Article(id=1253994379954287410, tenantId=1146029695717560320, journalId=1251234571887362144, issueId=1253994374069682477, articleNumber=null, orderNo=null, doi=10.20249/j.cnki.2096-5974.2025.05.001, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=null, receivedDateStr=null, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1776905158258, onlineDateStr=2026-04-23, pubDate=null, pubDateStr=null, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1776905158258, onlineIssueDateStr=2026-04-23, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1776905158257, creator=13041195026, updateTime=1776905158257, updator=13041195026, issue=Issue{id=1253994374069682477, tenantId=1146029695717560320, journalId=1251234571887362144, year='2025', volume='8', issue='5', pageStart='1', pageEnd='114', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=1, specialIssue=null, createTime=1776905156856, creator=13041195026, updateTime=1777355348378, updator=13041195026, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1255882614297248384, tenantId=1146029695717560320, journalId=1251234571887362144, issueId=1253994374069682477, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1255882614301442689, tenantId=1146029695717560320, journalId=1251234571887362144, issueId=1253994374069682477, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=1, endPage=10, ext={EN=ArticleExt(id=1253994382244377402, articleId=1253994379954287410, tenantId=1146029695717560320, journalId=1251234571887362144, language=EN, title=Probabilistic Graph Optimization Integrated Navigation Based on Probabilistic Time Series Transformer, columnId=1253994380264669540, journalTitle=Flight Control & Detection, columnName=Navigation, Guidance and Control Technology, runingTitle=null, highlight=null, articleAbstract=

To satisfy the modern track traffic's demand for maintaining high precision and continuity of navigation under complex environmental conditions,and to address the issue of positioning drift caused by data outages in nonlinear dynamic integrated navigation systems,this paper proposes a novel adaptive estimation method for observation errors in nonlinear dynamic integrated navi gation systems. This method is based on a Probabilistic Time Series Transformer model,aiming to resolve the aforementioned issues. By introducing self-learning capabilities through the Probabilistic Time Series Transformer,the method adaptively adjusts the impact of state prediction and observation information outages on the dynamic navigation system. The Probabilistic Time Series Transformer is composed of a dual-loop system of a generative model and an inference model, combined with LSTM network to tackle the challenges of multivariate time series modeling. The integrated navigation system based on the Probabilistic Time Series Transformer optimizes the error compensation mechanism by establishing a relationship between the current Kalman filter gain and the optimal estimation error,thereby improving the accuracy and stability of the nonlinear navigation system. Experimental results demonstrate that the proposed method not only effectively controls the impact of GNSS outages on the nonlinear navigation system but also accurately estimates and compensates for observation model system errors. The average positioning error in various complex scenarios is less than 10m. The suppression of positioning drift in the observation model is better than that of other filtering methods.

, 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=Lei ZHANG, Qin XU, Wanliang ZHAO, Yuxiang CHENG, Yan SUN), CN=ArticleExt(id=1253994399935950992, articleId=1253994379954287410, tenantId=1146029695717560320, journalId=1251234571887362144, language=CN, title=基于概率时间序列注意力模型的概率图优化组合导航算法, columnId=1253994380436636006, journalTitle=飞控与探测, columnName=导航制导与控制技术, runingTitle=null, highlight=null, articleAbstract=

为满足现代轨道交通在复杂的环境条件下保持高精度和连续性的导航需求,解决非线性动态组合导航系统因观测数据失锁导致的定位漂移问题,结合基于概率时间序列注意力模型,提出一种新的非线性动态组合导航系统观测误差自适应估计方法,利用概率时间序列注意力模型,引入自学习能力,自适应调整状态预测和观测信息失锁状态对动态导航系统的影响。概率时间序列注意力模型由生成模型和推理模型组成双循环系统,并结合长短期记忆网络,以解决多变量时间序列建模问题。基于概率时间序列注意力模型的组合导航系统,通过建立当前卡尔曼滤波增益与最优估计误差之间的关系,优化误差补偿机制以提高非线性导航系统的精度和稳定性。实验结果表明,所提出的研究方法不仅能够控制GNSS失锁状态对非线性导航系统的影响,且能够有效地估计和补偿观测模型系统误差,各种复杂状态下滤波解算平均定位误差小于10m;抑制观测模型定位漂移优于其他滤波方法。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=cNnMSHqf5pqVoOkEKpJp1Q==, magXml=Ks78GCoiuXy9AFe4BOhupA==, pdfUrl=null, pdf=DAgXnp0+r1VNfwtC3Ej2tg==, pdfFileSize=1916550, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=1OQgs2N21oBSNRDxPkYeqw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=3GUTVBHm98iHQvftOLrkXw==, mapNumber=null, authorCompany=null, fund=null, authors=

张雷,男,博士,教授,博士生导师。

, authorsList=张雷, 徐钦, 赵万良, 成宇翔, 孙研)}, authors=[Author(id=1253994400527347890, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, 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=1253994400615428279, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, authorId=1253994400527347890, language=EN, stringName=Lei ZHANG, firstName=Lei, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai 201210
2The Key Laboratory of Road and Traffic Engineering Ministry of Education, Tongji University, Shanghai 201804, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1253994400703508668, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, authorId=1253994400527347890, language=CN, stringName=张雷, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1同济大学 上海自主智能无人系统科学中心·上海·201210
2同济大学 道路与交通工程教育部重点实验室·上海·201804, bio={"content":"

张雷,男,博士,教授,博士生导师。

"}, bioImg=null, bioContent=

张雷,男,博士,教授,博士生导师。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1253994400250523806, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, xref=1, ext=[AuthorCompanyExt(id=1253994400258912415, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, companyId=1253994400250523806, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai 201210), AuthorCompanyExt(id=1253994400271495328, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, companyId=1253994400250523806, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1同济大学 上海自主智能无人系统科学中心·上海·201210)]), AuthorCompany(id=1253994400351187107, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, xref=2, ext=[AuthorCompanyExt(id=1253994400359575716, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, companyId=1253994400351187107, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2The Key Laboratory of Road and Traffic Engineering Ministry of Education, Tongji University, Shanghai 201804), AuthorCompanyExt(id=1253994400367964325, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, companyId=1253994400351187107, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2同济大学 道路与交通工程教育部重点实验室·上海·201804)])]), Author(id=1253994400774811837, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, 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=1253994400841920706, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, authorId=1253994400774811837, language=EN, stringName=Qin XU, firstName=Qin, middleName=null, lastName=XU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2The Key Laboratory of Road and Traffic Engineering Ministry of Education, Tongji University, Shanghai 201804, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1253994400971944134, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, authorId=1253994400774811837, language=CN, stringName=徐钦, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2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=1253994400351187107, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, xref=2, ext=[AuthorCompanyExt(id=1253994400359575716, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, companyId=1253994400351187107, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2The Key Laboratory of Road and Traffic Engineering Ministry of Education, Tongji University, Shanghai 201804), AuthorCompanyExt(id=1253994400367964325, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, companyId=1253994400351187107, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2同济大学 道路与交通工程教育部重点实验室·上海·201804)])]), Author(id=1253994401127133387, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, 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=1253994401223602384, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, authorId=1253994401127133387, language=EN, stringName=Wanliang ZHAO, firstName=Wanliang, middleName=null, lastName=ZHAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3Shanghai Aerospace Control Technology Institute, Shanghai 201109, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1253994401315877076, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, authorId=1253994401127133387, language=CN, stringName=赵万良, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3上海航天控制技术研究所·上海·201109, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1253994400443461801, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, xref=3, ext=[AuthorCompanyExt(id=1253994400456044714, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, companyId=1253994400443461801, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3Shanghai Aerospace Control Technology Institute, Shanghai 201109), AuthorCompanyExt(id=1253994400464433324, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, companyId=1253994400443461801, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3上海航天控制技术研究所·上海·201109)])]), Author(id=1253994401403957462, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, 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=1253994401504620764, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, authorId=1253994401403957462, language=EN, stringName=Yuxiang CHENG, firstName=Yuxiang, middleName=null, lastName=CHENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3Shanghai Aerospace Control Technology Institute, Shanghai 201109, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1253994401571729631, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, authorId=1253994401403957462, language=CN, stringName=成宇翔, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3上海航天控制技术研究所·上海·201109, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1253994400443461801, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, xref=3, ext=[AuthorCompanyExt(id=1253994400456044714, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, companyId=1253994400443461801, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3Shanghai Aerospace Control Technology Institute, Shanghai 201109), AuthorCompanyExt(id=1253994400464433324, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, companyId=1253994400443461801, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3上海航天控制技术研究所·上海·201109)])]), Author(id=1253994401647227106, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, orderNo=4, 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=1253994401722724581, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, authorId=1253994401647227106, language=EN, stringName=Yan SUN, firstName=Yan, middleName=null, lastName=SUN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2The Key Laboratory of Road and Traffic Engineering Ministry of Education, Tongji University, Shanghai 201804, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1253994401810804968, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, authorId=1253994401647227106, language=CN, stringName=孙研, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2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=1253994400351187107, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, xref=2, ext=[AuthorCompanyExt(id=1253994400359575716, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, companyId=1253994400351187107, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2The Key Laboratory of Road and Traffic Engineering Ministry of Education, Tongji University, Shanghai 201804), AuthorCompanyExt(id=1253994400367964325, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, companyId=1253994400351187107, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2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=1253994401940828397, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, language=EN, orderNo=1, keyword=integrated navigation), Keyword(id=1253994402003742960, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, language=EN, orderNo=2, keyword=attention model), Keyword(id=1253994402087629043, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, language=EN, orderNo=3, keyword=time series), Keyword(id=1253994402288955638, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, language=EN, orderNo=4, keyword=track traffic), Keyword(id=1253994402364453113, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, language=EN, orderNo=5, keyword=Kalman filtering), Keyword(id=1253994402444144891, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, language=CN, orderNo=1, keyword=组合导航), Keyword(id=1253994402511253757, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, language=CN, orderNo=2, keyword=注意力模型), Keyword(id=1253994402590945537, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, language=CN, orderNo=3, keyword=时间序列), Keyword(id=1253994402783883522, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, language=CN, orderNo=4, keyword=轨道交通), Keyword(id=1253994404335776005, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, language=CN, orderNo=5, keyword=卡尔曼滤波)], refs=[Reference(id=1253994405728284972, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2024, volume=7, issue=3, pageStart=22, pageEnd=30, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=刘丰宇, 程向红, 李艺恒, journalName=飞控与探测, refType=null, unstructuredReference=刘丰宇,程向红,李艺恒,.基于惯性/仿生视觉/激光雷达的智能感知无人系统[J].飞控与探测,2024, 7(3):22-30., articleTitle=基于惯性/仿生视觉/激光雷达的智能感知无人系统, refAbstract=null), Reference(id=1253994405803782447, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2024, volume=7, issue=3, pageStart=22, pageEnd=30, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=LIU F Y, CHENG X H, LI Y H, journalName=Flight Control & Detection, refType=null, unstructuredReference=LIU F Y,CHENG X H,LI Y H,et al.INS/bionic vision/LiDAR based intelligent perception unmanned system[J].Flight Control & Detection,2024,7(3):22-30(in Chinese)., articleTitle=INS/bionic vision/LiDAR based intelligent perception unmanned system, refAbstract=null), Reference(id=1253994405875085618, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, 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=QIN T, PAN J, CAO S, journalName=arXiv:1901.03642, refType=null, unstructuredReference=QIN T,PAN J,CAO S,et al.A general optimization-based framework for global pose estimation with multiple sensors[J/OL].arXiv:1901.03642.https://doi.org/10.48550/arXiv.1901.03642, articleTitle=A general optimization-based framework for global pose estimation with multiple sensors, refAbstract=null), Reference(id=1253994405975748917, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2018, volume=34, issue=4, pageStart=1004, pageEnd=1020, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=QIN T, LI P, SHEN S, journalName=IEEE Transactions on Robotics, refType=null, unstructuredReference=QIN T,LI P,SHEN S,et al.VINS-Mono:a robust and versatile monocular visual-inertial state estimator[J].IEEE Transactions on Robotics,2018,34(4):1004-1020., articleTitle=VINS-Mono:a robust and versatile monocular visual-inertial state estimator, refAbstract=null), Reference(id=1253994406088995129, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2023, volume=42, issue=3, pageStart=262, pageEnd=267,282, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=夏鸿, 何泉, 蒲磊, journalName=成都大学学报(自然科学版), refType=null, unstructuredReference=夏鸿,何泉,蒲磊,.神经网络提升低成本软件定义的无线电无人机探测平台定位准确率研究[J].成都大学学报(自然科学版),2023,42(3):262-267,282., articleTitle=神经网络提升低成本软件定义的无线电无人机探测平台定位准确率研究, refAbstract=null), Reference(id=1253994406181269819, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2023, volume=42, issue=3, pageStart=262, pageEnd=267,282, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=XIA H, HE Q, PU L, journalName=Journal of Chengdu University (Natural Science Edition), refType=null, unstructuredReference=XIA H,HE Q,PU L,et al.Research on using neural network to improve accuracy of radio platform for UAV detection defined by low-cost software[J]. Journal of Chengdu University (Natural Science Edition),2023,42(3):262-267,282(in Chinese)., articleTitle=Research on using neural network to improve accuracy of radio platform for UAV detection defined by low-cost software, refAbstract=null), Reference(id=1253994406273544509, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=朱明红, journalName=基于低成本IMU的通用多传感器集成动态定位关键技术研究, refType=null, unstructuredReference=朱明红.基于低成本IMU的通用多传感器集成动态定位关键技术研究[D].哈尔滨:哈尔滨工程大学,2021., articleTitle=null, refAbstract=null), Reference(id=1253994406340653375, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=ZHU M H, journalName=Research on key technologies of generic multi-sensor integrated kinematic positioning based on low-cost IMU, refType=null, unstructuredReference=ZHU M H.Research on key technologies of generic multi-sensor integrated kinematic positioning based on low-cost IMU[D].Harbin:Harbin Engineering University,2021 (in Chinese)., articleTitle=null, refAbstract=null), Reference(id=1253994406424539456, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=7, pageStart=147, pageEnd=151, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=房博乐, 梁永, 楼梁伟, journalName=测绘通报, refType=null, unstructuredReference=房博乐,梁永,楼梁伟.北斗-INS普速铁路精测精捣方法及应用[J].测绘通报,2024(7):147-151., articleTitle=北斗-INS普速铁路精测精捣方法及应用, refAbstract=null), Reference(id=1253994406495842626, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=7, pageStart=147, pageEnd=151, url=null, language=null, rfNumber=[6], rfOrder=9, authorNames=FANG B L, LIANG Y, LOU L W, journalName=Bulletin of Surveying and Mapping, refType=null, unstructuredReference=FANG B L,LIANG Y,LOU L W.Beidou-INS precision measurement and tamping method for ordinary speed railway[J].Bulletin of Surveying and Mapping, 2024(7):147-151(in Chinese)., articleTitle=Beidou-INS precision measurement and tamping method for ordinary speed railway, refAbstract=null), Reference(id=1253994406579728709, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=1, pageStart=120, pageEnd=129, url=null, language=null, rfNumber=[7], rfOrder=10, authorNames=陈熙源, 周云川, 钟雨露, journalName=仪器仪表学报, refType=null, unstructuredReference=陈熙源,周云川,钟雨露,.基于变分贝叶斯的鲁棒自适应因子图优化组合导航算法[J].仪器仪表学报,2024,45(1):120-129., articleTitle=基于变分贝叶斯的鲁棒自适应因子图优化组合导航算法, refAbstract=null), Reference(id=1253994406663614792, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=1, pageStart=120, pageEnd=129, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=CHEN X Y, ZHOU Y C, ZHONG Y L, journalName=Chinese Journal of Scientific Instrument, refType=null, unstructuredReference=CHEN X Y,ZHOU Y C,ZHONG Y L,et al.Robust adaptive factor graph optimization integrated navigation algorithm based on variational Bayesian[J].Chinese Journal of Scientific Instrument,2024,45(1):120-129(in Chinese)., articleTitle=Robust adaptive factor graph optimization integrated navigation algorithm based on variational Bayesian, refAbstract=null), Reference(id=1253994406730723659, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2024, volume=46, issue=13, pageStart=141, pageEnd=145, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=傅金琳, 王毅, 阎磊, journalName=舰船科学技术, refType=null, unstructuredReference=傅金琳,王毅,阎磊.卫导受限下惯导/数据链/卫导紧组合导航方法[J].舰船科学技术,2024,46(13):141-145., articleTitle=卫导受限下惯导/数据链/卫导紧组合导航方法, refAbstract=null), Reference(id=1253994406802026828, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2024, volume=46, issue=13, pageStart=141, pageEnd=145, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=FU J L, WANG Y, YAN L, journalName=Ship Science and Technology, refType=null, unstructuredReference=FU J L,WANG Y,YAN L.INS/DL/GNSS tightly coupled integrated navigation method under GNSS restricted conditions[J].Ship Science and Technology, 2024,46(13):141-145(in Chinese)., articleTitle=INS/DL/GNSS tightly coupled integrated navigation method under GNSS restricted conditions, refAbstract=null), Reference(id=1253994406890107215, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2023, volume=6, issue=3, pageStart=95, pageEnd=102, url=null, language=null, rfNumber=[9], rfOrder=14, authorNames=郭驿众, 李根, 许佳斌, journalName=飞控与探测, refType=null, unstructuredReference=郭驿众,李根,许佳斌,.基于ArUco码的无地图AMR视觉辅助归航方法[J].飞控与探测,2023,6(3):95-102., articleTitle=基于ArUco码的无地图AMR视觉辅助归航方法, refAbstract=null), Reference(id=1253994406978187602, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2023, volume=6, issue=3, pageStart=95, pageEnd=102, url=null, language=null, rfNumber=[9], rfOrder=15, authorNames=GUO Y Z, LI G, XU J B, journalName=Flight Control & Detection, refType=null, unstructuredReference=GUO Y Z,LI G,XU J B,et al.An ArUco marker-based homing method for visual-aid AMR without map building[J].Flight Control & Detection,2023, 6(3):95-102(in Chinese)., articleTitle=An ArUco marker-based homing method for visual-aid AMR without map building, refAbstract=null), Reference(id=1253994407049490772, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2022, volume=50, issue=1, pageStart=79, pageEnd=86, url=null, language=null, rfNumber=[10], rfOrder=16, authorNames=张雷, 沈国琛, 秦晓洁, journalName=同济大学学报(自然科学版), refType=null, unstructuredReference=张雷,沈国琛,秦晓洁,.智能网联交通系统中的信息物理映射与系统构建[J].同济大学学报(自然科学版),2022,50(1):79-86., articleTitle=智能网联交通系统中的信息物理映射与系统构建, refAbstract=null), Reference(id=1253994407145959766, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2022, volume=50, issue=1, pageStart=79, pageEnd=86, url=null, language=null, rfNumber=[10], rfOrder=17, authorNames=ZHANG L, SHEN G C, QIN X J, journalName=Journal of Tongji University (Natural Science), refType=null, unstructuredReference=ZHANG L,SHEN G C,QIN X J,et al.Informationphysical mapping and system construction of intelligent network transportation[J].Journal of Tongji University (Natural Science),2022,50(1):79-86(in Chinese)., articleTitle=Informationphysical mapping and system construction of intelligent network transportation, refAbstract=null), Reference(id=1253994408735600984, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=18, authorNames=林雪原, 孙炜玮, journalName=大地测量与地球动力学, refType=null, unstructuredReference=林雪原,孙炜玮.基于指数加权平均的GNSS/SINS组合导航系统Sage-Husa自适应卡尔曼滤波算法[J/OL].大地测量与地球动力学,https://doi.org/10., articleTitle=基于指数加权平均的GNSS/SINS组合导航系统Sage-Husa自适应卡尔曼滤波算法, refAbstract=null), Reference(id=1253994408832069977, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=19, authorNames=LIN X Y, SUN W W, journalName=Journal of Geodesy and Geodynamics, refType=null, unstructuredReference=LIN X Y,SUN W W.Sage-Husa adaptive Kalman filtering algorithm for GNSS/SINS integrated navigation system based on exponential weighted average[J/OL].Journal of Geodesy and Geodynamics,https://doi.org/10.14075/j.jgg.2024.02.068(in Chinese)., articleTitle=Sage-Husa adaptive Kalman filtering algorithm for GNSS/SINS integrated navigation system based on exponential weighted average, refAbstract=null), Reference(id=1253994408928538970, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2024, volume=37, issue=7, pageStart=280, pageEnd=290, url=null, language=null, rfNumber=[12], rfOrder=20, authorNames=魏文辉, 袁伟, 张逸凡, journalName=中国公路学报, refType=null, unstructuredReference=魏文辉,袁伟,张逸凡.智能汽车SINS/GNSS动态组合导航观测模型系统误差自适应估计方法[J].中国公路学报,2024,37(7):280-290., articleTitle=智能汽车SINS/GNSS动态组合导航观测模型系统误差自适应估计方法, refAbstract=null), Reference(id=1253994409004036443, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2024, volume=37, issue=7, pageStart=280, pageEnd=290, url=null, language=null, rfNumber=[12], rfOrder=21, authorNames=WEI W H, YUAN W, ZHANG Y F, journalName=China Journal of Highway and Transport, refType=null, unstructuredReference=WEI W H,YUAN W,ZHANG Y F.Adaptive estimation method of observational model systematic errors for intelligent vehicle SINS/GNSS dynamic integrated navigation[J].China Journal of Highway and Transport,2024,37(7):280-290(in Chinese)., articleTitle=Adaptive estimation method of observational model systematic errors for intelligent vehicle SINS/GNSS dynamic integrated navigation, refAbstract=null), Reference(id=1253994409075339612, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2024, volume=11, issue=6, pageStart=113, pageEnd=122, url=null, language=null, rfNumber=[13], rfOrder=22, authorNames=蔡灿烽, 许智理, 申志恒, journalName=导航定位与授时, refType=null, unstructuredReference=蔡灿烽,许智理,申志恒,.基于冗余GNSS观测的RTK/INS紧组合方法[J].导航定位与授时,2024,11(6):113-122., articleTitle=基于冗余GNSS观测的RTK/INS紧组合方法, refAbstract=null), Reference(id=1253994409138254173, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2024, volume=11, issue=6, pageStart=113, pageEnd=122, url=null, language=null, rfNumber=[13], rfOrder=23, authorNames=CAI C F, XU Z L, SHEN Z H, journalName=Navigation Positioning and Timing, refType=null, unstructuredReference=CAI C F,XU Z L,SHEN Z H,et al.The tightly coupled RTK/INS integration method based on re dundant GNSS measurement[J].Navigation Positioning and Timing,2024,11(6):113-122(in Chinese)., articleTitle=The tightly coupled RTK/INS integration method based on re dundant GNSS measurement, refAbstract=null), Reference(id=1253994409209557342, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2024, volume=41, issue=6, pageStart=282, pageEnd=286, url=null, language=null, rfNumber=[14], rfOrder=24, authorNames=侯华, 程萌, 黄鼎盛, journalName=计算机应用与软件, refType=null, unstructuredReference=侯华,程萌,黄鼎盛,.基于VB-EKF的GPS/INS松组合导航定位算法[J].计算机应用与软件,2024, 41(6):282-286., articleTitle=基于VB-EKF的GPS/INS松组合导航定位算法, refAbstract=null), Reference(id=1253994409293443423, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2024, volume=41, issue=6, pageStart=282, pageEnd=286, url=null, language=null, rfNumber=[14], rfOrder=25, authorNames=HOU H, CHENG M, HUANG D S, journalName=Computer Applications and Software, refType=null, unstructuredReference=HOU H,CHENG M,HUANG D S,et al.GPS/INS loose integrated navigation and positioning algorithm based on VB-EKF[J].Computer Applications and Software,2024,41(6):282-286(in Chinese)., articleTitle=GPS/INS loose integrated navigation and positioning algorithm based on VB-EKF, refAbstract=null), Reference(id=1253994409377329504, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2022, volume=36, issue=6, pageStart=73, pageEnd=81, url=null, language=null, rfNumber=[15], rfOrder=26, authorNames=张艳, 王宇, journalName=电子测量与仪器学报, refType=null, unstructuredReference=张艳,王宇.基于视觉里程计的室内位姿测量技术研究[J].电子测量与仪器学报,2022,36(6):73-81., articleTitle=基于视觉里程计的室内位姿测量技术研究, refAbstract=null), Reference(id=1253994409465409889, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2022, volume=36, issue=6, pageStart=73, pageEnd=81, url=null, language=null, rfNumber=[15], rfOrder=27, authorNames=ZHANG Y, WANG Y, journalName=Journal of Electronic Measurement and Instrumentation, refType=null, unstructuredReference=ZHANG Y,WANG Y.Design and implementation method of a visual odometer[J].Journal of Electronic Measurement and Instrumentation,2022,36(6):73-81(in Chinese)., articleTitle=Design and implementation method of a visual odometer, refAbstract=null), Reference(id=1253994409540907362, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=95, pageEnd=104, url=null, language=null, rfNumber=[16], rfOrder=28, authorNames=LAI G, CHANG W C, YANG Y, journalName=null, refType=null, unstructuredReference=LAI G,CHANG W C,YANG Y,et al.Modeling long-and short-term temporal patterns with deep neural networks[C]//The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval.Ann Arbor,MI,USA:Association for Computing Machinery.2018:95-104., articleTitle=Modeling long-and short-term temporal patterns with deep neural networks, refAbstract=null), Reference(id=1253994409633182051, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2020, volume=399, issue=null, pageStart=491, pageEnd=501, url=null, language=null, rfNumber=[17], rfOrder=29, authorNames=CHEN Y, KANG Y, CHEN Y, journalName=Neurocomputing, refType=null, unstructuredReference=CHEN Y,KANG Y,CHEN Y,et al.Probabilistic forecasting with temporal convolutional neural network[J].Neurocomputing,2020,399:491-501., articleTitle=Probabilistic forecasting with temporal convolutional neural network, refAbstract=null), Reference(id=1253994409712873828, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=30, authorNames=LIU S, YU H, LIAO C, journalName=null, refType=null, unstructuredReference=LIU S,YU H,LIAO C,et al.Pyraformer:low-complexity pyramidal attention for long-range time series modeling and forecasting[C]//International Conference on Learning Representations,International Machine Learning Society,2022., articleTitle=Pyraformer:low-complexity pyramidal attention for long-range time series modeling and forecasting, refAbstract=null), Reference(id=1253994409792565605, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2021, volume=37, issue=4, pageStart=1748, pageEnd=1764, url=null, language=null, rfNumber=[19], rfOrder=31, authorNames=LIM B, ARIK S Ö, LOEFF N, journalName=International Journal of Forecasting, refType=null, unstructuredReference=LIM B,ARIK S Ö,LOEFF N,et al.Temporal fusion transformers for interpretable multi-horizon time series forecasting[J].International Journal of Forecasting, 2021,37(4):1748-1764., articleTitle=Temporal fusion transformers for interpretable multi-horizon time series forecasting, refAbstract=null), Reference(id=1253994409884840294, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2024, volume=36, issue=8, pageStart=1810, pageEnd=1822, url=null, language=null, rfNumber=[20], rfOrder=32, authorNames=匡兴红, 黄傲威, journalName=系统仿真学报, refType=null, unstructuredReference=匡兴红,黄傲威.一种基于深度学习辅助的SINS/DVL组合导航方法[J].系统仿真学报,2024,36(8):1810-1822., articleTitle=一种基于深度学习辅助的SINS/DVL组合导航方法, refAbstract=null), Reference(id=1253994409985503591, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2024, volume=36, issue=8, pageStart=1810, pageEnd=1822, url=null, language=null, rfNumber=[20], rfOrder=33, authorNames=KUANG X H, HUANG A W, journalName=Journal of System Simulation, refType=null, unstructuredReference=KUANG X H,HUANG A W.A method based on deep learning for assisting SINS/DVL integrated navigation[J].Journal of System Simulation,2024,36(8):1810-1822(in Chinese)., articleTitle=A method based on deep learning for assisting SINS/DVL integrated navigation, refAbstract=null), Reference(id=1253994410081972584, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=19, pageStart=7389, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=34, authorNames=XU Q, ZHANG L, YU W, journalName=Sensors, refType=null, unstructuredReference=XU Q,ZHANG L,YU W.A localization method of ant colony optimization in nonuniform space[J].Sensors,2022,22(19):7389., articleTitle=A localization method of ant colony optimization in nonuniform space, refAbstract=null), Reference(id=1253994410228773225, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2021, volume=46, issue=2, pageStart=104, pageEnd=110, url=null, language=null, rfNumber=[22], rfOrder=35, authorNames=储诚涛, 吴峻, journalName=全球定位系统, refType=null, unstructuredReference=储诚涛,吴峻.神经网络在SINS/GPS组合定位中的应用[J].全球定位系统,2021,46(2):104-110., articleTitle=神经网络在SINS/GPS组合定位中的应用, refAbstract=null), Reference(id=1253994410300076394, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2021, volume=46, issue=2, pageStart=104, pageEnd=110, url=null, language=null, rfNumber=[22], rfOrder=36, authorNames=CHU C T, WU J, journalName=GNSS World of China, refType=null, unstructuredReference=CHU C T,WU J.Application of neural network in SINS/GPS combined positioning[J].GNSS World of China,2021,46(2):104-110(in Chinese)., articleTitle=Application of neural network in SINS/GPS combined positioning, refAbstract=null), Reference(id=1253994410375573867, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2021, volume=68, issue=1, pageStart=499, pageEnd=508, url=null, language=null, rfNumber=[23], rfOrder=37, authorNames=SHEN C, ZHANG Y, GUO X, journalName=IEEE Transactions on Industrial Electronics, refType=null, unstructuredReference=SHEN C,ZHANG Y,GUO X,et al.Seamless GPS/inertial navigation system based on self-learning square-root cubature Kalman filter[J].IEEE Transactions on Industrial Electronics,2021,68(1):499-508., articleTitle=Seamless GPS/inertial navigation system based on self-learning square-root cubature Kalman filter, refAbstract=null), Reference(id=1253994410446877036, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, doi=null, pmid=null, pmcid=null, year=2021, volume=34, issue=null, pageStart=23592, pageEnd=23608, url=null, language=null, rfNumber=[24], rfOrder=38, authorNames=TANG B, MATTESON D S, journalName=Advances in Neural Information Processing Systems, refType=null, unstructuredReference=TANG B,MATTESON D S.Probabilistic transformer for time series analysis[J].Advances in Neural Information Processing Systems,2021,34:23592-23608., articleTitle=Probabilistic transformer for time series analysis, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1253994400250523806, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, xref=1, ext=[AuthorCompanyExt(id=1253994400258912415, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, companyId=1253994400250523806, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai 201210), AuthorCompanyExt(id=1253994400271495328, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, companyId=1253994400250523806, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1同济大学 上海自主智能无人系统科学中心·上海·201210)]), AuthorCompany(id=1253994400351187107, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, xref=2, ext=[AuthorCompanyExt(id=1253994400359575716, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, companyId=1253994400351187107, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2The Key Laboratory of Road and Traffic Engineering Ministry of Education, Tongji University, Shanghai 201804), AuthorCompanyExt(id=1253994400367964325, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, companyId=1253994400351187107, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2同济大学 道路与交通工程教育部重点实验室·上海·201804)]), AuthorCompany(id=1253994400443461801, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, xref=3, ext=[AuthorCompanyExt(id=1253994400456044714, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, companyId=1253994400443461801, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3Shanghai Aerospace Control Technology Institute, Shanghai 201109), AuthorCompanyExt(id=1253994400464433324, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, companyId=1253994400443461801, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3上海航天控制技术研究所·上海·201109)])], figs=[ArticleFig(id=1253994404444827912, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, language=EN, label=Fig.1, caption=The structure of probabilistic time series transformer, figureFileSmall=qK7leN7Jh87vEg7fgO0YsQ==, figureFileBig=1OQgs2N21oBSNRDxPkYeqw==, tableContent=null), ArticleFig(id=1253994404524519691, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, language=CN, label=图1, caption=PTST结构图, figureFileSmall=qK7leN7Jh87vEg7fgO0YsQ==, figureFileBig=1OQgs2N21oBSNRDxPkYeqw==, tableContent=null), ArticleFig(id=1253994404734234896, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, language=EN, label=Fig.2, caption=The structure of integrated navigation system based on probabilistic time series transformer, figureFileSmall=RvQ930YrhnHwsWHSXV7Brw==, figureFileBig=D9cblcy9knG8lKH1nah6YA==, tableContent=null), ArticleFig(id=1253994404822315283, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, language=CN, label=图2, caption=基于概率时间序列注意力模型的组合导航系统结构图, figureFileSmall=RvQ930YrhnHwsWHSXV7Brw==, figureFileBig=D9cblcy9knG8lKH1nah6YA==, tableContent=null), ArticleFig(id=1253994404889424150, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, language=EN, label=Fig.3, caption=GNSS outage interval integrated navigation, figureFileSmall=QjezWeCcn+VI6EAmg0riSg==, figureFileBig=HBPqxJipQjPotrZ9lblBiQ==, tableContent=null), ArticleFig(id=1253994404960727321, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, language=CN, label=图3, caption=GNSS失锁区间组合导航, figureFileSmall=QjezWeCcn+VI6EAmg0riSg==, figureFileBig=HBPqxJipQjPotrZ9lblBiQ==, tableContent=null), ArticleFig(id=1253994405032030491, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, language=EN, label=Fig.4, caption=Planar trajectory of the experiment, figureFileSmall=ACkCmSq18TNdGZTLVnD2Ow==, figureFileBig=sIgx1fg/bV/FZO1qx0Ru8A==, tableContent=null), ArticleFig(id=1253994405099139358, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, language=CN, label=图4, caption=现场实验平面轨迹, figureFileSmall=ACkCmSq18TNdGZTLVnD2Ow==, figureFileBig=sIgx1fg/bV/FZO1qx0Ru8A==, tableContent=null), ArticleFig(id=1253994405178831135, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, language=EN, label=Fig.5, caption=The position errors in each axis direction were compensated by using the PTST model in the experiment, figureFileSmall=6l8XFGXYkv/EuH26o4frWg==, figureFileBig=kFCendsevBYPEpfi45o6EA==, tableContent=null), ArticleFig(id=1253994405266911520, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, language=CN, label=图5, caption=实验中使用PTST模型补偿后各轴向位置误差, figureFileSmall=6l8XFGXYkv/EuH26o4frWg==, figureFileBig=kFCendsevBYPEpfi45o6EA==, tableContent=null), ArticleFig(id=1253994405338214689, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, language=EN, label=Tab.1, caption=

Experiment parameter

, figureFileSmall=null, figureFileBig=null, tableContent=
类型参数数值采样率
IMU陀螺仪零偏6×10-4 (°)/s1000Hz
陀螺仪角度随机游走
加速度零偏10-5gg=9.18m/s2
加速度随机游走3×10-5g
GNSS水平定位精度1.5m10Hz
垂直定位精度2.5m
滤波初始值初始位置误差[3,3,3]m
初始速度误差[0.3,0.3,0.3]m/s
初始姿态误差δq0 = [3,0.15,0.15,0.15]T
初始系统误差μ0 = [3,3,3]T
), ArticleFig(id=1253994405413712163, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, language=CN, label=表1, caption=

实验参数

, figureFileSmall=null, figureFileBig=null, tableContent=
类型参数数值采样率
IMU陀螺仪零偏6×10-4 (°)/s1000Hz
陀螺仪角度随机游走
加速度零偏10-5gg=9.18m/s2
加速度随机游走3×10-5g
GNSS水平定位精度1.5m10Hz
垂直定位精度2.5m
滤波初始值初始位置误差[3,3,3]m
初始速度误差[0.3,0.3,0.3]m/s
初始姿态误差δq0 = [3,0.15,0.15,0.15]T
初始系统误差μ0 = [3,3,3]T
), ArticleFig(id=1253994405501792549, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, language=EN, label=Tab.2, caption=

Comparison of prediction error between PTST model and baseline algorithm

, figureFileSmall=null, figureFileBig=null, tableContent=
X轴向误差/mY轴向误差/m高程误差/m
最大值平均值均方根最大值平均值均方根最大值平均值均方根
ARIMA隧道区域56.0232.6338.4263.8536.6443.2518.7112.0915.63
遮挡区域15.697.7510.3919.5112.5514.4711.736.236.57
LSTM隧道区域23.8313.9514.2326.0915.7618.1512.356.736.92
遮挡区域15.538.7710.8019.3413.6516.3310.604.895.75
Deep-TCN隧道区域16.629.3711.6218.0011.1915.5110.364.195.41
遮挡区域13.287.728.8211.726.877.637.474.384.72
PTST隧道区域13.626.486.7314.145.697.209.213.874.31
遮挡区域9.874.194.658.924.525.367.253.163.40
), ArticleFig(id=1253994405585678632, tenantId=1146029695717560320, journalId=1251234571887362144, articleId=1253994379954287410, language=CN, label=表2, caption=

PTST模型与基线算法预测误差数据对比

, figureFileSmall=null, figureFileBig=null, tableContent=
X轴向误差/mY轴向误差/m高程误差/m
最大值平均值均方根最大值平均值均方根最大值平均值均方根
ARIMA隧道区域56.0232.6338.4263.8536.6443.2518.7112.0915.63
遮挡区域15.697.7510.3919.5112.5514.4711.736.236.57
LSTM隧道区域23.8313.9514.2326.0915.7618.1512.356.736.92
遮挡区域15.538.7710.8019.3413.6516.3310.604.895.75
Deep-TCN隧道区域16.629.3711.6218.0011.1915.5110.364.195.41
遮挡区域13.287.728.8211.726.877.637.474.384.72
PTST隧道区域13.626.486.7314.145.697.209.213.874.31
遮挡区域9.874.194.658.924.525.367.253.163.40
)], attaches=null, journal=Journal(id=1251231495105327204, delFlag=0, nameCn=飞控与探测, nameEn=Flight Control & Detection, nameHistory1=null, nameHistory2=null, issn=2096-5974, eissn=, cn=10-1567/TJ, coden=null, periodic=1, language=CN, oaType=1, 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=, officePhone=, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=62VTU3mFmPrlNa8O4U3NDw==, journalPrice=null, startedYear=null, abbrevIsoEn=Flight Control & Detection, journalRemark=null, publicationField=null, createdTime=1776246435193, updatedTime=1776397610259, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=F, firstLetterEn=F, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=62VTU3mFmPrlNa8O4U3NDw==, picEn=A2zKCSNdCDHegCegMgaNMQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1251865569406960556, language=CN, name=飞控与探测, 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=1776397610284, updatedTime=1776397610284, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://fkytc.ijournal.cn/ch/author/login.aspx, submissionEditorUrl=http://fkytc.ijournal.cn/ch/login.aspx, submissionReviewUrl=http://fkytc.ijournal.cn/ch/auditor/login.aspx, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1251865569457292205, language=EN, name=Flight Control & Detection, 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=1776397610296, updatedTime=1776397610296, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://fkytc.ijournal.cn/ch/author/login.aspx, submissionEditorUrl=http://fkytc.ijournal.cn/ch/login.aspx, submissionReviewUrl=http://fkytc.ijournal.cn/ch/auditor/login.aspx, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1251234571887362144, websiteList=[Website(id=1251257283523592241, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1251234571887362144, 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/fkytc/CN, language=CN, createTime=1776252583628, createBy=18614031015, updateTime=1776253801088, updateBy=18614031015, name=飞控与探测-中文, tplId=1146099689490845704, title=飞控与探测, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1251262529310241438, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283523592241, code=articleTextType, value=kx, createTime=1776253834321, updateTime=1776253834321, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262529289269915, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283523592241, code=banner, value=null, createTime=1776253834316, updateTime=1776253834316, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262529331212961, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283523592241, code=grayFlag, value=0, createTime=1776253834326, updateTime=1776253834326, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262529285075610, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283523592241, code=logo, value=https://castjournals.cast.org.cn/joweb/fkytc/CN/file/pic?fileId=i7mLZwFALt9PMt6SohU8eg==, createTime=1776253834315, updateTime=1776253834315, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262529343795875, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283523592241, code=minRunFlag, value=0, createTime=1776253834329, updateTime=1776253834329, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262529306047133, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283523592241, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/fkytc/CN/file/pic, createTime=1776253834320, updateTime=1776253834320, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262529335407266, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283523592241, code=silenceFlag, value=0, createTime=1776253834327, updateTime=1776253834327, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262529297658524, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283523592241, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1776253834318, updateTime=1776253834318, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262529318630047, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283523592241, code=themeColor, value=null, createTime=1776253834323, updateTime=1776253834323, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262529327018656, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283523592241, code=themeStyle, value=null, createTime=1776253834325, updateTime=1776253834325, creator=18614031015, updator=18614031015)]), Website(id=1251257283611672633, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1251234571887362144, 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/fkytc/EN, language=EN, createTime=1776252583649, createBy=18614031015, updateTime=1776253797406, updateBy=18614031015, name=飞控与探测-英文, tplId=1146101810881728533, title=Flight Control & Detection, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1251262470745174676, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283611672633, code=articleTextType, value=kx, createTime=1776253820358, updateTime=1776253820358, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262470724203153, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283611672633, code=banner, value=null, createTime=1776253820353, updateTime=1776253820353, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262470766146199, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283611672633, code=grayFlag, value=0, createTime=1776253820363, updateTime=1776253820363, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262470711620240, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283611672633, code=logo, value=https://castjournals.cast.org.cn/joweb/fkytc/EN/file/pic?fileId=i7mLZwFALt9PMt6SohU8eg==, createTime=1776253820350, updateTime=1776253820350, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262470778729113, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283611672633, code=minRunFlag, value=0, createTime=1776253820366, updateTime=1776253820366, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262470736786067, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283611672633, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/fkytc/EN/file/pic, createTime=1776253820356, updateTime=1776253820356, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262470770340504, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283611672633, code=silenceFlag, value=0, createTime=1776253820364, updateTime=1776253820364, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262470732591762, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283611672633, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1776253820355, updateTime=1776253820355, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262470749368981, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283611672633, code=themeColor, value=null, createTime=1776253820359, updateTime=1776253820359, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262470757757590, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283611672633, code=themeStyle, value=null, createTime=1776253820361, updateTime=1776253820361, creator=18614031015, updator=18614031015)])], journalTitle=飞控与探测, weixinUrl=null, journalUrl=http://fkytc.ijournal.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Flight Control & Detection, journalPhotoCn=62VTU3mFmPrlNa8O4U3NDw==, journalPhotoEn=A2zKCSNdCDHegCegMgaNMQ==, journalFirstLetter=F, 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/fkytc/CN/10.20249/j.cnki.2096-5974.2025.05.001, detailUrlEn=https://castjournals.cast.org.cn/joweb/fkytc/EN/10.20249/j.cnki.2096-5974.2025.05.001, pdfUrlCn=https://castjournals.cast.org.cn/joweb/fkytc/CN/PDF/10.20249/j.cnki.2096-5974.2025.05.001, pdfUrlEn=https://castjournals.cast.org.cn/joweb/fkytc/EN/PDF/10.20249/j.cnki.2096-5974.2025.05.001, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于概率时间序列注意力模型的概率图优化组合导航算法
收藏切换
PDF下载
张雷 1, 2 , 徐钦 2 , 赵万良 3 , 成宇翔 3 , 孙研 2
飞控与探测 | 导航制导与控制技术 2025,8(5): 1-10
收起
收藏切换
飞控与探测 | 导航制导与控制技术 2025, 8(5): 1-10
基于概率时间序列注意力模型的概率图优化组合导航算法
全屏
张雷1, 2, 徐钦2, 赵万良3, 成宇翔3, 孙研2
作者信息
  • 1同济大学 上海自主智能无人系统科学中心·上海·201210
  • 2同济大学 道路与交通工程教育部重点实验室·上海·201804
  • 3上海航天控制技术研究所·上海·201109
  • 张雷,男,博士,教授,博士生导师。

Probabilistic Graph Optimization Integrated Navigation Based on Probabilistic Time Series Transformer
Lei ZHANG1, 2, Qin XU2, Wanliang ZHAO3, Yuxiang CHENG3, Yan SUN2
Affiliations
  • 1Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai 201210
  • 2The Key Laboratory of Road and Traffic Engineering Ministry of Education, Tongji University, Shanghai 201804
  • 3Shanghai Aerospace Control Technology Institute, Shanghai 201109
doi: 10.20249/j.cnki.2096-5974.2025.05.001
文章导航
收藏切换

为满足现代轨道交通在复杂的环境条件下保持高精度和连续性的导航需求,解决非线性动态组合导航系统因观测数据失锁导致的定位漂移问题,结合基于概率时间序列注意力模型,提出一种新的非线性动态组合导航系统观测误差自适应估计方法,利用概率时间序列注意力模型,引入自学习能力,自适应调整状态预测和观测信息失锁状态对动态导航系统的影响。概率时间序列注意力模型由生成模型和推理模型组成双循环系统,并结合长短期记忆网络,以解决多变量时间序列建模问题。基于概率时间序列注意力模型的组合导航系统,通过建立当前卡尔曼滤波增益与最优估计误差之间的关系,优化误差补偿机制以提高非线性导航系统的精度和稳定性。实验结果表明,所提出的研究方法不仅能够控制GNSS失锁状态对非线性导航系统的影响,且能够有效地估计和补偿观测模型系统误差,各种复杂状态下滤波解算平均定位误差小于10m;抑制观测模型定位漂移优于其他滤波方法。

组合导航  /  注意力模型  /  时间序列  /  轨道交通  /  卡尔曼滤波

To satisfy the modern track traffic's demand for maintaining high precision and continuity of navigation under complex environmental conditions,and to address the issue of positioning drift caused by data outages in nonlinear dynamic integrated navigation systems,this paper proposes a novel adaptive estimation method for observation errors in nonlinear dynamic integrated navi gation systems. This method is based on a Probabilistic Time Series Transformer model,aiming to resolve the aforementioned issues. By introducing self-learning capabilities through the Probabilistic Time Series Transformer,the method adaptively adjusts the impact of state prediction and observation information outages on the dynamic navigation system. The Probabilistic Time Series Transformer is composed of a dual-loop system of a generative model and an inference model, combined with LSTM network to tackle the challenges of multivariate time series modeling. The integrated navigation system based on the Probabilistic Time Series Transformer optimizes the error compensation mechanism by establishing a relationship between the current Kalman filter gain and the optimal estimation error,thereby improving the accuracy and stability of the nonlinear navigation system. Experimental results demonstrate that the proposed method not only effectively controls the impact of GNSS outages on the nonlinear navigation system but also accurately estimates and compensates for observation model system errors. The average positioning error in various complex scenarios is less than 10m. The suppression of positioning drift in the observation model is better than that of other filtering methods.

integrated navigation  /  attention model  /  time series  /  track traffic  /  Kalman filtering
张雷, 徐钦, 赵万良, 成宇翔, 孙研. 基于概率时间序列注意力模型的概率图优化组合导航算法. 飞控与探测, 2025 , 8 (5) : 1 -10 . DOI: 10.20249/j.cnki.2096-5974.2025.05.001
Lei ZHANG, Qin XU, Wanliang ZHAO, Yuxiang CHENG, Yan SUN. Probabilistic Graph Optimization Integrated Navigation Based on Probabilistic Time Series Transformer[J]. Flight Control & Detection, 2025 , 8 (5) : 1 -10 . DOI: 10.20249/j.cnki.2096-5974.2025.05.001
在长期的工程实践中,轨道交通领域面临着复杂的地质条件、有限的运行空间以及各类系统的集成与支持等挑战。与此同时,随着我国轨道交通路网规模的扩展和运行速度的快速提升,在复杂场景下准确获取列车各时刻的速度与位置信息,已成为保障轨道交通系统正常运行的关键前提。这不仅是建设高效、鲁棒性强的交通体系的必要条件,更是确保系统稳定运行的基础。高效且鲁棒性强的交通运控系统需要在所有复杂场景下,全天候获取包括载体定位与速度在内的精确运行数据。
目前定位导航领域主要有全球导航卫星系统(Global Navigation Satellite System,GNSS)、惯性导航系统(Inertial Navigation System,INS)、基于无线电信号定位、视觉里程计和雷达里程计等导航定位方式[1]。其中惯性导航系统依赖惯性测量单元(Inertial Measurement Unit,IMU)基于增量思想通过递推积分求解姿态、速度、位置等定位导航参数,具有连续、自主性强且全天候等优点,但惯性测量单元增量式递推过程中易受噪声、重力和地球自转等干扰,导致误差迅速累积的同时定位精度随时间发散,因此惯性测量单元无法长时间进行独立导航[2-3]。全球导航卫星系统虽然能够提供不随时间发散且高精度的绝对位置和时间信息,但全球导航卫星系统的信号脆弱、可靠性低,在轨道交通所处地下通道、隧道等遮挡封闭环境中信号强度退化,会导致定位精度大幅降低。此外,无线电信号的定位技术依赖于轨旁基站的存在,建设成本高昂且在密集的城市环境或复杂的遮蔽场景中,信号的多路径传播和反射会显著降低定位精度[4-5]。而以视觉和雷达里程计为代表的感知定位,受限于视野域难以应用于光照条件复杂且缺乏显著视觉特征的轨道交通环境中。最后,视觉和雷达里程计涉及复杂的图像处理、特征匹配和点云分析,可能难以在列车高速行驶条件下实现实时处理,进而影响定位的及时性和准确性。
综上所述,具备自主、独立特性的GNSS/INS组合导航系统成为交通运控领域的主要导航解决方案[6]。该系统具有对列车实时定位与状态监控的能力,使得列车能够持续获取自身及其他列车的位置与速度信息,从而有效预防碰撞、协助检测轨道状况,并提高整体运行的安全性。此外,组合导航系统能够记录海量轨道交通运行数据,这些数据可用于后续的运行模式分析、潜在问题识别及运营策略优化。通过大数据分析,轨道交通系统能够不断迭代与优化,以实现更高效、更安全的运营。在应对复杂地理环境和多变外部条件时,组合导航系统凭借其内在工作原理,较少受到遮挡、封闭和强磁干扰等外界环境因素的影响,从而确保在各种环境下都能持续、不间断地提供自主定位与导航服务[7-8]。因此,将全球导航卫星系统与惯性测量单元耦合,同时离散数据与连续数据进行信息融合以提升定位系统的长期精度,是轨道交通导航领域的主要策略[9-10]
组合导航通过信息融合技术对来自不同导航系统的数据进行融合处理,其中卡尔曼滤波及其扩展算法作为重要的最优估计理论,被深度应用于全球定位系统与惯性导航系统信息融合模块[11]。卡尔曼滤波算法递归的方式用各子系统的特性,通过状态预测不断更新对系统状态的估计,动态地调整和补偿误差,提供一个综合、优化的状态估计,包括但不限于载体的位置、速度和姿态信息[12]。然而在实际使用过程中,考虑到随机噪声,载体行驶轨迹可能并不遵循任何运动模型;因此,若GNSS信号长时间失效,由于惯性测量单元数据的高度非线性,基于惯性测量单元的动态误差补偿变得异常困难,卡尔曼滤波可能无法有效抑制惯性导航系统的积分漂移,组合导航误差会急剧累积且在进入纯惯性导航模式之后定位精度会快速下降[13-14]
为了克服上述组合导航的局限性,本文引入结合时间序列分析的深度学习模型。在时序预测领域,可以将预测目标之前时间步作为编码器的输入,将预测目标之后时间步作为解码器的输入,并使用编码器—解码器框架进行预测。特别是,目前研究中编码器—解码器框架复杂多样,但主要采用循环神经网络和注意力机制的思想自适应地对输入数据各部分进行加权,使得模型更加关注高权重信息,同时减少低权值信息的干扰,将输入数据中的每个位置视为一个矢量,其本质是一种序列到序列的模型,使得深度学习模型能够自动学习时间序列数据中的模式和潜在趋势,尤其对于复杂非线性模式深度学习模型有着良好的表达能力。研究人员利用深度学习所具有的误差建模和预测能力,将深度学习的思想广泛应用于控制系统、模糊预测、状态估计以及多模态数据融合等领域中[15-16]。深度学习中的多层神经网络结构能够在多轮学习后,高精度地逼近连续非线性函数,尤其是在凸函数优化的情况下[17-18]。具体来说,惯性导航领域的研究人员用深度学习辅助组合导航的主要策略,是在GNSS信号有效时,将神经网络参数与卡尔曼滤波器输出的状态估计相关联。该策略使得深度学习模型能够在GNSS信号失效期间补充观测值,以优化状态估计,抑制累计误差的发散。为达到最优估计,研究人员使用了循环神经网络、长短时记忆网络、门控循环神经网络、径向基函数神经网络以及时间卷积网络等深度学习模型,并且已在各类场景中进行了实验验证。基于结构层面,辅助组合导航策略将模型视为一种具有自学习优化和记忆机制的组合导航系统位置误差预测器[19]。理论上,滤波器的输出位置误差与神经网络预测算法结合,将深度学习模型视为对卡尔曼滤波器的独立约束[20-22]
本文结合时间序列原理和深度学习模型,为进一步提高GNSS信号缺失状态下的组合导航系统的持续定位能力做了如下工作:1)通过整合概率时间序列注意力机制与组合导航系统,提出基于概率时间序列注意力模型的组合导航系统,赋予组合导航系统自我学习的能力,在GNSS信号确定时,概率时间序列注意力模型能够有效地学习GNSS内部信号传输的潜在状态,用以优化自身模型参数。2)利用基于概率时间序列注意力模型的组合导航系统来建立卡尔曼滤波器与集成导航系统观测值之间的联系。GNSS失锁区域,增加优化后的概率时间序列注意力机制能够预测GNSS位置与速度信息,并与滤波器协同工作,以更新状态信息,避免系统转入纯惯性导航模式,从而抑制误差扩散,提高在GNSS信号缺失情况下的定位精度。
概率时间序列变换器(Probabilistic Time Series Transformer,PTST)是一种基于注意力机制的时序预测算法,主要由生成模型和推理模型两个传播方向构成,以应对多变量时间序列建模问题。PTST基于概率图原理,结合状态空间模型与注意力机制的深度概率方法,模拟概率空间中非马尔可夫动态的潜在趋势,在按层次组织概率空间中多随机变量以增强表达能力的同时避免完全依赖循环神经网络。图1为PTST结构图,其中蓝色箭头表示生成机制,红色箭头表示推理过程。图中生成和推理模型的分离是为了可读性。本模型允许通过注意力机制在时间步之间进行非马尔可夫和非线性相互作用。相比于各类循环神经网络,PTST引入概率图原理使得模型具有概率性、非自回归性,并能够在训练阶段考虑非线性函数的长期不确定性。
在PTST中生成模型旨在学习非线性数据产生的逻辑过程。对于时序数据而言,这意味着模型需要学习到一个能反映数据点之间依赖关系的概率分布,从而生成新的序列或对缺失数据进行插补。具体地,考虑不同时刻多变量输入形式,结合多层感知机进行位置嵌入(Positional Embedding)得到矢量ht,即
式中:MLP()表示结合多层感知机对输入数据进行位置嵌入;Em b edding(t)是位置嵌入编码,对LayerNorm位置矢量进行归一化。
图1左半部为概率时间序列注意力生成模型结构图,生成模型对学习参数wt的优化是训练过程的核心目标。从一个可学习的、独立于输入的初始化参数w0开始,递归地计算输入样本以及当前时间步的位置嵌入矢量ht以更新wt
式中:N表示归一化操作;Attention将生成的上下文投影后,作为键和值,生成新的隐藏状态;Position(t)是一种预定义的正弦位置嵌入,用于在Transformer架构中为每个时间步t提供位置信息;Sample和Softplus分别代表高斯抽样和近似整流操作,每一个wt的随机样本通过一个多层感知器映射到一个序列;则为生成模型的预测目标,因此生成模型对未来分布预测的概率为
如式(5)所示,在每个时间步注意力机制得到的参数,基于概率图原理模拟潜在趋势的自回归分解;用高斯分布参数化条件概率,对先前状态进行推断,同时投射上下文注意力。为避免zt作为纯随机样本无法在时间步中有效地保留模型信息,本文将学习到的潜在趋势封装在隐藏矢量wt中,结合注意力机制,使用隐藏矢量wt表示有助于模型学习长时间依赖。总而言之,生成模型在概率空间中的生成过程比在观测空间中的其他过程更为简洁和高效,因为在观测空间中单一的注意力模型需要在学习过程中反复对高维数据进行编解码操作。
本文推理模型采用变分推断方法旨在学习和估计潜在变量的后验分布,以便能够从观测数据中推断出潜在趋势。具体来说,推理模型(由参数φ表示)的目标是,近似潜在变量zt给定观测序列的后验概率分布pθzT|)。这一过程不仅涉及对潜在状态的估计,还包括对推理模型参数的优化,从而允许推理模型学习如何从观测数据中逆向推断出潜在状态。通过与生成模型共享参数,推理模型能够有效地学习数据中的复杂结构和长期依赖。
图1右半部为概率时间序列注意力推理模型结构图,推理模型首先试图估计观测数据的近似后验分布qφzT|),这是潜在变量zT给定观测序列的变分后验分布。通过这种方式,推理模型可以有效地学习如何从观测数据中推断出潜在状态。推理模型将后验分布分解为自回归的形式,即
这意味着每个时间步的潜在变量zt的后验分布依赖于过去时间步的潜在变量。推理过程更类似于线性动态系统的平滑过程,通过多个自注意力来模拟过去和未来的观测。
式(7)、式(8)汇总了与当前时间步t相关的所有信息的隐藏表示φt。生成模型和推理模型通过单一的随机变分推断共享权重,进行交互训练,共同构成了变分自编码器框架的一部分。通过最小化生成模型和推理模型之间的Kullback-Leibler散度,PTST能够学习到准确预测观测值又能保持潜在状态合理性的参数。具体而言,推理模型帮助计算生成模型的对数似然下界。通过优化对数似然下界,推理模型能够学习到准确预测未来序列值的参数。其中变分界包括重建损失和Kullback-Leibler项。在生成模型生成未来序列值的过程中,推理模型通过近似后验分布,帮助PTST在给定当前观测值的情况下更新潜在状态,从而确保生成的序列符合观测数据的统计特性。总而言之,推理模型的作用在于帮助PTST学习如何从观测数据中逆向推断出潜在状态,从而支持PTST的训练和生成过程。
基于概率时间序列注意力模型的组合导航系统包含两种工作模式,完整的系统示意图如图2所示。当GNSS信号有效时,位置与速度数据和卡尔曼滤波反馈数据仅用于PTST模型的实时训练。当GNSS信号丢失时,系统切换为如图3所示的工作模式,PTST模型输出模拟的GNSS位置与速度数据,同时模型根据卡尔曼滤波反馈数据调整潜在变量。GNSS失锁区间组合导航在进行惯导航迹推算时要依据时间戳计算出载体相对于参考坐标系、坐标轴的空间关系,即载体的姿态,从而将加速度计比力测量值投影于参考坐标下,再对其参考系下的比力投影分量进行积分运算,解得载体的速度和位置[23-24]。最后,由PTST输出预测的位置和速度数据后,利用卡尔曼滤波器更新状态估计。
为深入挖掘GNSS原始观测数据的隐藏特征,PTST首先通过生成模型对载体位置、速度和姿态进行特征提取。
其中,PG表示GNSS输出的位置与速度数据。式(9)类似式(1),表示特征提取方法的统一,以便于式(10)注意力机制的查询操作。
在组合导航模式中,将惯性导航推算位置与GNSS解算位置之差作为观测矢量,考虑解算过程与观测过程的误差扰动,得到位置和速度观测方程。
式(11)中,为惯导在n系下的位置,旋转矩阵为载体姿态,为GNSS在n系下的位置,为GNSS中心相对于IMU中心的杆臂值。式(12)中,为惯导在n系下的速度,为GNSS在n系下的速度,为地球系相对于惯性系的角速度在导航系下的表示。式(13)中,Ht为观测矩阵,Xtt|tt为状态矩阵,由式(11)、式(12)计算结果和各零偏矢量、误差矢量构成。
根据上述递推结果,可得状态估计矢量,接下来将描述如何将基于概率时间序列注意力模型融入到组合导航系统框架中。
1)初始化:设置初始状态估计值和PTST模型参数。PTST预训练阶段旨在学习惯性传感器误差的动态特性,特别是GNSS信号中断期间组合导航系统的行为模式。
2)预测阶段:当组合导航系统处于图3所示的GNSS失锁区间时,无法通过式(11)、式(12)计算导航结果。此时,基于卡尔曼滤波更新状态和协方差矩阵。利用PTST模型,基于历史数据,预测当前时刻的惯性传感器误差,PTST模型作为一种新息矢量的外部输入,以弥补GNSS缺失数据,如式(14)所示。这一步骤旨在利用PTST的生成模型,捕捉长时间序列数据中的时间依赖性,从而在GNSS中断期间提供更为准确的误差预测。
3)更新阶段:当GNSS信号可用时,通过卡尔曼滤波,结合PTST模型,更新步骤来校正状态估计。在量测更新过程中首先计算增益矩阵Kt,然后更新系统状态X及误差协方差阵Pt|t-1。当Rt为正定阵时,Xt的最优估值可按下述方程求解
式(14)~式(18)为PTST结合离散型卡尔曼滤波的基本方程,只要给定初值X0P0,根据t时刻的量测值,即可递推计算任意时刻的状态估计。其中:Pt|t-1有多种等价的表达式,式(14)被称为Joseph形式,由于能够保证对称性和正定性,在工程中应用最为广泛;PPTST表示由式(5)输出预测的位置为上一时刻卡尔曼滤波输出位置;Zt为式(8)所得上一时刻时间步的潜在变量;Φ为状态转移矩阵。
虽然很多物理系统是连续系统,但只要合理离散化就能使用离散型卡尔曼滤波的基本方程。因此,在GNSS信号中断期间,可以利用PTST预测值作为虚拟观测数据,直接通过卡尔曼滤波进行状态更新以维持滤波器的自学习和连续更新能力,避免系统陷入纯惯性导航模式。重复上述预测和更新步骤,直到GNSS信号恢复进入卡尔曼滤波结合PTST模型更新状态模式。
通过上述步骤,组合导航系统不仅利用了卡尔曼滤波运行时在调整模型参数和噪声统计特性方面的自适应优势,还借助时间序列神经网络强大的非线性数据处理能力,显著提高了在GNSS信号丢失环境下导航系统的稳定性和精度。
为验证算法的有效性,本文结合高速轨道交通运行特点,设计了INS/GNSS组合定位地面实验,实验所采用的参数如表1所示。
现场实验路线图如图4所示,红色轨迹段列车GNSS信号正常,在进行卡尔曼滤波器更新状态估计的同时,利用GNSS输出数据对PTST模型进行在线训练。在黄色隧道区域期间,GNSS信号丢失导致组合导航系统长时间失锁,定位模型自动转换为PTST模型预测模式,此时系统输出惯性测量单元的导航参数与经过PTST生成模型校正后的导航参数。蓝色山脉遮挡区域,GNSS信号频繁短时丢失,组合导航系统在两种模式下频繁切换造成定位抖动漂移现象。
本文将差分整合移动平均自回归(Autoregressive Integrated Moving Average,ARIMA)模型、长短期记忆(Long Short Term Memory,LSTM)网络和深度时序卷积网络(Deep Temporal Convolutional Network,Deep-TCN)[17]作为基线算法,基于现场数据进行预测对比实验,实验误差结果对比如表2所示。实验数据重点考察在隧道和遮挡区域的GNSS信号中断时段,不同算法模式对列车定位的影响。对比预测结果表明,在信号中断时段,相比于最优基线算法,PTST下组合导航系统的各轴向位置误差显著降低,隧道段减少了42%~53%,遮挡段减少了29%~47%。因此当组合导航系统缺乏外部观测修正时,PTST可以改善列车定位精度。
图5为现场实验中各轴向位置误差分析图。在隧道区域内,由于信号遮挡导致的定位误差,在后续行驶过程中引发了在三维空间上的轨迹漂移。具体而言,在隧道的起始阶段,轨迹偏移相对较小且可控制,偏差大约维持在±5m之内;进入隧道中段后,轨迹偏移逐渐增加,并在XZ两个坐标轴方向达到了约±14m的最大偏差;而在隧道的末端部分,随着全球导航卫星系统信号的恢复,定位误差经历了一定程度的突变后趋于稳定。
相比之下,山脉遮挡区域虽然也存在GNSS信号的频繁丢失,但每次丢失的时间较短,因此,尽管轨迹出现了某种程度的波动,但总体的定位误差仍然有限,平均误差大约为±5m,最大误差不超过±10m。这种轨迹波动可能是由基于概率时间序列注意力模型的组合导航系统中PTST学习模式与预测模型之间的频繁切换所引起的。
然而,通过PTST模型进行预测并加以校正之后,组合导航系统的定位结果展现出了对于GNSS信号丢失情况下的强鲁棒性。定位误差主要集中在X轴和Z轴方向上,而沿Y轴(水平坐标轴)方向上的偏移则相对稳定,在各个坐标轴方向上平均定位误差均保持在10m以下,且定位轨迹表现出较高的平滑度,没有出现明显的轨迹估计发散现象。综上所述,多类复杂场景下列车的平均定位精度在±10m以内可确保列车在轨道上的位置能够精确到达各个站点,并保持与其他列车的安全间距。因此,本文所提出的基于概率时间序列注意力模型的组合导航系统不仅提供更高精度的定位状态估计,且兼顾了复杂环境自适应性能。
本文提出了一种基于概率时间序列注意力模型的组合导航系统,用于增强GNSS/INS组合导航在GNSS受限环境下的导航精度。基于概率时间序列注意力模型的组合导航系统包含两类导航模式,它们都以紧耦合的方式工作。本文通过引入具备推理和生成能力的概率时间序列注意力模型,赋予组合导航系统自我学习的能力,在GNSS信号确定时,概率时间序列注意力模型能够有效地学习优化GNSS内部信号传输的潜在状态及其模型参数。在GNSS失锁区域,基于优化后的PTST模型能够预测GNSS位置与速度信息并与滤波器协同工作,以更新状态信息,避免系统转入纯惯性导航模式,从而抑制误差扩散,提高在GNSS信号缺失情况下的定位精度。
然而,本文所采用的概率时间序列注意力模型仍存在一定的局限性。尽管PTST模型具有良好的长期学习和推理能力,但PTST模型对于不同GNSS信号缺失状态的泛化能力需要进一步增强,主要表现在面对GNSS信号多次短时间内的丢失情况,其抗干扰能力尚待改进。
总而言之,本文所提出的基于概率时间序列注意力模型的组合导航系统,与轨道交通领域的其他定位与测速方法相比较,具有非接触式的动态实时测量、易于实施以及建设和维护成本较低等显著优势,即使大规模部署也不会增加额外的轨旁设施建设需求。尽管目前轨道交通定位领域已有多样化的定位与测速方法,但仍需开展更深入广泛的研究,以进一步提高系统的精度与鲁棒性。未来的研究重点应聚焦于实现车载设备间的时空信息的实时获取与交互,并以工程应用为目标,持续探索各种技术路径的综合应用与实验验证。
参考文献 引证文献
排序方式:
[1]
刘丰宇,程向红,李艺恒,.基于惯性/仿生视觉/激光雷达的智能感知无人系统[J].飞控与探测,2024, 7(3):22-30.
LIU F Y,CHENG X H,LI Y H,et al.INS/bionic vision/LiDAR based intelligent perception unmanned system[J].Flight Control & Detection,2024,7(3):22-30(in Chinese).
[2]
QIN T,PAN J,CAO S,et al.A general optimization-based framework for global pose estimation with multiple sensors[J/OL].arXiv:1901.03642.https://doi.org/10.48550/arXiv.1901.03642
[3]
QIN T,LI P,SHEN S,et al.VINS-Mono:a robust and versatile monocular visual-inertial state estimator[J].IEEE Transactions on Robotics,2018,34(4):1004-1020.
[4]
夏鸿,何泉,蒲磊,.神经网络提升低成本软件定义的无线电无人机探测平台定位准确率研究[J].成都大学学报(自然科学版),2023,42(3):262-267,282.
XIA H,HE Q,PU L,et al.Research on using neural network to improve accuracy of radio platform for UAV detection defined by low-cost software[J]. Journal of Chengdu University (Natural Science Edition),2023,42(3):262-267,282(in Chinese).
[5]
朱明红.基于低成本IMU的通用多传感器集成动态定位关键技术研究[D].哈尔滨:哈尔滨工程大学,2021.
ZHU M H.Research on key technologies of generic multi-sensor integrated kinematic positioning based on low-cost IMU[D].Harbin:Harbin Engineering University,2021 (in Chinese).
[6]
房博乐,梁永,楼梁伟.北斗-INS普速铁路精测精捣方法及应用[J].测绘通报,2024(7):147-151.
FANG B L,LIANG Y,LOU L W.Beidou-INS precision measurement and tamping method for ordinary speed railway[J].Bulletin of Surveying and Mapping, 2024(7):147-151(in Chinese).
[7]
陈熙源,周云川,钟雨露,.基于变分贝叶斯的鲁棒自适应因子图优化组合导航算法[J].仪器仪表学报,2024,45(1):120-129.
CHEN X Y,ZHOU Y C,ZHONG Y L,et al.Robust adaptive factor graph optimization integrated navigation algorithm based on variational Bayesian[J].Chinese Journal of Scientific Instrument,2024,45(1):120-129(in Chinese).
[8]
傅金琳,王毅,阎磊.卫导受限下惯导/数据链/卫导紧组合导航方法[J].舰船科学技术,2024,46(13):141-145.
FU J L,WANG Y,YAN L.INS/DL/GNSS tightly coupled integrated navigation method under GNSS restricted conditions[J].Ship Science and Technology, 2024,46(13):141-145(in Chinese).
[9]
郭驿众,李根,许佳斌,.基于ArUco码的无地图AMR视觉辅助归航方法[J].飞控与探测,2023,6(3):95-102.
GUO Y Z,LI G,XU J B,et al.An ArUco marker-based homing method for visual-aid AMR without map building[J].Flight Control & Detection,2023, 6(3):95-102(in Chinese).
[10]
张雷,沈国琛,秦晓洁,.智能网联交通系统中的信息物理映射与系统构建[J].同济大学学报(自然科学版),2022,50(1):79-86.
ZHANG L,SHEN G C,QIN X J,et al.Informationphysical mapping and system construction of intelligent network transportation[J].Journal of Tongji University (Natural Science),2022,50(1):79-86(in Chinese).
[11]
林雪原,孙炜玮.基于指数加权平均的GNSS/SINS组合导航系统Sage-Husa自适应卡尔曼滤波算法[J/OL].大地测量与地球动力学,https://doi.org/10.
LIN X Y,SUN W W.Sage-Husa adaptive Kalman filtering algorithm for GNSS/SINS integrated navigation system based on exponential weighted average[J/OL].Journal of Geodesy and Geodynamics,https://doi.org/10.14075/j.jgg.2024.02.068(in Chinese).
[12]
魏文辉,袁伟,张逸凡.智能汽车SINS/GNSS动态组合导航观测模型系统误差自适应估计方法[J].中国公路学报,2024,37(7):280-290.
WEI W H,YUAN W,ZHANG Y F.Adaptive estimation method of observational model systematic errors for intelligent vehicle SINS/GNSS dynamic integrated navigation[J].China Journal of Highway and Transport,2024,37(7):280-290(in Chinese).
[13]
蔡灿烽,许智理,申志恒,.基于冗余GNSS观测的RTK/INS紧组合方法[J].导航定位与授时,2024,11(6):113-122.
CAI C F,XU Z L,SHEN Z H,et al.The tightly coupled RTK/INS integration method based on re dundant GNSS measurement[J].Navigation Positioning and Timing,2024,11(6):113-122(in Chinese).
[14]
侯华,程萌,黄鼎盛,.基于VB-EKF的GPS/INS松组合导航定位算法[J].计算机应用与软件,2024, 41(6):282-286.
HOU H,CHENG M,HUANG D S,et al.GPS/INS loose integrated navigation and positioning algorithm based on VB-EKF[J].Computer Applications and Software,2024,41(6):282-286(in Chinese).
[15]
张艳,王宇.基于视觉里程计的室内位姿测量技术研究[J].电子测量与仪器学报,2022,36(6):73-81.
ZHANG Y,WANG Y.Design and implementation method of a visual odometer[J].Journal of Electronic Measurement and Instrumentation,2022,36(6):73-81(in Chinese).
[16]
LAI G,CHANG W C,YANG Y,et al.Modeling long-and short-term temporal patterns with deep neural networks[C]//The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval.Ann Arbor,MI,USA:Association for Computing Machinery.2018:95-104.
[17]
CHEN Y,KANG Y,CHEN Y,et al.Probabilistic forecasting with temporal convolutional neural network[J].Neurocomputing,2020,399:491-501.
[18]
LIU S,YU H,LIAO C,et al.Pyraformer:low-complexity pyramidal attention for long-range time series modeling and forecasting[C]//International Conference on Learning Representations,International Machine Learning Society,2022.
[19]
LIM B,ARIK S Ö,LOEFF N,et al.Temporal fusion transformers for interpretable multi-horizon time series forecasting[J].International Journal of Forecasting, 2021,37(4):1748-1764.
[20]
匡兴红,黄傲威.一种基于深度学习辅助的SINS/DVL组合导航方法[J].系统仿真学报,2024,36(8):1810-1822.
KUANG X H,HUANG A W.A method based on deep learning for assisting SINS/DVL integrated navigation[J].Journal of System Simulation,2024,36(8):1810-1822(in Chinese).
[21]
XU Q,ZHANG L,YU W.A localization method of ant colony optimization in nonuniform space[J].Sensors,2022,22(19):7389.
[22]
储诚涛,吴峻.神经网络在SINS/GPS组合定位中的应用[J].全球定位系统,2021,46(2):104-110.
CHU C T,WU J.Application of neural network in SINS/GPS combined positioning[J].GNSS World of China,2021,46(2):104-110(in Chinese).
[23]
SHEN C,ZHANG Y,GUO X,et al.Seamless GPS/inertial navigation system based on self-learning square-root cubature Kalman filter[J].IEEE Transactions on Industrial Electronics,2021,68(1):499-508.
[24]
TANG B,MATTESON D S.Probabilistic transformer for time series analysis[J].Advances in Neural Information Processing Systems,2021,34:23592-23608.
2025年第8卷第5期
PDF下载
108
48
引用本文
BibTeX
文章信息
doi: 10.20249/j.cnki.2096-5974.2025.05.001
  • 首发时间:2026-04-23
补充材料
相关文章
文章信息
作者
出版历史
基金
作者信息
    1同济大学 上海自主智能无人系统科学中心·上海·201210
    2同济大学 道路与交通工程教育部重点实验室·上海·201804
    3上海航天控制技术研究所·上海·201109
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/fkytc/CN/10.20249/j.cnki.2096-5974.2025.05.001
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