Article(id=1251893508177609139, tenantId=1146029695717560320, journalId=1251234473337991274, issueId=1251893504037831074, articleNumber=null, orderNo=null, doi=10.3969/j.issn.1003-3114.2025.05.021, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1742832000000, receivedDateStr=2025-03-25, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1776404271406, onlineDateStr=2026-04-17, pubDate=1758124800000, pubDateStr=2025-09-18, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1776404271406, onlineIssueDateStr=2026-04-17, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1776404271406, creator=13701087609, updateTime=1776404271406, updator=13701087609, issue=Issue{id=1251893504037831074, tenantId=1146029695717560320, journalId=1251234473337991274, year='2025', volume='51', issue='5', pageStart='877', pageEnd='1134', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=1, specialIssue=null, createTime=1776404270419, creator=13701087609, updateTime=1776404832543, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1251895861849043019, tenantId=1146029695717560320, journalId=1251234473337991274, issueId=1251893504037831074, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1251895861849043020, tenantId=1146029695717560320, journalId=1251234473337991274, issueId=1251893504037831074, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=1080, endPage=1086, ext={EN=ArticleExt(id=1251893508970332600, articleId=1251893508177609139, tenantId=1146029695717560320, journalId=1251234473337991274, language=EN, title=Transformer Network-assisted Fusion of Satellite and Inertial Navigation Technologies, columnId=1251893508886446519, journalTitle=Radio Communications Technology, columnName=Special Topic:Frontiers in Intelligent Communication, Storage, and Information Processing Technologies, runingTitle=null, highlight=null, articleAbstract=

When a carrier (such as drones, ships, and vehicles) moves in extreme environments, the visibility of satellites may be lost, leading to a temporary or prolonged loss of lock on Global Navigation Satellite System (GNSS) signals. In such scenarios, an integrated navigation system is forced to switch to a pure Inertial Navigation System (INS). However, prolonged reliance on inertial navigation alone results in the accumulation of errors and a rapid decline in navigation accuracy. To address the rapid decline in INS accuracy after GNSS signal loss, a fusion navigation technology of GNSS and INS assisted by Transformer networks is proposed. When the GNSS signal is locked, the Transformer network utilizes current INS information and GNSS incremental data (the change in GNSS position information between two adjacent time periods) to train a mapping relationship between the two. When the GNSS signal is lost, the Transformer network leverages the previously established mapping relationship to predict GNSS incremental information based on the current INS data, and then integrates the INS information with the predicted GNSS data for navigation. Simulation results demonstrate that the Transformer network-assisted GNSS/INS fusion navigation technology can provide stable and reliable navigation signals even under conditions of temporary or prolonged GNSS signal loss. Furthermore, the Transformer network-assisted fusion navigation method offers a reference for other network-assisted fusion implementations.

, 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=Siyuan WU, Dahua ZUO, Ming JIANG), CN=ArticleExt(id=1251893526083093387, articleId=1251893508177609139, tenantId=1146029695717560320, journalId=1251234473337991274, language=CN, title=Transformer网络辅助的融合卫星与惯性导航技术, columnId=1251893509079384505, journalTitle=无线电通信技术, columnName=专题:智能通信、存储与信息处理技术前沿, runingTitle=null, highlight=null, articleAbstract=

当载体(如无人机、船只和车辆等)在极端环境下运动时,可能会出现可见卫星消失的情况,这会导致全球卫星导航系统(Global Navigation Satellite System,GNSS)信号出现短暂或长时间的丢失(失锁)。在这种情况下,融合导航将被迫切换到纯惯性导航系统(Inertial Navigation System,INS),纯惯性导航运行时间的增加会导致误差不断累积,导航精度快速下降。为解决GNSS信号丢失后INS精度快速下降的问题,提出基于变换器(Transformer)网络辅助的GNSS与INS融合导航技术。当GNSS信号锁定时,Transformer网络利用当前的INS信息和GNSS增量信息(2个相邻时刻GNSS位置信息的变化量)来训练出二者的映射关系;当GNSS信号失锁时,Transformer网络利用之前训练出的映射关系,由当前的INS信息预测GNSS增量信息,并将INS信息和预测的GNSS信息进行融合导航。仿真结果表明,基于Transformer网络辅助的GNSS与INS融合导航技术,在GNSS信号短暂或一定时间内失锁的条件下,仍然可以提供稳定可靠的导航信号。此外,Transformer网络辅助的融合导航方法为其他网络辅助的融合提供了参考。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=xx2A4G3OVq/WJh9uEF4Gjg==, magXml=7kFbU228Jg7ghbRW1wG6iQ==, pdfUrl=null, pdf=+4MY56/1XCrxzMg8aM4wDw==, pdfFileSize=4175690, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=rbDlR538Jd+vWKmYheSHSw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=JUMOBuHDtC9urKme/i99Yg==, mapNumber=null, authorCompany=null, fund=null, authors=

吴思远 男,(1999—),硕士研究生。主要研究方向:5G移动通信。

左大华 男,(1988—),硕士,高级工程师。主要研究方向:水上移动通信、船舶自动控制等。

姜明 男,(1976—),博士,副教授。主要研究方向:移动通信系统中物理层/应用层纠错码编解码技术、迭代接收算法、基于人工智能的通信技术。

, authorsList=吴思远, 左大华, 姜明)}, authors=[Author(id=1251895531337892528, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, 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=1251895531434361527, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, authorId=1251895531337892528, language=EN, stringName=Siyuan WU, firstName=Siyuan, middleName=null, lastName=WU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Information Science and Engineering, Southeast University, Nanjing 214135, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251895531539219135, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, authorId=1251895531337892528, language=CN, stringName=吴思远, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.东南大学 信息科学与工程学院,江苏 南京 214135, bio={"content":"

吴思远 男,(1999—),硕士研究生。主要研究方向:5G移动通信。

"}, bioImg=null, bioContent=

吴思远 男,(1999—),硕士研究生。主要研究方向:5G移动通信。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251895531086234268, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, xref=1., ext=[AuthorCompanyExt(id=1251895531119788702, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, companyId=1251895531086234268, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Information Science and Engineering, Southeast University, Nanjing 214135, China), AuthorCompanyExt(id=1251895531136565920, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, companyId=1251895531086234268, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.东南大学 信息科学与工程学院,江苏 南京 214135)])]), Author(id=1251895531660853958, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, 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=1251895531816043212, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, authorId=1251895531660853958, language=EN, stringName=Dahua ZUO, firstName=Dahua, middleName=null, lastName=ZUO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Nanjing Sandemarine Information Technology Co. , Ltd. , Nanjing 210031, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251895531967038163, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, authorId=1251895531660853958, language=CN, stringName=左大华, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.南京海善达信息科技有限公司,江苏 南京 210031, bio={"content":"

左大华 男,(1988—),硕士,高级工程师。主要研究方向:水上移动通信、船舶自动控制等。

"}, bioImg=null, bioContent=

左大华 男,(1988—),硕士,高级工程师。主要研究方向:水上移动通信、船舶自动控制等。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251895531224646310, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, xref=2., ext=[AuthorCompanyExt(id=1251895531237229223, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, companyId=1251895531224646310, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Nanjing Sandemarine Information Technology Co. , Ltd. , Nanjing 210031, China), AuthorCompanyExt(id=1251895531245617832, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, companyId=1251895531224646310, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.南京海善达信息科技有限公司,江苏 南京 210031)])]), Author(id=1251895532050924248, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, 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=1251895532134810336, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, authorId=1251895532050924248, language=EN, stringName=Ming JIANG, firstName=Ming, middleName=null, lastName=JIANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Information Science and Engineering, Southeast University, Nanjing 214135, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251895533716062950, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, authorId=1251895532050924248, language=CN, stringName=姜明, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.东南大学 信息科学与工程学院,江苏 南京 214135, bio={"content":"

姜明 男,(1976—),博士,副教授。主要研究方向:移动通信系统中物理层/应用层纠错码编解码技术、迭代接收算法、基于人工智能的通信技术。

"}, bioImg=null, bioContent=

姜明 男,(1976—),博士,副教授。主要研究方向:移动通信系统中物理层/应用层纠错码编解码技术、迭代接收算法、基于人工智能的通信技术。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251895531086234268, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, xref=1., ext=[AuthorCompanyExt(id=1251895531119788702, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, companyId=1251895531086234268, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Information Science and Engineering, Southeast University, Nanjing 214135, China), AuthorCompanyExt(id=1251895531136565920, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, companyId=1251895531086234268, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.东南大学 信息科学与工程学院,江苏 南京 214135)])])], keywords=[Keyword(id=1251895533938361076, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, language=EN, orderNo=1, keyword=INS), Keyword(id=1251895534101938937, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, language=EN, orderNo=2, keyword=GNSS), Keyword(id=1251895534215185155, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, language=EN, orderNo=3, keyword=integrated navigation), Keyword(id=1251895534299071240, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, language=EN, orderNo=4, keyword=loss of lock), Keyword(id=1251895534382957325, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, language=EN, orderNo=5, keyword=Transformer neural network), Keyword(id=1251895534458454802, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, language=CN, orderNo=1, keyword=惯性导航系统), Keyword(id=1251895534542340887, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, language=CN, orderNo=2, keyword=全球卫星导航系统), Keyword(id=1251895534630421273, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, language=CN, orderNo=3, keyword=融合导航), Keyword(id=1251895534710113055, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, language=CN, orderNo=4, keyword=失锁), Keyword(id=1251895534806582052, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, language=CN, orderNo=5, keyword=变换器神经网络)], refs=[Reference(id=1251895536232645494, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, doi=null, pmid=null, pmcid=null, year=2025, volume=15, issue=1, pageStart=44, pageEnd=48, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=孙淑光, 徐延枝, 王浩琳, journalName=物联网技术, refType=null, unstructuredReference=孙淑光,徐延枝,王浩琳.卫星拒止环境下无人机INS/GNSS紧组合定位算法研究[J].物联网技术,2025,15(1):44-48., articleTitle=卫星拒止环境下无人机INS/GNSS紧组合定位算法研究, refAbstract=null), Reference(id=1251895536320725884, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, doi=null, pmid=null, pmcid=null, year=2024, volume=32, issue=4, pageStart=354, pageEnd=362, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=武文博, 吕志伟, 周玟龙, journalName=中国惯性技术学报, refType=null, unstructuredReference=武文博,吕志伟,周玟龙,.基于组合历元新息抗差的GNSS/INS欺骗检测方法[J].中国惯性技术学报, 2024,32(4):354-362., articleTitle=基于组合历元新息抗差的GNSS/INS欺骗检测方法, refAbstract=null), Reference(id=1251895536396223362, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=11, pageStart=78, pageEnd=82, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=周涛, 邹进贵, 赵胤植, journalName=测绘通报, refType=null, unstructuredReference=周涛,邹进贵,赵胤植,.附加UWB约束的GNSS/INS组合导航算法[J].测绘通报,2024(11):78-82., articleTitle=附加UWB约束的GNSS/INS组合导航算法, refAbstract=null), Reference(id=1251895536563995529, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, doi=null, pmid=null, pmcid=null, year=2024, volume=41, issue=5, pageStart=54, pageEnd=61, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=王尔申, 刘依凡, 于腾丽, journalName=沈阳航空航天大学学报, refType=null, unstructuredReference=王尔申,刘依凡,于腾丽,.基于全连接神经网络的GNSS/INS组合定位方法[J].沈阳航空航天大学学报,2024,41(5):54-61., articleTitle=基于全连接神经网络的GNSS/INS组合定位方法, refAbstract=null), Reference(id=1251895536656270221, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, doi=null, pmid=null, pmcid=null, year=2024, volume=42, issue=3, pageStart=64, pageEnd=69, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=闫文林, 严泰明, 潘兴驰, journalName=江苏师范大学学报(自然科学版), refType=null, unstructuredReference=闫文林,严泰明,潘兴驰,.GNSS/INS松、紧组合导航算法的等价性条件[J].江苏师范大学学报(自然科学版),2024,42(3):64-69., articleTitle=GNSS/INS松、紧组合导航算法的等价性条件, refAbstract=null), Reference(id=1251895538220745622, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, doi=null, pmid=null, pmcid=null, year=2025-03-21, volume=null, issue=null, pageStart=1, pageEnd=9, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=王艳红, 赵亮, 王官军, journalName=计算机工程与应用, refType=null, unstructuredReference=王艳红,赵亮,王官军.改进Transformer模型的语音识别轻量化设计[J/OL].计算机工程与应用1-9[2025-03-21]. https://link.cnki.net/urlid/11.2127.TP.20241231.1449.014., articleTitle=改进Transformer模型的语音识别轻量化设计, refAbstract=null), Reference(id=1251895538329797533, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, doi=null, pmid=null, pmcid=null, year=2025, volume=53, issue=2, pageStart=545, pageEnd=557, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=金峥, 贾克斌, journalName=电子学报, refType=null, unstructuredReference=金峥,贾克斌.一种基于Transformer架构的多层级自动睡眠分期模型[J].电子学报,2025,53(2):545-557., articleTitle=一种基于Transformer架构的多层级自动睡眠分期模型, refAbstract=null), Reference(id=1251895538430460831, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, doi=null, pmid=null, pmcid=null, year=2024, volume=41, issue=6, pageStart=1195, pageEnd=1203, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=潘丹, 骆根强, 曾安, journalName=生物医学工程学杂志, refType=null, unstructuredReference=潘丹,骆根强,曾安.基于Transformer和卷积神经网络双并行分支编码器神经网络的冠状动脉分割[J].生物医学工程学杂志,2024,41(6):1195-1203., articleTitle=基于Transformer和卷积神经网络双并行分支编码器神经网络的冠状动脉分割, refAbstract=null), Reference(id=1251895538505958309, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, doi=null, pmid=null, pmcid=null, year=2024, volume=41, issue=12, pageStart=1550, pageEnd=1557, url=null, language=null, rfNumber=[9], rfOrder=8, authorNames=王安琪, 于超, 陈胤玮, journalName=中国医学物理学杂志, refType=null, unstructuredReference=王安琪,于超,陈胤玮,.基于LSTM-Transformer的脑电情感分析[J].中国医学物理学杂志,2024,41(12):1550-1557., articleTitle=基于LSTM-Transformer的脑电情感分析, refAbstract=null), Reference(id=1251895538594038700, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, doi=null, pmid=null, pmcid=null, year=2024, volume=8, issue=9, pageStart=184, pageEnd=187, url=null, language=null, rfNumber=[10], rfOrder=9, authorNames=孙洪驰, 杨轩, 龙腾, journalName=电子元器件与信息技术, refType=null, unstructuredReference=孙洪驰,杨轩,龙腾,.随机多步时延背景下GNSS/低轨/INS多源导航系统联邦滤波方法[J].电子元器件与信息技术,2024,8(9):184-187., articleTitle=随机多步时延背景下GNSS/低轨/INS多源导航系统联邦滤波方法, refAbstract=null), Reference(id=1251895538690507698, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=增刊2, pageStart=263, pageEnd=266, url=null, language=null, rfNumber=[11], rfOrder=10, authorNames=周佩旻, 马下平, journalName=测绘通报, refType=null, unstructuredReference=周佩旻,马下平.不同场景下GNSS与INS组合定位性能评估[J].测绘通报,2024(增刊2):263-266., articleTitle=不同场景下GNSS与INS组合定位性能评估, refAbstract=null), Reference(id=1251895538770199478, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, doi=null, pmid=null, pmcid=null, year=2024, volume=40, issue=4, pageStart=348, pageEnd=354, url=null, language=null, rfNumber=[12], rfOrder=11, authorNames=吴庆, 刘长建, 肖国锐, journalName=测绘科学技术学报, refType=null, unstructuredReference=吴庆,刘长建,肖国锐,.不同情形下GNSS/INS组合导航系统精度分析[J].测绘科学技术学报,2024,40(4):348-354., articleTitle=不同情形下GNSS/INS组合导航系统精度分析, refAbstract=null), Reference(id=1251895538887639996, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, doi=null, pmid=null, pmcid=null, year=2024, volume=12, issue=4, pageStart=123, pageEnd=131, url=null, language=null, rfNumber=[13], rfOrder=12, authorNames=骆元鹏, 程正逢, 易祎, journalName=导航定位学报, refType=null, unstructuredReference=骆元鹏,程正逢,易祎,.一种GNSS/INS紧组合状态域多故障渐消方法[J].导航定位学报,2024,12(4):123-131., articleTitle=一种GNSS/INS紧组合状态域多故障渐消方法, refAbstract=null), Reference(id=1251895538975720383, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=13, authorNames=刘静, journalName=基于GNSS/INS/Visual组合的自主定位定向算法研究, refType=null, unstructuredReference=刘静.基于GNSS/INS/Visual组合的自主定位定向算法研究[D].西安:西安理工大学,2024., articleTitle=null, refAbstract=null), Reference(id=1251895539042829251, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=14, authorNames=褚雨欣, journalName=基于图优化的共时钟多天线单差GNSS/INS组合测姿算法研究, refType=null, unstructuredReference=褚雨欣.基于图优化的共时钟多天线单差GNSS/INS组合测姿算法研究[D].上海:华东师范大学,2024., articleTitle=null, refAbstract=null), Reference(id=1251895539164464071, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=15, authorNames=李忱汉, journalName=复杂场景GNSS/INS数据融合定位算法研究, refType=null, unstructuredReference=李忱汉.复杂场景GNSS/INS数据融合定位算法研究[D].北京:中国测绘科学研究院,2024., articleTitle=null, refAbstract=null), Reference(id=1251895539290293198, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, doi=null, pmid=null, pmcid=null, year=2025, volume=26, issue=1, pageStart=115, pageEnd=124, url=null, language=null, rfNumber=[17], rfOrder=16, authorNames=王高峰, 张卓石, 高蔓, journalName=北华大学学报(自然科学版), refType=null, unstructuredReference=王高峰,张卓石,高蔓,.基于多特征融合卷积神经网络结合Transformer的电能质量扰动分类方法[J].北华大学学报(自然科学版),2025,26(1):115-124., articleTitle=基于多特征融合卷积神经网络结合Transformer的电能质量扰动分类方法, refAbstract=null), Reference(id=1251895539382567891, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=17, authorNames=陶毅峰, journalName=GRU循环神经网络辅助的GNSS/INS组合导航算法研究, refType=null, unstructuredReference=陶毅峰. GRU循环神经网络辅助的GNSS/INS组合导航算法研究[D].武汉:武汉大学,2021., articleTitle=null, refAbstract=null), Reference(id=1251895539462259671, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=2, pageStart=370, pageEnd=376, url=null, language=null, rfNumber=[19], rfOrder=18, authorNames=陶毅峰, 江金光, 方伟, journalName=计算机工程与设计, refType=null, unstructuredReference=陶毅峰,江金光,方伟.基于GRU循环神经网络辅助的组合导航算法[J].计算机工程与设计,2021,42(2):370-376., articleTitle=基于GRU循环神经网络辅助的组合导航算法, refAbstract=null), Reference(id=1251895539546145754, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, doi=null, pmid=null, pmcid=null, year=2024, volume=29, issue=2, pageStart=11, pageEnd=19, url=null, language=null, rfNumber=[20], rfOrder=19, authorNames=黄庆东, 王皓, 郭振, journalName=西安邮电大学学报, refType=null, unstructuredReference=黄庆东,王皓,郭振,.基于注意力机制的GRU神经网络辅助INS/GNSS组合导航算法[J].西安邮电大学学报,2024,29(2):11-19., articleTitle=基于注意力机制的GRU神经网络辅助INS/GNSS组合导航算法, refAbstract=null), Reference(id=1251895539634226149, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, doi=null, pmid=null, pmcid=null, year=2024, volume=43, issue=6, pageStart=24, pageEnd=33, url=null, language=null, rfNumber=[21], rfOrder=20, authorNames=柳絮, 王坚, 肖星星, journalName=山东科技大学学报(自然科学版), refType=null, unstructuredReference=柳絮,王坚,肖星星,. GNSS失锁下Tent-ASO-BP辅助GNSS/INS松组合导航算法[J].山东科技大学学报(自然科学版),2024,43(6):24-33., articleTitle=GNSS失锁下Tent-ASO-BP辅助GNSS/INS松组合导航算法, refAbstract=null), Reference(id=1251895539705529322, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, doi=null, pmid=null, pmcid=null, year=2024, volume=23, issue=5/6, pageStart=163, pageEnd=173, url=null, language=null, rfNumber=[22], rfOrder=21, authorNames=王家鑫, 周艳玲, 庞茹, journalName=导航与控制, refType=null, unstructuredReference=王家鑫,周艳玲,庞茹. GNSS拒止下GRU神经网络INS/GNSS融合导航研究[J].导航与控制,2024,23(5/6):163-173., articleTitle=GNSS拒止下GRU神经网络INS/GNSS融合导航研究, refAbstract=null), Reference(id=1251895539818775540, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, doi=null, pmid=null, pmcid=null, year=2015, volume=17, issue=2, pageStart=110, pageEnd=120, url=null, language=null, rfNumber=[23], rfOrder=22, authorNames=GONZALEZ R, GIRIBET J I, PATIO H D, journalName=Control Engineering and Applied Informatics, refType=null, unstructuredReference=GONZALEZ R, GIRIBET J I, PATIO H D. Navego: A Simulation Framework for Low-cost Integrated Navigation Systems[J]. Control Engineering and Applied Informatics,2015,17(2):110-120., articleTitle=Navego: A Simulation Framework for Low-cost Integrated Navigation Systems, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1251895531086234268, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, xref=1., ext=[AuthorCompanyExt(id=1251895531119788702, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, companyId=1251895531086234268, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Information Science and Engineering, Southeast University, Nanjing 214135, China), AuthorCompanyExt(id=1251895531136565920, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, companyId=1251895531086234268, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.东南大学 信息科学与工程学院,江苏 南京 214135)]), AuthorCompany(id=1251895531224646310, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, xref=2., ext=[AuthorCompanyExt(id=1251895531237229223, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, companyId=1251895531224646310, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Nanjing Sandemarine Information Technology Co. , Ltd. , Nanjing 210031, China), AuthorCompanyExt(id=1251895531245617832, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, companyId=1251895531224646310, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.南京海善达信息科技有限公司,江苏 南京 210031)])], figs=[ArticleFig(id=1251895535012102958, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, language=EN, label=Fig. 1, caption=Transformer network assisted INS/GNSS integrated navigation training process, figureFileSmall=9slhCo0GMyflzsH9N05fVQ==, figureFileBig=rbDlR538Jd+vWKmYheSHSw==, tableContent=null), ArticleFig(id=1251895535100183348, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, language=CN, label=图1, caption=Transformer网络辅助INS/GNSS组合导航训练过程, figureFileSmall=9slhCo0GMyflzsH9N05fVQ==, figureFileBig=rbDlR538Jd+vWKmYheSHSw==, tableContent=null), ArticleFig(id=1251895535217623866, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, language=EN, label=Fig. 2, caption=Transformer network assisted INS/GNSS integrated navigation prediction process, figureFileSmall=ROLU29jJ7He+knfSG+cWIA==, figureFileBig=cOMaahXc+IVQiL+Ks/L8ZA==, tableContent=null), ArticleFig(id=1251895535314092865, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, language=CN, label=图2, caption=Transformer网络辅助INS/GNSS组合导航预测过程, figureFileSmall=ROLU29jJ7He+knfSG+cWIA==, figureFileBig=cOMaahXc+IVQiL+Ks/L8ZA==, tableContent=null), ArticleFig(id=1251895535393784647, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, language=EN, label=Fig. 3, caption=Prediction trajectory of combined navigation assisted by different neural networks, figureFileSmall=EPtki9RJ6M//O2I8IPt3Lg==, figureFileBig=tWE5aAEfddEddndNQc9X8g==, tableContent=null), ArticleFig(id=1251895535481865036, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, language=CN, label=图3, caption=不同神经网络辅助的组合导航预测轨迹, figureFileSmall=EPtki9RJ6M//O2I8IPt3Lg==, figureFileBig=tWE5aAEfddEddndNQc9X8g==, tableContent=null), ArticleFig(id=1251895535611888466, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, language=EN, label=Fig. 4, caption=Position prediction error of combined navigation assisted by different neural networks, figureFileSmall=RRQsE6t6twSO0P7nnyuwSQ==, figureFileBig=Pq8C2deOyDaqtaHUsmwskw==, tableContent=null), ArticleFig(id=1251895535699968856, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, language=CN, label=图4, caption=不同神经网络辅助的组合导航预测位置误差, figureFileSmall=RRQsE6t6twSO0P7nnyuwSQ==, figureFileBig=Pq8C2deOyDaqtaHUsmwskw==, tableContent=null), ArticleFig(id=1251895535783854939, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, language=EN, label=Fig. 5, caption=Transformer networks of different scales assist in predicting trajectories for integrated navigation, figureFileSmall=HucsSFhh3zkr639OCTBwGw==, figureFileBig=dkoXHMC7M+MwkfH5wEgwkQ==, tableContent=null), ArticleFig(id=1251895535880323936, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, language=CN, label=图5, caption=不同规模的Transformer网络辅助组合导航预测轨迹, figureFileSmall=HucsSFhh3zkr639OCTBwGw==, figureFileBig=dkoXHMC7M+MwkfH5wEgwkQ==, tableContent=null), ArticleFig(id=1251895535976792931, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, language=EN, label=Fig. 6, caption=Prediction position error of Transformer network assisted integrated navigation with different sizes, figureFileSmall=WBEQ+xai5mv1ffb9VeBQZA==, figureFileBig=3xEnlR1JPI7gIzaaKrtQHg==, tableContent=null), ArticleFig(id=1251895536056484713, tenantId=1146029695717560320, journalId=1251234473337991274, articleId=1251893508177609139, language=CN, label=图6, caption=不同规模的Transformer网络辅助组合导航预测位置误差, figureFileSmall=WBEQ+xai5mv1ffb9VeBQZA==, figureFileBig=3xEnlR1JPI7gIzaaKrtQHg==, tableContent=null)], attaches=null, journal=Journal(id=1251231494887223395, delFlag=0, nameCn=无线电通信技术, nameEn=Radio Communications Technology, nameHistory1=null, nameHistory2=null, issn=1003-3114, eissn=, cn=13-1099/TN, 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=veWCdfK9mJVXm/uFgI4wQA==, journalPrice=null, startedYear=null, abbrevIsoEn=Radio Communications Technology, journalRemark=null, publicationField=null, createdTime=1776246435141, updatedTime=1776397604574, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=R, firstLetterEn=R, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=veWCdfK9mJVXm/uFgI4wQA==, picEn=OSQVHuARoHUd1TQ4ONLQrQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1251865545604285354, language=CN, name=无线电通信技术, 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=1776397604609, updatedTime=1776397604609, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://wxdt.cbpt.cnki.net/index.aspx?t=1, submissionEditorUrl=https://wxdt.cbpt.cnki.net/index.aspx?t=3, submissionReviewUrl=https://wxdt.cbpt.cnki.net/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1251865545646228395, language=EN, name=Radio Communications Technology, 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=1776397604619, updatedTime=1776397604619, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://wxdt.cbpt.cnki.net/index.aspx?t=1, submissionEditorUrl=https://wxdt.cbpt.cnki.net/index.aspx?t=3, submissionReviewUrl=https://wxdt.cbpt.cnki.net/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1251234473337991274, websiteList=[Website(id=1251257283515203650, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1251234473337991274, 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/wxdtxjs/CN, language=CN, createTime=1776252583627, createBy=18614031015, updateTime=1776253691546, updateBy=18614031015, name=无线电通信技术-中文, tplId=1146099689490845704, title=无线电通信技术, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1251262047678313076, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283515203650, code=articleTextType, value=kx, createTime=1776253719491, updateTime=1776253719491, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262047653147249, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283515203650, code=banner, value=null, createTime=1776253719485, updateTime=1776253719485, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262047707673207, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283515203650, code=grayFlag, value=0, createTime=1776253719498, updateTime=1776253719498, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262047644758640, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283515203650, code=logo, value=https://castjournals.cast.org.cn/joweb/wxdtxjs/CN/file/pic?fileId=sk5LMh+QbAm+98l18HjovQ==, createTime=1776253719483, updateTime=1776253719483, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262047720256121, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283515203650, code=minRunFlag, value=0, createTime=1776253719501, updateTime=1776253719501, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262047669924467, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283515203650, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/wxdtxjs/CN/file/pic, createTime=1776253719489, updateTime=1776253719489, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262047716061816, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283515203650, code=silenceFlag, value=0, createTime=1776253719500, updateTime=1776253719500, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262047661535858, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283515203650, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1776253719487, updateTime=1776253719487, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262047682507381, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283515203650, code=themeColor, value=null, createTime=1776253719492, updateTime=1776253719492, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262047690895990, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283515203650, code=themeStyle, value=null, createTime=1776253719494, updateTime=1776253719494, creator=18614031015, updator=18614031015)]), Website(id=1251257283607478339, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1251234473337991274, 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/wxdtxjs/EN, language=EN, createTime=1776252583648, createBy=18614031015, updateTime=1776253687916, updateBy=18614031015, name=无线电通信技术-英文, tplId=1146101810881728533, title=Radio Communications Technology, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1251262071707484468, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283607478339, code=articleTextType, value=kx, createTime=1776253725220, updateTime=1776253725220, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262071690707249, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283607478339, code=banner, value=null, createTime=1776253725216, updateTime=1776253725216, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262071724261687, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283607478339, code=grayFlag, value=0, createTime=1776253725224, updateTime=1776253725224, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262071682318640, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283607478339, code=logo, value=https://castjournals.cast.org.cn/joweb/wxdtxjs/EN/file/pic?fileId=sk5LMh+QbAm+98l18HjovQ==, createTime=1776253725214, updateTime=1776253725214, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262071732650297, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283607478339, code=minRunFlag, value=0, createTime=1776253725226, updateTime=1776253725226, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262071703290163, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283607478339, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/wxdtxjs/EN/file/pic, createTime=1776253725219, updateTime=1776253725219, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262071728455992, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283607478339, code=silenceFlag, value=0, createTime=1776253725225, updateTime=1776253725225, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262071694901554, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283607478339, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1776253725217, updateTime=1776253725217, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262071711678773, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283607478339, code=themeColor, value=null, createTime=1776253725221, updateTime=1776253725221, creator=18614031015, updator=18614031015), WebsiteProps(id=1251262071720067382, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283607478339, code=themeStyle, value=null, createTime=1776253725223, updateTime=1776253725223, creator=18614031015, updator=18614031015)])], journalTitle=无线电通信技术, weixinUrl=null, journalUrl=https://wxdt.cbpt.cnki.net/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Radio Communications Technology, journalPhotoCn=veWCdfK9mJVXm/uFgI4wQA==, journalPhotoEn=OSQVHuARoHUd1TQ4ONLQrQ==, journalFirstLetter=R, 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/wxdtxjs/CN/10.3969/j.issn.1003-3114.2025.05.021, detailUrlEn=https://castjournals.cast.org.cn/joweb/wxdtxjs/EN/10.3969/j.issn.1003-3114.2025.05.021, pdfUrlCn=https://castjournals.cast.org.cn/joweb/wxdtxjs/CN/PDF/10.3969/j.issn.1003-3114.2025.05.021, pdfUrlEn=https://castjournals.cast.org.cn/joweb/wxdtxjs/EN/PDF/10.3969/j.issn.1003-3114.2025.05.021, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
Transformer网络辅助的融合卫星与惯性导航技术
收藏切换
PDF下载
吴思远 1 , 左大华 2 , 姜明 1
无线电通信技术 | 专题:智能通信、存储与信息处理技术前沿 2025,51(5): 1080-1086
收起
收藏切换
无线电通信技术 | 专题:智能通信、存储与信息处理技术前沿 2025, 51(5): 1080-1086
Transformer网络辅助的融合卫星与惯性导航技术
全屏
吴思远1, 左大华2, 姜明1
作者信息
  • 1.东南大学 信息科学与工程学院,江苏 南京 214135
  • 2.南京海善达信息科技有限公司,江苏 南京 210031
  • 吴思远 男,(1999—),硕士研究生。主要研究方向:5G移动通信。

    左大华 男,(1988—),硕士,高级工程师。主要研究方向:水上移动通信、船舶自动控制等。

    姜明 男,(1976—),博士,副教授。主要研究方向:移动通信系统中物理层/应用层纠错码编解码技术、迭代接收算法、基于人工智能的通信技术。

Transformer Network-assisted Fusion of Satellite and Inertial Navigation Technologies
Siyuan WU1, Dahua ZUO2, Ming JIANG1
Affiliations
  • 1.School of Information Science and Engineering, Southeast University, Nanjing 214135, China
  • 2.Nanjing Sandemarine Information Technology Co. , Ltd. , Nanjing 210031, China
出版时间: 2025-09-18 doi: 10.3969/j.issn.1003-3114.2025.05.021
文章导航
收藏切换

当载体(如无人机、船只和车辆等)在极端环境下运动时,可能会出现可见卫星消失的情况,这会导致全球卫星导航系统(Global Navigation Satellite System,GNSS)信号出现短暂或长时间的丢失(失锁)。在这种情况下,融合导航将被迫切换到纯惯性导航系统(Inertial Navigation System,INS),纯惯性导航运行时间的增加会导致误差不断累积,导航精度快速下降。为解决GNSS信号丢失后INS精度快速下降的问题,提出基于变换器(Transformer)网络辅助的GNSS与INS融合导航技术。当GNSS信号锁定时,Transformer网络利用当前的INS信息和GNSS增量信息(2个相邻时刻GNSS位置信息的变化量)来训练出二者的映射关系;当GNSS信号失锁时,Transformer网络利用之前训练出的映射关系,由当前的INS信息预测GNSS增量信息,并将INS信息和预测的GNSS信息进行融合导航。仿真结果表明,基于Transformer网络辅助的GNSS与INS融合导航技术,在GNSS信号短暂或一定时间内失锁的条件下,仍然可以提供稳定可靠的导航信号。此外,Transformer网络辅助的融合导航方法为其他网络辅助的融合提供了参考。

惯性导航系统  /  全球卫星导航系统  /  融合导航  /  失锁  /  变换器神经网络

When a carrier (such as drones, ships, and vehicles) moves in extreme environments, the visibility of satellites may be lost, leading to a temporary or prolonged loss of lock on Global Navigation Satellite System (GNSS) signals. In such scenarios, an integrated navigation system is forced to switch to a pure Inertial Navigation System (INS). However, prolonged reliance on inertial navigation alone results in the accumulation of errors and a rapid decline in navigation accuracy. To address the rapid decline in INS accuracy after GNSS signal loss, a fusion navigation technology of GNSS and INS assisted by Transformer networks is proposed. When the GNSS signal is locked, the Transformer network utilizes current INS information and GNSS incremental data (the change in GNSS position information between two adjacent time periods) to train a mapping relationship between the two. When the GNSS signal is lost, the Transformer network leverages the previously established mapping relationship to predict GNSS incremental information based on the current INS data, and then integrates the INS information with the predicted GNSS data for navigation. Simulation results demonstrate that the Transformer network-assisted GNSS/INS fusion navigation technology can provide stable and reliable navigation signals even under conditions of temporary or prolonged GNSS signal loss. Furthermore, the Transformer network-assisted fusion navigation method offers a reference for other network-assisted fusion implementations.

INS  /  GNSS  /  integrated navigation  /  loss of lock  /  Transformer neural network
吴思远, 左大华, 姜明. Transformer网络辅助的融合卫星与惯性导航技术. 无线电通信技术, 2025 , 51 (5) : 1080 -1086 . DOI: 10.3969/j.issn.1003-3114.2025.05.021
Siyuan WU, Dahua ZUO, Ming JIANG. Transformer Network-assisted Fusion of Satellite and Inertial Navigation Technologies[J]. Radio Communications Technology, 2025 , 51 (5) : 1080 -1086 . DOI: 10.3969/j.issn.1003-3114.2025.05.021
INS/GNSS组合导航系统结合了INS与GNSS的优点,实现了高精度、高可靠性的定位和导航能力[1]。INS通过检测载体的加速度和角速度来确定其位置、速度及姿态,然而,这种导航方式的误差会随着时间逐渐累积[2]。GNSS能够提供长期稳定的位置信息,但受制于卫星信号的可用性和环境干扰[3]。二者结合后,GNSS为INS提供定期的精确校准,抑制INS误差增长。同时,在卫星信号丢失时,INS可以继续提供短时间内的可靠导航数据[4]。这种互补特性使得组合导航系统在复杂环境下也能保持良好的性能,广泛应用于航空、航海、陆地车辆等领域[5]
随着神经网络技术的迅猛发展,利用神经网络辅助的导航方案逐步成为研究热点。早期的神经网络应用多数是前馈神经网络(Feedforward Neural Network,FNN)[6],为了增强处理序列数据的能力提出了循环神经网络(Recurrent Neural Network,RNN)[7],再到门控循环单元(Gated Recurrent Unit,GRU)[8],近几年,又出现了性能强大的Transformer神经网络,这一过程反映了神经网络对序列数据处理能力的不断提升和模型复杂度的逐步优化[9],也使得神经网络在各种实际系统中的部署应用成为可能。
当载体在复杂和恶劣的环境中移动时,可见卫星数量可能极少甚至完全不可见,导致GNSS信号丢失[10]。在这种情形下,组合导航系统将完全依赖于INS进行解算,而使用单一的INS会导致误差迅速累积,精度快速下降[11]。为解决GNSS信号丢失后INS精度快速下降的问题,目前使用神经网络来辅助组合导航是非常有潜力的一种解决方案[12]。因此,选择性能强大的Transformer网络来辅助组合导航,对研究基于神经网络辅助的INS/GNSS组合导航具有重要的意义。
INS主要分为平台式INS和捷联式INS两大类[13]。平台式INS的惯性测量组件通过机械万向节与载体连接,保持相对于惯性空间的固定方向,直接提供载体在惯性空间中的角速度和加速度信息。捷联式INS不采用机械平台来维持传感器的方向[14],而是将加速度计和陀螺仪等惯性传感器直接安装在载体上,利用数学算法来计算载体的姿态、速度和位置信息[15]。因此,平台式系统通常更复杂但可能提供更高的精度,捷联式系统则结构简单、成本较低且可靠性高[16]。本文使用的是捷联式INS。
捷联式INS的解算算法分为姿态更新、速度更新和位置更新3个部分。
将姿态角转化为姿态矩阵,给定俯仰角θ、横滚角φ和航向角ψC1表示绕y轴旋转的旋转矩阵、C2表示绕x轴旋转的旋转矩阵、C3表示绕z轴旋转的旋转矩阵,可构造旋转矩阵:
使用最小旋转矢量进行姿态更新,最小旋转矢量ϕ的计算涉及反对称矩阵(V×),反对称矩阵计算如下:
最小旋转矢量对应的旋转矩阵MRVϕ)为:
式中:I为单位矩阵。
最终的姿态更新矩阵为:
式中:表示第m时刻的T为采样时间间隔,为地球自转角速度加上由于载体移动引起的导航坐标系相对惯性空间的变化率,为在2个连续时刻之间由陀螺仪测量得到的角度增量。
将姿态矩阵转换回姿态角,为了从更新后的姿态矩阵中提取出新的姿态角,可采用:
式中:xy)表示矩阵中在第x行第y列的元素。INS输出的航向角可表示为Ai=(θφψ)。
速度更新考虑了多种因素,包括载体相对于惯性空间的速度变化、科里奥利力以及重力加速度的影响。速度更新的推导可表示为:
式中:g0=9.780 325 333 434 361 m/s2g表示特定位置的重力加速度。
最终的速度更新计算为:
式中:表示在第m个时间段内由于旋转运动导致的速度变化量,Δθm表示角位移,Δvm表示速度变化,表示在第m个时间段内由于斯科柳拉效应导致的速度变化量,表示比力速度增量即惯性测量单元输出的三轴加速度计数据表示有害加速度的速度增量,表示地球相对于惯性空间的旋转角速度,表示载体相对于地球表面的旋转角速度,表示INS输出的速度信息Vi
位置更新涉及到将速度积分成位移,并考虑到地球曲率的影响。对于纬度L、经度λ和高度h,更新公式如下:
式中:pm-1为上一采样时刻的位置向量,pm为当前时刻的位置向量,即INS输出的位置信息Pi
p定义为:
矩阵Mpv定义为:
式中:RM为子午圈半径,RN为卯酉圈半径。
Transformer网络是一种采用自注意力机制的架构[17],在自然语言处理及其他序列建模任务中表现出色。与传统的RNN和卷积神经网络的工作原理不同,Transformer网络完全依赖于注意力机制来捕捉输入序列中的依赖关系,因此支持更加并行化的训练过程,并且在处理长距离依赖方面表现优异。
给定一个输入序列X=(x1x2,…,xn),其中每个xi为一个嵌入向量,Transformer网络模型将这些向量线性变换为3个不同矩阵:查询(Query)矩阵、键(Key)矩阵和值(Value)矩阵,分别记作QKV,表示为:
式中:WQWKWV为可学习的权重矩阵,用于从输入序列生成查询、键和值。通过计算查询和所有键之间的点积来衡量其相关性,再经过缩放和平滑处理,通常是软最大值(softmax)函数,得到注意力权重矩阵A:
式中:dk为键的维度,用来缩放点积以稳定梯度。
将注意力权重应用于V来获取加权求和的结果,即上下文向量Z:
该过程可看作是在输入序列的不同位置之间分配注意力权重,使得重要的部分被强调,而不太相关的信息则被抑制。
为了增强模型的能力,Transformer网络使用了多头注意力机制。并非仅使用一组QKV,而是创建多个独立的头,每个头均有一组独立的权重矩阵,并对结果进行拼接和线性变换:
式中:MultiHead表示多头注意力机制函数,Concat表示将所有注意力头的结果拼接成一个大矩阵的函数,Hi表示第i个注意力头的输出结果,h表示头的数量,WO表示最终的输出权重矩阵,Attention表示单个注意力机制计算过程的函数。
Transformer网络还包括FNN,其作用是对每个位置的向量应用相同的线性变换,FNN之后为激活函数:
式中:FNNx)为对输入x进行处理的FNN函数,b1b2分别为第一层和第二层的偏置向量。
每个子层后面都有残差连接和层归一化来加速收敛和提高模型性能,表示为:
式中:Sublayer表示对输出x进行处理的子层函数,LayerNorm表示进行层归一化的函数。
多头自注意力机制MultiHead和FNN共同组成一个Transformer层,Transformer网络由多个Transformer层组成,最后一个Transformer层的输出即为Transformer网络的最终输出。
当GNSS信号锁定时,Transformer网络辅助INS/GNSS组合导航训练过程如图1所示。使用Transformer网络进行实时训练,该网络的输入为惯性测量单元提供的三轴加速度计数据、三轴陀螺仪数据、INS输出的速度信息VI、航向角AI和GNSS输出的位置信息增量ΔPG,即Transformer网络的输入序列X=(VIAI,ΔPG)。在这种模式下,Transformer网络可以得到惯性测量单元信息、INS信息和GNSS增量信息之间的映射关系,训练期间,仍可通过将实时INS信息和累加后的GNSS增量信息送入卡尔曼滤波进行误差修正,得到INS/GNSS组合导航信息[18-19]图1中,PI表示INS输出的位置信息,PG0表示GNSS输出的初始位置信息,PG表示GNSS输出的位置信息,δPδVδA分别表示位置信息的修正误差、速度信息的修正误差、航向角的修正误差,PI/GVI/GAI/G分别表示INS/GNSS组合导航后的位置信息、速度信息、航向角。
当GNSS信号失锁时,Transformer网络辅助INS/GNSS组合导航预测过程如图2所示[20]。虽然失锁,无法获取真实的GNSS信息,但在Transformer网络辅助INS/GNSS组合导航训练过程中,已学习到惯性测量单元信息、INS信息和GNSS增量信息之间的映射关系[21-22],此时惯性测量单元信息、INS信息送入Transformer网络将得到预测的GNSS增量信息ΔPG(即Transformer网络最后一个Transformer层的输出FNN),将预测的GNSS增量信息进行累加得到当前时刻的预测GNSS信息,将当前时刻的INS信息和当前时刻的预测GNSS信息送入卡尔曼滤波进行误差修正,得到Transformer网络辅助的INS/GNSS组合导航信息。
本文采用Python 3.11.4环境训练Transformer网络模型,并基于Matlab开源导航工具箱NaveGo[23]构建INS/GNSS组合导航仿真平台。该平台实现了INS/GNSS数据融合算法,通过模拟ADIS16405惯性测量单元的惯性数据与GARMIN GNSS接收机(5~18 Hz可变更新率)的卫星定位数据,实现组合导航系统的仿真与分析。图3图6的仿真结果中,在GNSS信号锁定时,0~360 s的数据用于神经网络训练;360~420 s的数据对应GNSS信号失锁阶段,数据由Transformer网络预测生成。
图3展示了在GNSS信号失锁时,对纯惯性导航、GRU和Transformer网络的仿真预测轨迹进行对比的结果。可以看出,初始阶段三者的轨迹预测误差均较小;随着导航时间增加,纯惯性导航的轨迹显著偏离实际轨迹,而GRU和Transformer网络的预测轨迹仍然贴近实际轨迹。在导航后半段,Transformer网络的预测轨迹比GRU网络更接近实际轨迹。
图4展示了图3的具体量化分析结果,即GRU和Transformer网络的预测轨迹位置误差的仿真结果。在390 s时,Transformer网络的预测位置误差相比GRU网络减少了54.7%;在420 s时,该误差减少了57.2%。可见,Transformer网络的预测位置误差相比GRU网络降低了50%~60%。
图5为不同规模的Transformer网络辅助组合导航的仿真预测轨迹对比。其中前一个数字表示Transformer网络的输入与输出向量维度,后一个数字表示前馈网络的隐藏层大小。从图中可以看出,Transformer网络辅助组合导航并非规模越大性能越好,而是规模为64-128时性能最优;此后,网络规模减小或增大均会导致性能下降。
图6展示了图5的具体量化分析结果,即不同规模Transformer网络辅助组合导航的预测轨迹位置误差仿真结果。可以看出,规模为64-128时预测位置误差最小;此后,网络规模减小或增大均会导致预测位置误差增大。在390 s时,Transformer网络规模为64-128的预测位置误差比256-512减少66.7%,比16-32减少41.1%,比32-64减少39.6%,比128-256减少18.8%。在420 s时,Transformer网络规模为64-128的预测位置误差比256-512减少66.2%,比16-32减少64.7%,比32-64减少30.7%,比128-256减少30.3%。可见,规模为64-128的Transformer网络,其预测位置误差相比其他规模网络降低了20%-67%。
本文在INS/GNSS组合导航的基础上引入神经网络辅助,GNSS信号失锁时,可通过神经网络预测GNSS信号并用于组合导航。GNSS信号失锁后,不同神经网络或不同规模的同种神经网络辅助的组合导航具有不同轨迹预测性能。研究了GRU和Transformer网络辅助的组合导航性能,仿真结果表明,Transformer网络辅助的组合导航性能优于GRU辅助的组合导航。
参考文献 引证文献
排序方式:
[1]
孙淑光,徐延枝,王浩琳.卫星拒止环境下无人机INS/GNSS紧组合定位算法研究[J].物联网技术,2025,15(1):44-48.
[2]
武文博,吕志伟,周玟龙,.基于组合历元新息抗差的GNSS/INS欺骗检测方法[J].中国惯性技术学报, 2024,32(4):354-362.
[3]
周涛,邹进贵,赵胤植,.附加UWB约束的GNSS/INS组合导航算法[J].测绘通报,2024(11):78-82.
[4]
王尔申,刘依凡,于腾丽,.基于全连接神经网络的GNSS/INS组合定位方法[J].沈阳航空航天大学学报,2024,41(5):54-61.
[5]
闫文林,严泰明,潘兴驰,.GNSS/INS松、紧组合导航算法的等价性条件[J].江苏师范大学学报(自然科学版),2024,42(3):64-69.
[6]
王艳红,赵亮,王官军.改进Transformer模型的语音识别轻量化设计[J/OL].计算机工程与应用1-9[2025-03-21]. https://link.cnki.net/urlid/11.2127.TP.20241231.1449.014.
[7]
金峥,贾克斌.一种基于Transformer架构的多层级自动睡眠分期模型[J].电子学报,2025,53(2):545-557.
[8]
潘丹,骆根强,曾安.基于Transformer和卷积神经网络双并行分支编码器神经网络的冠状动脉分割[J].生物医学工程学杂志,2024,41(6):1195-1203.
[9]
王安琪,于超,陈胤玮,.基于LSTM-Transformer的脑电情感分析[J].中国医学物理学杂志,2024,41(12):1550-1557.
[10]
孙洪驰,杨轩,龙腾,.随机多步时延背景下GNSS/低轨/INS多源导航系统联邦滤波方法[J].电子元器件与信息技术,2024,8(9):184-187.
[11]
周佩旻,马下平.不同场景下GNSS与INS组合定位性能评估[J].测绘通报,2024(增刊2):263-266.
[12]
吴庆,刘长建,肖国锐,.不同情形下GNSS/INS组合导航系统精度分析[J].测绘科学技术学报,2024,40(4):348-354.
[13]
骆元鹏,程正逢,易祎,.一种GNSS/INS紧组合状态域多故障渐消方法[J].导航定位学报,2024,12(4):123-131.
[14]
刘静.基于GNSS/INS/Visual组合的自主定位定向算法研究[D].西安:西安理工大学,2024.
[15]
褚雨欣.基于图优化的共时钟多天线单差GNSS/INS组合测姿算法研究[D].上海:华东师范大学,2024.
[16]
李忱汉.复杂场景GNSS/INS数据融合定位算法研究[D].北京:中国测绘科学研究院,2024.
[17]
王高峰,张卓石,高蔓,.基于多特征融合卷积神经网络结合Transformer的电能质量扰动分类方法[J].北华大学学报(自然科学版),2025,26(1):115-124.
[18]
陶毅峰. GRU循环神经网络辅助的GNSS/INS组合导航算法研究[D].武汉:武汉大学,2021.
[19]
陶毅峰,江金光,方伟.基于GRU循环神经网络辅助的组合导航算法[J].计算机工程与设计,2021,42(2):370-376.
[20]
黄庆东,王皓,郭振,.基于注意力机制的GRU神经网络辅助INS/GNSS组合导航算法[J].西安邮电大学学报,2024,29(2):11-19.
[21]
柳絮,王坚,肖星星,. GNSS失锁下Tent-ASO-BP辅助GNSS/INS松组合导航算法[J].山东科技大学学报(自然科学版),2024,43(6):24-33.
[22]
王家鑫,周艳玲,庞茹. GNSS拒止下GRU神经网络INS/GNSS融合导航研究[J].导航与控制,2024,23(5/6):163-173.
[23]
GONZALEZ R, GIRIBET J I, PATIO H D. Navego: A Simulation Framework for Low-cost Integrated Navigation Systems[J]. Control Engineering and Applied Informatics,2015,17(2):110-120.
2025年第51卷第5期
PDF下载
101
48
引用本文
BibTeX
文章信息
doi: 10.3969/j.issn.1003-3114.2025.05.021
  • 接收时间:2025-03-25
  • 首发时间:2026-04-17
  • 出版时间:2025-09-18
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-03-25
基金
作者信息
    1.东南大学 信息科学与工程学院,江苏 南京 214135
    2.南京海善达信息科技有限公司,江苏 南京 210031
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/wxdtxjs/CN/10.3969/j.issn.1003-3114.2025.05.021
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