t R l o n和交互效用项 U a

10

计算整体轨迹效用 U i R l a t + R l o n + θ · U a

11

记录备选轨迹效用 U l i s t i U i

12

将备选轨迹投影至笛卡尔坐标系 p e

13

记录备选轨迹 P l i s t i p e

14

end if

15

end for

16

遍历 U l i s t获取最大项及其对应序号 i m a x

17

输出最大效用轨迹 p e ( t ) P l i s t i m a x

), ArticleFig(id=1173315901333062158, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
规划算法 换道后TTC/s

前向TTC

均值

后向TTC

均值

纳什博弈

规划

基线 4.54 -4.99
合作型( θ = 0.5 4.72 -4.62
竞争型( θ = - 0.5 4.26 -4.80

Frenet

最优规划

基线 -0.75 1.93
合作型( θ = 0.5 -0.80 1.91
竞争型( θ = - 0.5 -0.58* 1.69*
), ArticleFig(id=1173315901408559631, tenantId=1146029695717560320, journalId=1146120084050784272, articleId=1153780686294081765, language=CN, label=表4, caption=

匝道汇出任务安全性指标

, figureFileSmall=null, figureFileBig=null, tableContent=
规划算法 换道后TTC/s

前向TTC

均值

后向TTC

均值

纳什博弈

规划

基线 4.54 -4.99
合作型( θ = 0.5 4.72 -4.62
竞争型( θ = - 0.5 4.26 -4.80

Frenet

最优规划

基线 -0.75 1.93
合作型( θ = 0.5 -0.80 1.91
竞争型( θ = - 0.5 -0.58* 1.69*
)], attaches=null, journal=Journal(id=1146119049450201092, delFlag=0, nameCn=汽车工程, nameEn=Automotive Engineering, nameHistory1=null, nameHistory2=null, issn=1000-680X, eissn=, cn=11-2221/U, coden=null, periodic=0, language=CN, oaType=否, 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=QBBRQev7wkMVPuUPGz0mFw==, journalPrice=null, startedYear=null, abbrevIsoEn=Auto Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1755587219741, createdBy=null, updatedBy=15831073675, firstLetterCn=A, firstLetterEn=A, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=QBBRQev7wkMVPuUPGz0mFw==, picEn=p+MsLQKu3DZkDibBsTBu1Q==, jcr=null, cjcr=null, exts=[JournalExt(id=1164580465202643295, language=CN, name=汽车工程, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=https://www.qichegongcheng.com/CN/1000-680X/home.shtml, createdTime=1755587219763, updatedTime=1755587219763, createdBy=15831073675, updatedBy=15831073675, submissionGuidelinesUrl=https://www.qichegongcheng.com/CN/column/column6.shtml, submissionAuthorUrl=https://journal03.magtechjournal.com/journalx_qcgc/authorLogOn.action, submissionEditorUrl=https://journal03.magtechjournal.com/journalx_qcgc/editorLogOn.action, submissionReviewUrl=https://journal03.magtechjournal.com/journalx_qcgc/expertLogOn.action, submissionCeEditorUrl=https://journal03.magtechjournal.com/journalx_qcgc/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1164580465248780640, language=EN, name=Automotive Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=https://www.qichegongcheng.com/EN/1000-680X/home.shtml, createdTime=1755587219774, updatedTime=1755587219774, createdBy=15831073675, updatedBy=15831073675, submissionGuidelinesUrl=https://www.qichegongcheng.com/EN/column/column6.shtml, submissionAuthorUrl=https://journal03.magtechjournal.com/journalx_qcgc/authorLogOn.action, submissionEditorUrl=https://journal03.magtechjournal.com/journalx_qcgc/editorLogOn.action, submissionReviewUrl=https://journal03.magtechjournal.com/journalx_qcgc/expertLogOn.action, submissionCeEditorUrl=https://journal03.magtechjournal.com/journalx_qcgc/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146120084050784272, websiteList=[Website(id=1148243202387206565, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146120084050784272, 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/qcygc/CN, language=CN, createTime=1751692112776, createBy=18614031015, updateTime=1753500958911, updateBy=18614031015, name=《汽车工程》中文站点, tplId=1146099689490845704, title=汽车工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622315115540535, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202387206565, code=articleTextType, value=kx, createTime=1751782500294, updateTime=1751782500294, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622315094569012, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202387206565, code=banner, value=null, createTime=1751782500289, updateTime=1751782500289, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622315081986099, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202387206565, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=+W0ZN6/p6N8AvZxnX71krg==, createTime=1751782500286, updateTime=1751782500286, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622315107151926, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202387206565, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782500292, updateTime=1751782500292, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622315102957621, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202387206565, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782500291, updateTime=1751782500291, creator=18614031015, updator=18614031015)]), Website(id=1155829970321686531, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146120084050784272, 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/qcygc/EN, language=EN, createTime=1753500939211, createBy=18614031015, updateTime=1753500939211, updateBy=18614031015, name=《汽车工程》英文站点, tplId=1146101810881728533, title=Automotive Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155830904879702095, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155829970321686531, code=articleTextType, value=kx, createTime=1753501162023, updateTime=1753501162023, creator=18614031015, updator=18614031015), WebsiteProps(id=1155830904858730572, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155829970321686531, code=banner, value=null, createTime=1753501162018, updateTime=1753501162018, creator=18614031015, updator=18614031015), WebsiteProps(id=1155830904837759051, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155829970321686531, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=+W0ZN6/p6N8AvZxnX71krg==, createTime=1753501162013, updateTime=1753501162013, creator=18614031015, updator=18614031015), WebsiteProps(id=1155830904875507790, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155829970321686531, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753501162022, updateTime=1753501162022, creator=18614031015, updator=18614031015), WebsiteProps(id=1155830904867119181, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155829970321686531, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753501162020, updateTime=1753501162020, creator=18614031015, updator=18614031015)])], journalTitle=汽车工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Automotive Engineering, journalPhotoCn=QBBRQev7wkMVPuUPGz0mFw==, journalPhotoEn=p+MsLQKu3DZkDibBsTBu1Q==, journalFirstLetter=A, 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/qcygc/CN/10.19562/j.chinasae.qcgc.2024.02.005, detailUrlEn=https://castjournals.cast.org.cn/joweb/qcygc/EN/10.19562/j.chinasae.qcgc.2024.02.005, pdfUrlCn=https://castjournals.cast.org.cn/joweb/qcygc/CN/PDF/10.19562/j.chinasae.qcgc.2024.02.005, pdfUrlEn=https://castjournals.cast.org.cn/joweb/qcygc/EN/PDF/10.19562/j.chinasae.qcgc.2024.02.005, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
社会性驾驶交互关键效用析取与应用*
收藏切换
PDF下载
赵晓聪 1 , 房世玉 1 , 李子睿 2 , 孙剑 1
汽车工程 | 专题:汽车智能化关键技术 2024,46(2): 230-240
收起
收藏切换
汽车工程 | 专题:汽车智能化关键技术 2024, 46(2): 230-240
社会性驾驶交互关键效用析取与应用*
全屏
赵晓聪1, 房世玉1, 李子睿2, 孙剑1
作者信息
  • 1. 同济大学,道路与交通工程教育部重点实验室,上海 201804
  • 2. 北京理工大学机械与车辆学院,北京 100081

通讯作者:

孙剑,教授,博士,E-mail:
Extraction and Application of Key Utility Term for Social Driving Interaction
Xiaocong Zhao1, Shiyu Fang1, Zirui Li2, Jian Sun1
Affiliations
  • 1. Tongji University,The Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Shanghai 201804
  • 2. School of Mechanical Engineering,Beijing Institute of Technology,Beijing 100081
出版时间: 2024-02-25 doi: 10.19562/j.chinasae.qcgc.2024.02.005
文章导航
收藏切换

共享道路空间中的人类驾驶交互行为具有兼顾伴行车损益的社会性特征。由于对驾驶交互社会性的理解缺失,自动驾驶车辆往往难以估计自身行为对伴行车辆的潜在影响,因而陷入“被迫保守”的决策困境。本文在博弈论框架中引入驾驶人兼顾伴行车损益的行为特征,构建社会性驾驶交互行为模型,刻画了驾驶交互中个体间的动作依赖关系。结合该模型,提出主车预期行为对其交互对象所造成潜在影响的通用定量表达——交互效用项。通过在规划目标中引入交互效用项,可定向调整运动规划算法的交互主动性。高速路出匝道实验结果表明,在对安全性无显著影响的前提下,通过提升交互主动性,基于优化和基于采样的运动规划算法在给定距离内出匝道任务成功率可分别提升3.9%与5.2%。

自动驾驶  /  运动规划  /  社会性驾驶交互  /  博弈论  /  高速路出匝道

In shared road space,human driving interaction behavior has the social characteristics of considering the impact on surrounding vehicles. Lacking the understanding of such social characteristics,autonomous vehicles often struggle to estimate the potential impact of their behavior on surrounding vehicles,thus falling into over conservativeness of decision-making dilemma. A game-theory-based social driving interaction model is constructed by introducing in the behavioral characteristics of drivers considering the impact on surrounding vehicles to capture the action dependencies among road users. With this model,a generalized measurement,utility term of interaction activeness (UTIA),is proposed to quantify the potential impact of the host vehicle's anticipated behavior on its interactants. By introducing the UTIA into the planning objective,the interaction activeness of motion planning algorithm can be directionally adjusted. The results of highway exit experiments show that without compromising safety,enhancing interaction activeness can improve the success rate of the exit task within a given distance by 3.9% and 5.2% for optimization-based and sampling-based motion planning algorithm,respectively.

autonomous driving  /  motion planning  /  social driving interaction  /  game theory  /  highway exiting
赵晓聪, 房世玉, 李子睿, 孙剑. 社会性驾驶交互关键效用析取与应用*. 汽车工程, 2024 , 46 (2) : 230 -240 . DOI: 10.19562/j.chinasae.qcgc.2024.02.005
Xiaocong Zhao, Shiyu Fang, Zirui Li, Jian Sun. Extraction and Application of Key Utility Term for Social Driving Interaction[J]. Automotive Engineering, 2024 , 46 (2) : 230 -240 . DOI: 10.19562/j.chinasae.qcgc.2024.02.005
随着自动驾驶车辆在公开道路的测试与落地应用,与人类驾驶车辆进行和谐交互成为自动驾驶车辆必需的驾驶能力[1-2]。在交通法规和有限道路资源的约束下,驾驶人常需要通过主动交互争取道路资源,以完成冲突场景(图1)中的驾驶任务[3]。主动交互行为往往伴随收益的让渡或分配,因而体现了人类驾驶环境中以路权为媒介考虑他人损益的社会性特征。对主动交互行为的合理应用和应对,是驾驶人在“遵守交通法规”之外的驾驶行为准则,也是目前自动驾驶汽车融入人类驾驶环境的过程中所欠缺的能力[1]
主动交互能力的缺失可表现为无法在高密度行驶环境中寻找合理的可行规划空间,以及对伴行车辆发起的“试探行为”无差别地退让。其本质是由于对交互主动性和规划安全性缺少权衡的能力,因而被迫选择保守决策[4]。自动驾驶的过保守行为一方面将降低交互场景中自身和交通系统的通行效率[5];另一方面,由于缺乏社会性,因而难以被人类理解和预测,故更易引发伴行的人类道路使用者的路怒[6],甚至安全隐患[7-8]
已有研究中,针对自动驾驶在交互场景中的运动规划,主要通过以下几类方式调整交互行为。(1)通过引入交互行为相关的可变特征参数,例如收益函数的权重参数[9-11],使得规划器具有差异化的交互特性。此类研究可在不改变原有运动规划器结构的前提下实现交互风格的调整,具有易于实施的优点,但受限于参数的物理含义模糊,难以保障可控的交互行为。(2)通过为特定驾驶场景或驾驶任务设计额外的效用项,具象化表达对交互行为的调整目标,可使得交互行为更具可控性。例如合流场景中以交互对象的加速度变化量作为合作收益[8],在交叉口场景中将交互对象让行所需减速度作为合作收益[12-13]等。(3)基于博弈的运动规划研究将交互对象的规划目标直接纳入自身运动规划的效用函数中,可实现具有场景迁移能力的交互风格调整[1014-16]。但受限于博弈问题求解的计算复杂度[17],此类规划算法在相对复杂的混行交通环境中尚无法满足实时部署的需求。
综上,交互驾驶场景的运动规划研究中,仍缺少交互行为特性的普适描述和量化方法,因而难以支撑自动驾驶在运动规划中交互主动性和安全性的平衡与调整。
本文针对由路径冲突导致的驾驶交互场景,在博弈论框架中考虑驾驶人兼顾他人收益的社会性行为特征,构建了社会性驾驶交互行为模型。基于该模型所刻画的个体间动作依赖关系,提出了主车预期行为对其交互对象所造成潜在影响的定量表达——交互效用项。相较于已有研究中的交互行为特性量化方式,交互效用项基于交互事件的轨迹层特征提出,具有明确的物理含义和闭式表达,因而在脱离博弈模型框架后,对基于目标函数的运动规划算法均具适用性。仿真实验表明,交互效用项的引入可使得基于优化和基于采样的两类典型运动规划算法在保证安全约束的前提下,定向调整运动规划器的交互风格,实现安全性与交互主动性的平衡。
交互驾驶事件多出现于因路权不严格明确而存在潜在冲突的驾驶场景中(图1),例如无保护左转场景、合流场景、无信号交叉口直行冲突场景、对向冲突场景等。此类场景的共同特点是至少两个交互个体的未来通行路径存在冲突,且交互个体通过冲突区域的优先权存在相互让渡的可能性。
为保证交互行为建模结果的通用性,本文在建模阶段不对场景进行具象化,仅假定交互个体具有明确的通行路径和道路边界,且交互个体间的通行路径存在冲突。为表述简洁,本文在模型构建中以一对一交互场景为例,同时讨论了该模型在一对多交互场景中的潜在扩展方式和局限性。
对于交互个体在给定时域 N Z +内的运动规划问题,定义动作变量 a = [ a 1 ,   a 2 , , a N ],位置变量 p = [ p 0 , p 1 , , p N ]。由于交互事件中主车的运动规划问题涉及其交互对象的状态描述,故分别使用下标 i - i表征主车和其交互对象。
在博弈框架下,个体以最大化自身效用作为运动规划的目标,由此将主车的运动规划表述为以下优化问题:
p i * = a r g m a x p i   R p i + θ R - i * p i
s . t .     g p i , p - i 0
其中, k 0 , N Z,位置变量与动作变量满足运动学状态转移方程 p ˙ k + 1 = p ˙ k + a k及动作约束 a k a ¯,且有 a k = a x k , a y k T p k = p x k , p y k T a ¯为动作变量上界;主车的效用函数为主车自身收益 R ( p i )与交互对象在给定主车规划结果下的最大收益 R - i * ( p i )的加权和, θ ( - 1,1 )为自由参数。通过在主车的运动规划问题中引入交互对象的收益项作为效用函数的一部分,可体现交互场景中的社会性行为特征,即驾驶人会在决策自身行为时考虑到他人损益。此外,由于交互双方通行路径存在冲突,轨迹规划结果具有潜在碰撞,因此引入式(1b)避撞约束用以构建交互双方的动作依赖关系。此处以交互双方轨迹点的欧氏距离作为避撞约束,则 g 0的具体形式为 p i k - p - i k d ¯,其中 d ¯为最小安全距离。
式(1)所给出的原始问题定义中,效用函数包含交互对象的收益项 R - i *,但由于交互对象的收益并不是优化变量 p i显式函数,因此无法直接得到 R - i *关于 p i的闭式表达。本文应用规划问题中处理非线性要素的敏感性分析方法[18],对 R - i *关于 p i的隐函数进行线性化近似。考虑轨迹规划的时间一致性假设,即 t - 1 t两个连续时间帧的运动规划结果中,对应同一未来时刻的2个轨迹点应在彼此的平面邻域内。由此可在 t - 1时的最优解 p i * , ( t - 1 )(记为 p ¯ i ( t - 1 ))处附近对 R - i *进行泰勒展开,获得 t时刻交互对象的最大收益关于优化变量 p i的隐函数的1阶近似:
R - i * p i R - i * p ¯ i t - 1 + d R - i * d p i p i = p ¯ i t - 1 ( p i - p ¯ i ( t - 1 ) )
式(1)中,交互对象的最大收益 R - i * ( p i )是优化目标的一部分,由于移除优化目标中与优化变量 p i无关的项 R - i * p ¯ i t - 1后不改变优化问题的结果,因而可将式(2)中交互对象的最大收益进一步简化为
R - i * p i d R - i * d p i p i = p ¯ i ( t - 1 ) ( p i - p ¯ i ( t - 1 ) )
其中, d R - i * d p i即为交互对象的最大收益对于主车轨迹的敏感性。将式(3)代入式(1a)所述的效用函数,即得到效用函数关于优化变量的闭式表达,并可将式(1)所述问题改写为
p i * = a r g m a x p i   R p i + θ d R - i * d p i p i = p ¯ i ( t - 1 ) p i - p ¯ i t - 1
s . t .     g p i , p - i 0
式(4a) d R - i * d p i p i = p ¯ i ( t - 1 )的计算考虑以下关系。
(1)交互对象最大收益对主车轨迹的敏感性
d R - i * d p i = d R d p - i p - i = p - i * · d p - i * p i d p i
(2)交互对象最大收益
R - i * = a r g m a x p - i   R ( p - i )
s . t .     g p i , p - i 0
对于任给 p i式(6)的最优解 p - i *须满足Karush-Kuhn-Tucker驻点条件:
d R d p - i   p - i = p - i * + μ g p i , p - i p - i   p - i = p - i * = 0
μ g p i , p - i * = 0
g p i , p - i * 0
μ 0
式中 μ = [ μ 1 ,   μ 2 , , μ N ]为拉格朗日乘子。式(7a-d)为给定主车规划结果 p i时,交互对象最优轨迹解的必要性条件,即交互对象(局部)最优轨迹解的共有特性。因此,当交互对象由于非线性收益函数存在多个(局部)最优轨迹解时,式(7a-d)所刻画的最优轨迹解特性依然保持成立。此外,由于式(7b)对于任给 p i成立,故有该式对 p i的全微分保持成立:
d d p i μ g p i , p - i * = μ g p - i , p i p - i p - i = p - i * · d p - i * p i d p i + g p - i , p i p i p - i = p - i * = 0
式(7a)与式(8)代入式(5)可得交互对象最大收益轨迹敏感性的闭式表达:
d R - i * d p i = μ g p - i , p i p i p - i = p - i * =
μ p i - p - i * ( p i ) T p i - p - i * ( p i ) = μ ε p i , p - i * ( p i ) T
式中 ε p i , p - i * ( p i )表示由 p i指向 p - i * ( p i )的方向向量。将式(9)代入式(4)后,得到主车在考虑交互关系时的运动规划问题的完整表述为
p i * = a r g m a x p i   R p i + θ U a p i
s . t .     g p i , p - i * p ¯ i t - 1 0
μ 0
式(10a)中的 U a p i = μ ε p ¯ i t - 1 , p - i * p ¯ i t - 1 T p i - p ¯ i t - 1即为主车因考虑社会性交互而产生的效用项,其中 p - i * p ¯ i t - 1可通过在式(6)中令 p i = p ¯ i t - 1后求解得到。
以下结合图2,讨论式(10a)中交互效用项 U a p i的物理含义。将交互双方规划轨迹(图2(a))中满足 k { k | μ k > 0 }的临近安全约束的轨迹点记为“预期危险点”(图2(b))。如图2(b)所示, U a p i中的 ε为预期危险点处从交互对象指向主车原位置的单位向量, p i - p ¯ i t - 1则为主车的位置更新向量。两者点积反映了主车在预期危险点处更新轨迹的倾向。当 ε p i - p ¯ i t - 1点积为正,主车倾向于在预期危险点处远离交互对象,从而使得交互对象拥有进一步优化自身轨迹的空间;反之,当 ε p i - p ¯ i t - 1点积为负,主车倾向于在预期危险点处接近交互对象,进一步压缩其规划空间,迫使其放弃当前的最优轨迹解。
通过在运动规划问题引入交互效用项,可量化自身运动规划结果对交互对象的影响,进而在必要时主动干预交互对象的运动。对于式(10)所述的交互运动规划策略,需要说明如下。
(1) 交互效用项 U a p i的闭式表达具有明确的物理含义,其适用范围不局限于基于博弈的运动规划算法。其他基于目标函数的规划算法同样可通过引入交互效用项调整交互主动性。后文将通过仿真实验对此进一步说明。
(2) 式(10a)中,通过改变交互效用项权重 θ即可实现不同交互风格的主动交互行为。当 θ = 0时,交互项不生效,主车进行独立规划,即主车运动规划不考虑对环境车的潜在影响;当 θ > 0时,主车可从“减少对他车的影响”中获得收益,因此运动规划结果表现为具有合作性,可实现与他车的协同;当 θ < 0时,主车倾向于通过“侵入他车最优轨迹”主动与他车形成交互,因此运动规划结果表现为具有竞争性,可实现主动干预他车行为以实现特定驾驶目标(例如,汇入高密度车流)。
(3) 当设定交互效用项权重 θ < 0进行竞争型运动规划时,规划结果中可能出现邻近安全约束的预期危险点。为确保规划结果的安全性,在实际部署中仅当预期危险点出现在较远的未来时刻点时,主车才可获得交互效用项相关的收益。若主动交互行为没有得到预期的回应,即交互对象未给出退让响应,预期危险点将逐步逼近当前时刻点,直至足够接近当前时刻点时(本文中将该阈值设定为0.5倍的规划时域),竞争性行为将无法带来额外收益,进而放弃主动交互。由此,主车一方面可在不破坏安全约束的前提下通过竞争性驾驶行为实现主动交互,另一方面可适应交互对象的行为特性,在无法确保安全性时退出主动交互。
(4) 实际驾驶场景中,主车往往须同时面对多个交互对象,对于主车须考虑多个交互对象的驾驶交互场景,可将式(10a)中的优化目标扩展为
p i * = a r g m a x p i   R p i + θ M - i M U a p i , p - i *
式中 M为交互对象的个数。需要说明,该扩展形式虽可使得主车的运动规划同时兼顾多个交互对象的收益,但由于忽略了交互对象之间的内在交互,在当主车的交互对象相互间存在明显交互关系时,该扩展形式的适用性受限。
本文采用高速路出匝道作为实验场景。在高密度交通流中,通过等待安全的换道时机往往需要耗费较长时间,因而驾驶人常需要与相邻车道内的其他车辆主动交互,制造合适的换道时机,以避免错过出匝道时机。在高速路出匝道场景中,驾驶交互主动性对出匝道任务的成功率具有重要影响,故可有效体现运动规划算法的主动交互能力[19]。如图3所示的四车道场景,实验初始时刻主车位于最内侧车道,须在给定任务距离内换道至最外侧车道以完成驾驶任务。实验中,要求被测车辆在进入匝道前的行驶速度不低于60 km/h。为计算出匝道场景中的任务表现(成功率与安全性),每种被测算法均在该场景中进行500次重复实验,以获得任务表现的统计结果。
背景车辆在各车道起始点随机生成,单个车道的最大车辆密度为37.5辆/km[19]。为提高背景交通的随机性,背景车辆采用具有随机参数的智能驾驶员模型(intelligent driver model,IDM)控制,其纵向加速度为
a ( t ) = a m a x 1 - v ( t ) v ˜ β - s ˜ ( t ) s ( t ) 2
式中: a m a x为最大加速度; v v ˜分别为当前速度和期望速度; s s ˜分别为当前车头间距与期望车头间距。期望车头间距 s ˜的计算如下:
s ˜ ( t ) = s 0 + m a x   0 , v ( t ) T ˜ - v ( t ) Δ v ( t ) 2 a m a x a c o m f
式中: s 0为最小驻车间距; T ˜为期望车头时距; Δ v为主车与前车的相对速度; a c o m f为舒适加速度。IDM模型的参数数值分布见表1
此外,通过引入横向响应参数 d l a t,使得背景车辆的横向响应特性亦具有随机性[20]。如图4所示,背景车的横向响应参数 d l a t随机分布于 0 ,   w l a n e区间内,其中 w l a n e为车道宽度。对于一辆给定背景车,仅当主车与背景车的横向间距小于该背景车的 d l a t时,背景车才会将主车视为当前的前车,进而作出减速的响应。因此,横向响应参数 d l a t越大,背景车行为表现为越保守(图4(a)),反之,背景车行为越激进(图4(b))。
本文选取了两类典型的运动规划算法作为基线算法,分别为基于优化的纳什博弈规划算法和基于采样的Frenet最优规划算法。两类基线算法均受到效用函数的驱动,因而可通过在效用函数中增加不同权重的交互效用项 U a,形成合作型与竞争型的衍生算法。以下对基线算法与衍生算法进行说明。
纳什博弈规划算法通过求解轨迹博弈问题的均衡[21],得到对自身运动的规划结果 p i *和对交互对象的轨迹预测结果 p ^ - i
p i * = a r g m a x p i P i ( p ^ - i )   U ( p i )
s . t . k , p i k = 𝒟 ( p i k - 1 , a i k )
p i k - p - i k d ¯
p ^ - i ( p i ) = a r g m a x p - i P - i ( p i )   R p - i
s . t .     k ,   p - i k = 𝒟 ( p - i k - 1 , a - i k )
p - i k - p i k d ¯
其中:式(11a)为主车自身的轨迹最优化问题;效用函数 U = R p i + θ U a p i由主车自身收益与交互效用项构成;式(11d)为交互对象的轨迹最优化问题;式(11b)式(11e)为运动学单轨模型约束下的运动状态转移方程,其中 a i k a - i k为动作变量;式(11c)式(11f)为避撞约束。主车自身收益 R p i具体包含效率、安全和舒适项:
R p i = k e f f τ i p i N + k s a f e p i n m - p - i n m 2 - 1 N t j t
其中:效率项 τ i p i N为规划轨迹在参考路径上的投影长度,表征规划结果的有效行程,本文中效率项权重 k e f f = 0.3;安全项 p i n m - p - i n m 2中, n m表征规划轨迹中与交互对象的最小间距点,本文中安全项权重 k s a f e = 0.7;舒适项 1 N t j t中, j t为规划轨迹中各时刻点的加速度。
对于式(11)所述问题,本文采用最优迭代响应法[16](iterative best response,IBR)对纳什均衡进行数值求解。表2所示为该算法应用于高速路出匝道场景时的具体算法流程。由于纳什博弈规划算法以车道中心线为参考路径,而换道行为涉及车道中心线的切换,因此该算法在实际规划中将分别以原车道和目标车道的车道中心线为参考路径计算纳什均衡。为有效完成汇出任务,规划中优先选择以目标车道为参考路径的均衡解作为规划结果。当以目标车道为参考路径无法获得满足避撞约束的均衡解时,则采取以原车道中心线为参考路径的均衡解,从而退回至原车道。为保证运动规划的连续性,两类均衡解的切换时间间隔设定为大于一个规划周期(3 s)。
Frenet最优规划算法通过采样获得参考路径集后,将主车及其交互车辆的运动状态转换至Frenet坐标,并通过五次多项式拟合及插值生成备选轨迹。
对于满足动力学约束和避撞约束的备选轨迹分别计算横、纵向收益和交互效用项,最终选取最大总效用的轨迹作为规划结果。该算法应用于高速路出匝道场景时的算法流程如表3所示。其中,主车的横、纵向收益具体包含:
R l a t = - a l a t F 2 - d l a t F 2
R l o n = p i F p e F D i F ( p i F )
横向收益 R l a t中, a l a t F d l a t F分别为Frenet坐标下横向加速度和横向偏移距离;纵向收益 R l o n中, D i F为备选轨迹 p e F中轨迹点 p i F与障碍物沿参考路径的距离。
合理的交互行为应当在保证安全性的前提下,利用主动交互提高行驶效率。本节将分别在汇出任务成功率和安全性两方面,分析交互效用项对于运动规划算法表现的影响。
图5所示,在效用函数中增加不同权重的交互效用项后,两类基线规划算法在匝道汇出任务中的成功率产生了差异化的影响。两类基线算法的竞争型衍生算法( θ = - 0.5)的汇出成功率均得到了提升;但在合作型衍生算法( θ = 0.5)方面,纳什博弈规划算法的合作型衍生算法的汇出任务成功率得到了提升,而Frenet最优规划算法的合作型衍生算法的成功率出现了下降。此外,随着任务距离的增长,交互效用项对于任务成功率的影响逐渐减小。后文中将通过微观交互行为分析,进一步揭示交互效用项对两类规划算法造成差异化影响的原因。
匝道汇出任务的执行过程中涉及多次换道,因而该过程的安全性可由换道完成时(主车形心进入目标车道)主车与前后车的碰撞时间(time to collision,TTC)进行表征。当TTC绝对值较小时,表明换道行为较为危险;反之,换道行为较为安全。图6所示为各规划算法在完成换道时的前后向TTC分布情况,表4所示为记录的完成换道时的前后向TTC均值。
总体上,竞争型衍生算法均使得换道后TTC绝对值降低,即相较于各自的基线算法表现出更为激进的换道行为。但这种差异仅在Frenet最优规划算法与其 θ = - 0.5的竞争型衍生算法间具有显著性( p < 0.01),而在纳什博弈规划算法中不具有统计意义( p = 0.32)。
进一步分析交互效用项对于驾驶交互安全性的影响,图7所示为不同权重的交互效用项下,两类规划算法换道完成时的TTC。随着 θ的减小,交互行为逐渐趋向竞争型,即倾向于通过挤占交互对象的规划空间来提升自身的行驶效率,因而换道后的TTC绝对值呈下降趋势。但值得注意,当交互效用项权重 θ取负值但分别大于等于 - 0.5(纳什博弈规划算法)和 - 0.2(Frenet最优规划算法)时,TTC的变化不具有显著性。这表明当交互效用项的权重取负值但大于等于特定临界权重时,可在不对安全性造成显著负面影响的同时,提升规划算法的交互能力。以 700 m的任务距离为例,结合临界权重下的交互效用项,本文中的两类算法在匝道汇出任务中的成功率可分别提升 3.9 %(纳什博弈规划算法)和 5.2 %(Frenet最优规划算法)。对于纳什博弈这类预留安全冗余较大的规划算法,若权衡一部分安全性,则可进一步实现更为高效的驾驶交互。
针对交互效用项的引入对两类基线规划算法差异化影响,本节从微观轨迹视角分析其致因。图8所示为两类基线算法及其衍生算法在相同场景下的轨迹规划结果。该场景中主车的目标车道后方存在背景车辆,且沿车道方向的运动速度与主车一致。
Frenet最优规划算法的前瞻点纵向位置由规划时刻的运动状态确定,因此备选轨迹虽在轨迹形状与速度曲线上存在差异,但在车道方向的行驶进程是一致的。如图8(a)所示,随着轨迹逐渐远离交互对象,轨迹在安全性和交互主动性方面均呈单调变化,即交互主动性的提升必然引起安全性的降低。因此,当引入交互效用项后,竞争型衍生算法通过提升交互主动性迫使后车减速让行,进而在提高汇出任务成功率的同时,不可避免地影响轨迹安全性。而合作型衍生算法由于降低了交互主动性,更难以触发目标车道后车的减速响应,进而导致任务成功率的下降。
纳什博弈规划由于其基于优化的算法本质,具有更大的轨迹自由度和收益权衡空间。如图8(b)所示,相较于基线算法,竞争型纳什博弈规划算法的规划结果更贴近交互对象的轨迹,但在邻近安全约束处并未明显减小最小间距,而是通过将最小间距点提前,以提高轨迹的交互主动性。与Frenet最优规划算法的合作型衍生算法不同,合作型纳什博弈规划算法通过采取额外的加速动作牺牲了一定的纵向舒适性,在远离交互对象、减弱交互主动性的同时,提升了行驶进程方面的收益。这类行为在目标车道前方车辆较远时,可制造更大换道空间,因而最终提升了出匝道任务的成功率。
在基于效用函数的规划算法中引入交互效用项可实现合作型和竞争型两类算法的衍生,并可通过权重值连续调节驾驶交互风格。当交互效用项权重为正值时,衍生算法优先减少与伴行对象的交互,在不对伴行对象产生负面影响的前提下优化自身轨迹,且合作性随交互效用项权重增加而提高。当交互效用项权重为负值时,竞争型衍生算法通过(在不破坏安全约束的前提下)更多或更早地入侵交互对象的预期未来轨迹,以试探性的入侵行为争取交互对象给出有利于主车的响应,实现主动交互,且竞争性随交互效用项权重降低而提高。值得说明,竞争型衍生算法试探行为的有效性同时还取决于交互对象的行为特性。以竞争型纳什博弈规划算法为例,图9为该算法在面对不同交互对象时的两类交互情形。当与保守型背景车交互时,背景车以减速行为响应主车的试探,主车的试探行为获得了预期响应,进而实现换道(图9(a));反之,当与激进型背景车交互时,背景车未对主车的试探给出退让响应,因而随着预期危险点的接近,主车放弃试探退回原车道行驶(图9(b))。这两类情形反映了人类驾驶环境中常见的主动交互模式,即驾驶人通过试探性行为表达“请求路权”的意图时,由于他车在社交倾向方面的差异[22-23],有时可得到他车的协作让行进而完成驾驶任务,有时则无法得到合作响应而须终止主动交互行为[1924]
此外,交互效用项的引入对规划算法交互行为的影响在不同基线算法中还存在差异性,并主要与基线规划算法本身的规划逻辑所确定的可行轨迹空间相关:(1)若基线算法的可行轨迹集中的轨迹安全性与交互效用项呈严格负相关(例如Frenet最优规划算法),则竞争型衍生算法在提升交互主动性的同时,必然引起轨迹解安全性的下降,反之,合作型衍生算法必然引起安全性的提升。需要说明,由于交互过程还同时受到交互对象的响应逻辑的影响,实际交互结果的安全性并不一定存在显著变化,因而当竞争型Frenet最优规划算法的 θ > - 0.2时,其驾驶交互实际结果的安全性未发生显著下降(图7(a))。(2)若基线算法的可行轨迹集中的轨迹安全性与交互效用非严格负相关(例如纳什博弈规划算法),则衍生算法在调整交互主动性的同时,可保留其他行驶目标(安全、舒适、高效等)的权衡空间。此时,竞争型衍生算法更易于在保证安全性水平不改变的同时,提升轨迹的交互主动性,从而提高驾驶交互任务的成功率。
针对自动驾驶运动规划中交互主动性和安全性的权衡问题,构建了基于博弈的社会性驾驶交互行为模型,推导得到了具有明确物理含义的交互行为特性量化形式——交互效用项。通过开展高速路出匝道场景的仿真实验,验证了交互效用项对运动规划算法交互主动性的调整能力,实验结果表明:
(1) 交互效用项对基于效用函数的运动规划算法具有一般适应性。本文中,两类不同规划逻辑(基于优化和基于采样)的基线算法均可通过引入交互效用项,调节运动规划结果的交互主动性,进而影响其驾驶交互任务的成功率。
(2) 通过交互效用项的权重调节,可实现驾驶交互风格的连续调节和可控表达。随着交互效用项的权重由正至负逐渐减小,运动规划的交互主动性逐渐增加,驾驶行为倾向由合作型让行转为竞争型试探抢行。
(3) 交互效用项与其他行驶目标之间具有相对独立性。当基线运动规划算法的可行轨迹集中轨迹安全性与交互效用项非严格负相关时,通过引入交互效用项,可在调整驾驶交互主动性的同时保留其他驾驶目标的调整自由度。
  • *国家自然科学基金重点项目(52232015)
  • 国家自然科学基金杰出青年基金(52125208)
参考文献 引证文献
排序方式:
[1]
SCHIEBEN A,WILBRINK M,KETTWICH C,et al. Designing the interaction of automated vehicles with other traffic participants: design considerations based on human needs and expectations[J]. Cognition,Technology & Work,2019,21(1): 69-85.
[2]
彭理群,王依婷,马育林,等. 面向混合自动驾驶车流的协同自适应巡航控制[J]. 汽车工程,2022,44(8): 1153–1161.
PENG L Q,WANG Y T,MA Y L,et al. Cooperated adaptive cruise control for mixed autonomous traffic flow[J]. Automotive Engineering,2022,44(8): 1153-1161.
[3]
WANG H,WANG W,YUAN S,et al. On social interactions of merging behaviors at highway on-ramps in congested traffic[J]. IEEE Transactions on Intelligent Transportation Systems,2021,23(8): 11237-11248.
[4]
ZHAN W,LIU C,CHAN C,et al. A non-conservatively defensive strategy for urban autonomous driving[C]. 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC). IEEE,2016: 459-464.
[5]
NOH S. Decision-making framework for autonomous driving at road intersections: safeguarding against collision,overly conservative behavior,and violation vehicles[J]. IEEE Transactions on Industrial Electronics,2019,66(4): 3275-3286.
[6]
POKORNY P,HØYE A. Descriptive analysis of reports on autonomous vehicle collisions in California: January 2021-June 2022[J]. Traffic Safety Research,2022,2: 000011-000011.
[7]
PETROVIĆ Đ,MIJAILOVIĆ R,PEŠIĆ D. Traffic accidents with autonomous vehicles: type of collisions,manoeuvres and errors of conventional vehicles’ drivers[J]. Transportation Research Procedia,2020,45: 161-168.
[8]
胡益凯,庄瀚洋,王春香,等. 基于主从博弈的智能车汇流场景决策方法[J]. 上海交通大学学报,2021,55(8): 1027-1034.
HU Y K,ZHUANG H Y,WANG C X,et al. Stackelberg-game-based intelligent vehicle decision method for merging scenarios[J],Journal of Shanghai Jiao Tong University,2021,55(8): 1027-1034.
[9]
YU H,TSENG H E,LANGARI R. A human-like game theory-based controller for automatic lane changing[J]. Transportation Research Part C: Emerging Technologies,2018,88: 140-158.
[10]
REN Y,ELLIOTT S,WANG Y,et al. How shall I drive? interaction modeling and motion planning towards empathetic and socially-graceful driving[C]. 2019 International Conference on Robotics and Automation (ICRA). IEEE,2019: 4325-4331.
[11]
LINIGER A,LYGEROS J. A noncooperative game approach to autonomous racing[J]. IEEE Transactions on Control Systems Technology,2020,28(3): 884-897.
[12]
ZHOU D,MA Z,ZHANG X,et al. Autonomous vehicles’ intended cooperative motion planning for unprotected turning at intersections[J]. IET Intelligent Transport Systems,2022,16(8): 1058-1073.
[13]
ZHOU D,MA Z,ZHAO X,et al. Reasoning graph: a situation-aware framework for cooperating unprotected turns under mixed connected and autonomous traffic environments[J]. Transportation Research Part C: Emerging Technologies,2022,143: 103815.
[14]
SADIGH D,LANDOLFI N,SASTRY S S,et al. Planning for cars that coordinate with people: leveraging effects on human actions for planning and active information gathering over human internal state[J]. Autonomous Robots,2018,42(7): 1405-1426.
[15]
LIU X,PETERS L,ALONSO-MORA J. Learning to play trajectory games against opponents with unknown objectives[J]. arXiv Preprint arXiv: 2023.
[16]
SPICA R,CRISTOFALO E,WANG Z,et al. A real-time game theoretic planner for autonomous two-player drone racing[J]. IEEE Transactions on Robotics,2020,36(5): 1389-1403.
[17]
兰凤崇,刘迎节,陈吉清,等. 基于动态博弈算法的切入场景下自动驾驶车辆运动规划研究[J]. 汽车工程,2023,45(1): 9-19.
LAN F C,LIU Y J,CHEN J Q,et al. Study on motion planning of autonomous vehicles in cut-in scenes based on dynamic game algorithm[J]. Automotive Engineering,2023,45(1): 9-19.
[18]
FIACCO A V. Introduction to sensitivity and stability analysis in nonlinear programming[M]. New York: Academic Press,1983.
[19]
CAO Z,YANG D,XU S,et al. Highway exiting planner for automated vehicles using reinforcement learning[J]. IEEE Transactions on Intelligent Transportation Systems,2021,22(2): 990-1000.
[20]
ISELE D. Interactive decision making for autonomous vehicles in dense traffic[C]. 2019 IEEE Intelligent Transportation Systems Conference (ITSC). IEEE,2019: 3981-3986.
[21]
ZHAO X,TIAN Y,SUN J. Yield or rush? social-preference-aware driving interaction modeling using game-theoretic framework[C]. 2021 IEEE International Intelligent Transportation Systems Conference (ITSC). IEEE,2021: 453-459.
[22]
SCHWARTING W,PIERSON A,ALONSO-MORA J,et al. Social behavior for autonomous vehicles[J]. Proceedings of the National Academy of Sciences,2019: 201820676.
[23]
张晓彤,王嘉诚,何景涛,等. 面向不确定性环境的自动驾驶运动规划:机遇与挑战[J]. 模式识别与人工智能,2023,36(1): 1-21.
ZHANG X T,WANG J C,HE J T,et al. Motion planning under uncertainty for autonomous driving: opportunities and challenges[J]. Pattern Recognition and Artificial Intelligence,2023,36(1): 1-21.
[24]
叶颖俊,倪颖,孙剑. 高密度瓶颈交通流主动-回应汇入行为定义与建模[J]. 中国公路学报,2022,35(8): 278-290.
YE Y J,NI Y,SUN J. Defining and modeling active-responsive merging behavior at high-density expressway on-ramp bottlenecks[J]. China Journal of Highway and Transport,2022,35(8): 278-290.
2024年第46卷第2期
PDF下载
366
155
引用本文
BibTeX
文章信息
doi: 10.19562/j.chinasae.qcgc.2024.02.005
  • 接收时间:2023-06-24
  • 首发时间:2025-07-20
  • 出版时间:2024-02-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2023-06-24
  • 修回日期:2023-07-13
基金
*国家自然科学基金重点项目(52232015)
国家自然科学基金杰出青年基金(52125208)
作者信息
    1. 同济大学,道路与交通工程教育部重点实验室,上海 201804
    2. 北京理工大学机械与车辆学院,北京 100081

通讯作者:

孙剑,教授,博士,E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/qcygc/CN/10.19562/j.chinasae.qcgc.2024.02.005
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