Article(id=1244336190690800003, tenantId=1146029695717560320, journalId=1244323073571209252, issueId=1244336186114819067, articleNumber=null, orderNo=null, doi=10.13695/j.cnki.12-1222/o3.2025.10.008, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1731513600000, receivedDateStr=2024-11-14, revisedDate=null, revisedDateStr=null, acceptedDate=1755619200000, acceptedDateStr=2025-08-20, onlineDate=1774602466508, onlineDateStr=2026-03-27, pubDate=1761753600000, pubDateStr=2025-10-30, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1774602466508, onlineIssueDateStr=2026-03-27, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1774602466508, creator=13701087609, updateTime=1774602466508, updator=13701087609, issue=Issue{id=1244336186114819067, tenantId=1146029695717560320, journalId=1244323073571209252, year='2025', volume='33', issue='10', pageStart='955', pageEnd='1060', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1774602465418, creator=13701087609, updateTime=1774604459075, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1244344548185452773, tenantId=1146029695717560320, journalId=1244323073571209252, issueId=1244336186114819067, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1244344548185452774, tenantId=1146029695717560320, journalId=1244323073571209252, issueId=1244336186114819067, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=1016, endPage=1025, ext={EN=ArticleExt(id=1244336191017955720, articleId=1244336190690800003, tenantId=1146029695717560320, journalId=1244323073571209252, language=EN, title=A regional recognition method for seamless indoor-outdoor localization of unmanned vehicles, columnId=1244336188069364733, journalTitle=Journal of Chinese Inertial Technology, columnName=Integrated Navigation Technology, runingTitle=null, highlight=null, articleAbstract=

To address the challenge of accurately determining the environmental region of unmanned vehicles during seamless indoor-outdoor positioning, a regional recognition method for seamless indoor-outdoor localization is proposed. Firstly, a joint prediction model integrating particle swarm optimization-support vector machine (PSO-SVM) and hidden Markov model (HMM) is designed. Environmental feature data acquired by sensors serve as model inputs to generate regional recognition results. Secondly, three environmental models are introduced to describe the vehicle's operational environment, with corresponding measurement information selected based on the regional recognition outcomes. Finally, the regional transition probabilities are utilized to update the switching probabilities of the three environmental sub-models in the interactive multiple model (IMM) algorithm, thereby enhancing the accuracy of environmental region recognition and positioning precision for seamless indoor-outdoor navigation. The results of real-vehicle experiment show that the proposed joint recognition method achieves an accuracy of 98.09% in region recognition, representing improvements of 2.13% and 9.53% compared to using PSO-SVM or HMM alone. Further experiments indicate that the proposed seamless positioning method enhances the average positioning accuracy by 43.75% and 22.30% compared to the traditional federated Kalman filter (FKF) algorithm and IMM algorithm, respectively.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Xiujian YANG, Yixing YANG, Shengbin ZHANG), CN=ArticleExt(id=1244336215110038367, articleId=1244336190690800003, tenantId=1146029695717560320, journalId=1244323073571209252, language=CN, title=无人车辆室内外无缝定位的区域识别方法, columnId=1244336188241331200, journalTitle=中国惯性技术学报, columnName=组合导航技术, runingTitle=null, highlight=null, articleAbstract=

针对无人车辆室内外无缝定位过程中难以准确判定车辆所处区域的问题,提出了一种无人车辆室内外无缝定位的区域识别方法。首先,设计基于粒子群优化的支持向量机(PSO-SVM)与隐马尔可夫模型(HMM)的联合预测模型,并利用传感器获取环境特征数据作为模型输入,得到区域识别结果;然后,引入三种环境模型描述车辆所处环境,根据区域识别结果选择相应的量测信息;最后,利用区域切换概率更新交互式多模型算法(IMM)中三个环境子模型的切换概率,从而提高无人车辆的室内外无缝定位环境区域识别的准确性和定位精度。实车实验结果表明,联合识别方法在区域识别中的准确性为98.09%,相较于单独使用PSO-SVM或HMM分别提升了2.13%和9.53%。进一步实验表明,与传统的联邦卡尔曼滤波算法(FKF)以及IMM算法相比,采用所提区域识别方法的平均定位精度分别提高了43.75%和22.30%。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
张生斌(1981—),男,讲师,博士,从事车辆测试技术研究。
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=j2QT8DuN3b42rRNtqRsIWg==, magXml=FdGVRFKHpS0Iklob2yxIhw==, pdfUrl=null, pdf=mlfzGWNZwBM+mvS7UN/UTQ==, pdfFileSize=5186899, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=d/0wlZhM7hts0xTSrxHx3A==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=0A+FVsSDRKNCZoZxQMtztA==, mapNumber=null, authorCompany=null, fund=null, authors=

杨秀建(1980—),男,教授,博士生导师,从事车辆动力学控制、智能车辆技术研究。

, authorsList=杨秀建, 杨义兴, 张生斌)}, authors=[Author(id=1244336215495914353, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, 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=1244336215579800439, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, authorId=1244336215495914353, language=EN, stringName=Xiujian YANG, firstName=Xiujian, middleName=null, lastName=YANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Faculty of Transportation Engineering, Kunming University of Science and Technology, Kunming 650500, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1244336215680463739, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, authorId=1244336215495914353, language=CN, stringName=杨秀建, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=昆明理工大学 交通工程学院,昆明 650500, bio={"content":"

杨秀建(1980—),男,教授,博士生导师,从事车辆动力学控制、智能车辆技术研究。

"}, bioImg=null, bioContent=

杨秀建(1980—),男,教授,博士生导师,从事车辆动力学控制、智能车辆技术研究。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1244336215391056746, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, xref=null, ext=[AuthorCompanyExt(id=1244336215395251051, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, companyId=1244336215391056746, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Faculty of Transportation Engineering, Kunming University of Science and Technology, Kunming 650500, China), AuthorCompanyExt(id=1244336215403639660, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, companyId=1244336215391056746, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=昆明理工大学 交通工程学院,昆明 650500)])]), Author(id=1244336215802098559, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, 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=1244336215919539079, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, authorId=1244336215802098559, language=EN, stringName=Yixing YANG, firstName=Yixing, middleName=null, lastName=YANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Faculty of Transportation Engineering, Kunming University of Science and Technology, Kunming 650500, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1244336216016008073, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, authorId=1244336215802098559, language=CN, stringName=杨义兴, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=昆明理工大学 交通工程学院,昆明 650500, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1244336215391056746, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, xref=null, ext=[AuthorCompanyExt(id=1244336215395251051, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, companyId=1244336215391056746, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Faculty of Transportation Engineering, Kunming University of Science and Technology, Kunming 650500, China), AuthorCompanyExt(id=1244336215403639660, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, companyId=1244336215391056746, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=昆明理工大学 交通工程学院,昆明 650500)])]), Author(id=1244336216120865679, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, 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=1244336216229917590, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, authorId=1244336216120865679, language=EN, stringName=Shengbin ZHANG, firstName=Shengbin, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Faculty of Transportation Engineering, Kunming University of Science and Technology, Kunming 650500, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1244336216313803673, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, authorId=1244336216120865679, language=CN, stringName=张生斌, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=昆明理工大学 交通工程学院,昆明 650500, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1244336215391056746, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, xref=null, ext=[AuthorCompanyExt(id=1244336215395251051, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, companyId=1244336215391056746, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Faculty of Transportation Engineering, Kunming University of Science and Technology, Kunming 650500, China), AuthorCompanyExt(id=1244336215403639660, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, companyId=1244336215391056746, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=昆明理工大学 交通工程学院,昆明 650500)])])], keywords=[Keyword(id=1244336216439632800, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=EN, orderNo=1, keyword=unmanned vehicles), Keyword(id=1244336216552879012, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=EN, orderNo=2, keyword=regional recognition), Keyword(id=1244336216695485353, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=EN, orderNo=3, keyword=multi-source fusion), Keyword(id=1244336216854868911, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=EN, orderNo=4, keyword=interactive multiple model algorithm), Keyword(id=1244336216955532210, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=EN, orderNo=5, keyword=seamless indoor-outdoor positioning), Keyword(id=1244336217064584118, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=CN, orderNo=1, keyword=无人车辆), Keyword(id=1244336217152664506, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=CN, orderNo=2, keyword=区域识别), Keyword(id=1244336217244939198, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=CN, orderNo=3, keyword=多源融合), Keyword(id=1244336217316242369, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=CN, orderNo=4, keyword=交互多模型算法), Keyword(id=1244336217404322756, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=CN, orderNo=5, keyword=室内外无缝定位)], refs=[Reference(id=1244336222542344281, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=2024, volume=32, issue=07, pageStart=654, pageEnd=662, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=杨秀建, 敖鹏, 沈世全, journalName=中国惯性技术学报, refType=null, unstructuredReference=杨秀建, 敖鹏, 沈世全, . 面向复杂环境的UWB/LiDAR/IMU组合定位方法[J]. 中国惯性技术学报, 2024, 32(07): 654-662., articleTitle=面向复杂环境的UWB/LiDAR/IMU组合定位方法, refAbstract=null), Reference(id=1244336224060682334, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=2024, volume=32, issue=07, pageStart=654, pageEnd=662, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Yang X, Ao P, Shen S, journalName=Journal of Chinese Inertial Technology, refType=null, unstructuredReference=Yang X, Ao P, Shen S, et al. UWB/LiDAR/IMU combined localization method for complex environment[J]. Journal of Chinese Inertial Technology, 2024, 32(07): 654-662., articleTitle=UWB/LiDAR/IMU combined localization method for complex environment, refAbstract=null), Reference(id=1244336224161345634, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=557, pageEnd=562, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=Zhao X, Tang P, Song Q, journalName=null, refType=null, unstructuredReference=Zhao X, Tang P, Song Q, et al. Experimental analysis of multipath effects on GNSS positioning in urban canyon[C]//2021 IEEE 4th International Conference on Electronic Information and Communication Technology (ICEICT). China, August 18-20, 2021: 557-562., articleTitle=Experimental analysis of multipath effects on GNSS positioning in urban canyon, refAbstract=null), Reference(id=1244336224253620325, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=2022, volume=30, issue=3, pageStart=322, pageEnd=327, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=李旭, 孔鑫, 刘锡祥, journalName=中国惯性技术学报, refType=null, unstructuredReference=李旭, 孔鑫, 刘锡祥, . 基于交互多模型距离平滑的UWB/IMU因子图组合导航方法[J]. 中国惯性技术学报, 2022, 30(3): 322-327., articleTitle=基于交互多模型距离平滑的UWB/IMU因子图组合导航方法, refAbstract=null), Reference(id=1244336224345895016, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=2022, volume=30, issue=3, pageStart=322, pageEnd=327, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=Li X, Kong X, Liu X, journalName=Journal of Chinese Inertial Technology, refType=null, unstructuredReference=Li X, Kong X, Liu X, et al. UWB/IMU factor graph integrated navigation method based on interactive multi-model distance smoothing[J]. Journal of Chinese Inertial Technology, 2022, 30(3): 322-327., articleTitle=UWB/IMU factor graph integrated navigation method based on interactive multi-model distance smoothing, refAbstract=null), Reference(id=1244336224433975404, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=2011, volume=99, issue=11, pageStart=1882, pageEnd=1904, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=Fernandez-Prades C, Presti L, Falletti E, journalName=Proceedings of the IEEE, refType=null, unstructuredReference=Fernandez-Prades C, Presti L, Falletti E. Satellite radio localization from GPS to GNSS and beyond: novel technologies and applications for civil mass market[J]. Proceedings of the IEEE, 2011, 99(11): 1882-1904., articleTitle=Satellite radio localization from GPS to GNSS and beyond: novel technologies and applications for civil mass market, refAbstract=null), Reference(id=1244336224551415920, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=2021, volume=23, issue=8, pageStart=9995, pageEnd=10011, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=Li Y, Chen R, Niu X, journalName=IEEE Transactions on Intelligent Transportation Systems, refType=null, unstructuredReference=Li Y, Chen R, Niu X, et al. Inertial sensing meets machine learning: Opportunity or challenge[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 23(8): 9995-10011., articleTitle=Inertial sensing meets machine learning: Opportunity or challenge, refAbstract=null), Reference(id=1244336224681439348, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=2024, volume=32, issue=04, pageStart=354, pageEnd=362, url=null, language=null, rfNumber=[6], rfOrder=7, 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(04): 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=1244336224777908344, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=2024, volume=32, issue=04, pageStart=354, pageEnd=362, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=Wu W, Lyu Z, Zhou W, journalName=Journal of Chinese Inertial Technology, refType=null, unstructuredReference=Wu W, Lyu Z, Zhou W, et al. GNSS/INS spoofing detection method based on combined epoch innovation robustness[J]. Journal of Chinese Inertial Technology, 2024, 32(04): 354-362., articleTitle=GNSS/INS spoofing detection method based on combined epoch innovation robustness, refAbstract=null), Reference(id=1244336224845017212, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=2025, volume=12, issue=11, pageStart=16653, pageEnd=16667, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=Zhang S, Tang H, Chen L, journalName=IEEE Internet of Things Journal, refType=null, unstructuredReference=Zhang S, Tang H, Chen L, et al. A seamless pedestrian localization system based on GNSS/IMU/UWB/MAP integration[J]. IEEE Internet of Things Journal, 2025, 12(11): 16653-16667., articleTitle=A seamless pedestrian localization system based on GNSS/IMU/UWB/MAP integration, refAbstract=null), Reference(id=1244336225071509634, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=2011, volume=null, issue=null, pageStart=21, pageEnd=23, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=Kohtake N, Morimoto S, Kogure S, journalName=null, refType=null, unstructuredReference=Kohtake N, Morimoto S, Kogure S, et al. Indoor and outdoor seamless positioning using indoor messaging system and GPS[C]//Proceedings of the international conference on indoor positioning and indoor navigation (IPIN2011), Guimarães, Portugal. 2011: 21-23., articleTitle=Indoor and outdoor seamless positioning using indoor messaging system and GPS, refAbstract=null), Reference(id=1244336225277030535, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=2024, volume=243, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=11, authorNames=Feng T, Liu Y, Yu Y, journalName=Expert Systems with Applications, refType=null, unstructuredReference=Feng T, Liu Y, Yu Y, et al. CrowdLOC-S: Crowdsourced seamless localization framework based on CNN-LSTM-MLP enhanced quality indicator[J]. Expert Systems with Applications, 2024, 243: 122852., articleTitle=CrowdLOC-S: Crowdsourced seamless localization framework based on CNN-LSTM-MLP enhanced quality indicator, refAbstract=null), Reference(id=1244336225381888138, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=20, pageStart=24895, pageEnd=24906, url=null, language=null, rfNumber=[10], rfOrder=12, authorNames=Li X, Wu Z, Shen Z, journalName=IEEE Sensors Journal, refType=null, unstructuredReference=Li X, Wu Z, Shen Z, et al. An indoor and outdoor seamless positioning system for low-cost UGV using PPP/INS/UWB tightly coupled integration[J]. IEEE Sensors Journal, 2023, 23(20): 24895-24906., articleTitle=An indoor and outdoor seamless positioning system for low-cost UGV using PPP/INS/UWB tightly coupled integration, refAbstract=null), Reference(id=1244336225482551438, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=2015, volume=23, issue=01, pageStart=76, pageEnd=80, url=null, language=null, rfNumber=[11], rfOrder=13, authorNames=张威奕, 曾庆喜, 张鹏娜, journalName=中国惯性技术学报, refType=null, unstructuredReference=张威奕, 曾庆喜, 张鹏娜, . 基于UKF的车辆GPS/蜂窝网无缝定位算法[J]. 中国惯性技术学报, 2015, 23(01): 76-80., articleTitle=基于UKF的车辆GPS/蜂窝网无缝定位算法, refAbstract=null), Reference(id=1244336225587409043, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=2015, volume=23, issue=01, pageStart=76, pageEnd=80, url=null, language=null, rfNumber=[11], rfOrder=14, authorNames=Zhang W, Zeng Q, Zhang P, journalName=Journal of Chinese Inertial Technology, refType=null, unstructuredReference=Zhang W, Zeng Q, Zhang P, et al. Vehicle GPS/cellular network seamless positioning algorithm based on UKF[J]. Journal of Chinese Inertial Technology, 2015, 23(01): 76-80., articleTitle=Vehicle GPS/cellular network seamless positioning algorithm based on UKF, refAbstract=null), Reference(id=1244336225704849559, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=2023, volume=35, issue=1, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=15, authorNames=Yao L, Li M, Xu T, journalName=Measurement Science and Technology, refType=null, unstructuredReference=Yao L, Li M, Xu T, et al. GNSS/UWB/INS indoor and outdoor seamless positioning algorithm based on federal filtering[J]. Measurement Science and Technology, 2023, 35(1): 015135., articleTitle=GNSS/UWB/INS indoor and outdoor seamless positioning algorithm based on federal filtering, refAbstract=null), Reference(id=1244336225822290076, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=16, authorNames=张容阁, journalName=null, refType=null, unstructuredReference=张容阁. 基于UWB/GNSS/IMU的机器人室内外无缝定位技术研究[D]. 哈尔滨: 哈尔滨工业大学, 2020., articleTitle=基于UWB/GNSS/IMU的机器人室内外无缝定位技术研究, refAbstract=null), Reference(id=1244336225931341983, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=17, authorNames=Zhang R, journalName=null, refType=null, unstructuredReference=Zhang R. Research on indoor-outdoor seamless robot positioning technology based on UWB/GNSS/IMU[D]. Harbin: Harbin Institute of Technology, 2020., articleTitle=Research on indoor-outdoor seamless robot positioning technology based on UWB/GNSS/IMU, refAbstract=null), Reference(id=1244336226073948324, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=18, authorNames=王琳, journalName=null, refType=null, unstructuredReference=王琳. 室内外无缝定位中的情境感知方法研究[D]. 上海: 上海交通大学, 2017., articleTitle=室内外无缝定位中的情境感知方法研究, refAbstract=null), Reference(id=1244336226203971751, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=19, authorNames=Wang L, journalName=null, refType=null, unstructuredReference=Wang L. Research on context awareness in indoor and outdoor seamless positioning[D]. Shanghai: Shanghai Jiao Tong University, 2017., articleTitle=Research on context awareness in indoor and outdoor seamless positioning, refAbstract=null), Reference(id=1244336226308829354, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=2014, volume=11, issue=2, pageStart=1, pageEnd=29, url=null, language=null, rfNumber=[15], rfOrder=20, authorNames=Li M, Zhou P, Zheng Y, journalName=ACM Transactions on Sensor Networks (TOSN), refType=null, unstructuredReference=Li M, Zhou P, Zheng Y, et al. IODetector: A generic service for indoor/outdoor detection[J]. ACM Transactions on Sensor Networks (TOSN), 2014, 11(2): 1-29., articleTitle=IODetector: A generic service for indoor/outdoor detection, refAbstract=null), Reference(id=1244336226388521133, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=2019, volume=19, issue=4, pageStart=786, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=21, authorNames=Zhu Y, Luo H, Wang Q, journalName=Sensors, refType=null, unstructuredReference=Zhu Y, Luo H, Wang Q, et al. A fast indoor/outdoor transition detection algorithm based on machine learning[J]. Sensors, 2019, 19(4): 786., articleTitle=A fast indoor/outdoor transition detection algorithm based on machine learning, refAbstract=null), Reference(id=1244336226514350256, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=2024, volume=44, issue=06, pageStart=1559, pageEnd=1565, url=null, language=null, rfNumber=[17], rfOrder=22, authorNames=曾庆栋, 陈光辉, 李文鑫, journalName=光谱学与光谱分析, refType=null, unstructuredReference=曾庆栋, 陈光辉, 李文鑫, . 基于粒子群-支持向量机算法的激光诱导击穿光谱钢铁快速检测与分类[J]. 光谱学与光谱分析, 2024, 44(06): 1559-1565., articleTitle=基于粒子群-支持向量机算法的激光诱导击穿光谱钢铁快速检测与分类, refAbstract=null), Reference(id=1244336226627596467, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=2024, volume=44, issue=06, pageStart=1559, pageEnd=1565, url=null, language=null, rfNumber=[17], rfOrder=23, authorNames=Zeng Q, Chen G, Li W, journalName=Spectroscopy and Spectral Analysis, refType=null, unstructuredReference=Zeng Q, Chen G, Li W, et al. Classification of special steel based on LIBS combined with particle swarm optimization and support vector machine[J]. Spectroscopy and Spectral Analysis, 2024, 44(06): 1559-1565., articleTitle=Classification of special steel based on LIBS combined with particle swarm optimization and support vector machine, refAbstract=null), Reference(id=1244336226753425592, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, doi=null, pmid=null, pmcid=null, year=2011, volume=74, issue=17, pageStart=3114, pageEnd=3124, url=null, language=null, rfNumber=[18], rfOrder=24, authorNames=Xu J, journalName=Neurocomputing, refType=null, unstructuredReference=Xu J. An extended one-versus-rest support vector machine for multi-label classification[J]. Neurocomputing, 2011, 74(17): 3114-3124., articleTitle=An extended one-versus-rest support vector machine for multi-label classification, refAbstract=null)], funds=[Fund(id=1244336222349406289, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, awardId=202501AS070115, language=CN, fundingSource=云南省基础研究计划项目(202501AS070115), fundOrder=null, country=null), Fund(id=1244336222433292372, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, awardId=202402AE090009, language=CN, fundingSource=云南省重大科技专项计划(202402AE090009), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1244336215391056746, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, xref=null, ext=[AuthorCompanyExt(id=1244336215395251051, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, companyId=1244336215391056746, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Faculty of Transportation Engineering, Kunming University of Science and Technology, Kunming 650500, China), AuthorCompanyExt(id=1244336215403639660, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, companyId=1244336215391056746, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=昆明理工大学 交通工程学院,昆明 650500)])], figs=[ArticleFig(id=1244336217567900620, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=EN, label=Fig.1, caption=Indoor-outdoor seamless localization architecture based on region recognition, figureFileSmall=KieCvQi2F8vSqje8piYc1w==, figureFileBig=d/0wlZhM7hts0xTSrxHx3A==, tableContent=null), ArticleFig(id=1244336217752450001, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=CN, label=图1, caption=基于区域识别的室内外无缝定位架构, figureFileSmall=KieCvQi2F8vSqje8piYc1w==, figureFileBig=d/0wlZhM7hts0xTSrxHx3A==, tableContent=null), ArticleFig(id=1244336218004108251, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=EN, label=Fig.2, caption=SVM binary classification, figureFileSmall=T4dpVtLKY9S1yhwGsD0cZA==, figureFileBig=nP1GzJcZ1irsuNX/Ch+ThQ==, tableContent=null), ArticleFig(id=1244336218100577247, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=CN, label=图2, caption=SVM二分类, figureFileSmall=T4dpVtLKY9S1yhwGsD0cZA==, figureFileBig=nP1GzJcZ1irsuNX/Ch+ThQ==, tableContent=null), ArticleFig(id=1244336219614720996, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=EN, label=Fig.3, caption=Hidden Markov model process, figureFileSmall=iPizWKR8FSYPHGTMQ1uPRw==, figureFileBig=qDzwm3bci37mrjUNiEkoLQ==, tableContent=null), ArticleFig(id=1244336219702801382, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=CN, label=图3, caption=HMM过程, figureFileSmall=iPizWKR8FSYPHGTMQ1uPRw==, figureFileBig=qDzwm3bci37mrjUNiEkoLQ==, tableContent=null), ArticleFig(id=1244336219782493161, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=EN, label=Fig.4, caption=Experimental platform of unmanned vehicle, figureFileSmall=Str79aYFltMW2GNbqUYGwg==, figureFileBig=+BYdCaweesfO+6gdAehO4A==, tableContent=null), ArticleFig(id=1244336219849602029, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=CN, label=图4, caption=无人车辆实验平台, figureFileSmall=Str79aYFltMW2GNbqUYGwg==, figureFileBig=+BYdCaweesfO+6gdAehO4A==, tableContent=null), ArticleFig(id=1244336219937682418, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=EN, label=Fig.5, caption=Real experimental scene, figureFileSmall=Xitwfl2NknwtGvsSM1MkXA==, figureFileBig=gZtv4CbRoJffwqono9vFYw==, tableContent=null), ArticleFig(id=1244336220017374197, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=CN, label=图5, caption=真实实验场景, figureFileSmall=Xitwfl2NknwtGvsSM1MkXA==, figureFileBig=gZtv4CbRoJffwqono9vFYw==, tableContent=null), ArticleFig(id=1244336220189340666, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=EN, label=Fig.6, caption=Region recognition results, figureFileSmall=0TWdc93DcdBCZTRNa8GLSw==, figureFileBig=SaxVy4LES9G3oIcqhWmRGQ==, tableContent=null), ArticleFig(id=1244336220264838143, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=CN, label=图6, caption=区域识别结果, figureFileSmall=0TWdc93DcdBCZTRNa8GLSw==, figureFileBig=SaxVy4LES9G3oIcqhWmRGQ==, tableContent=null), ArticleFig(id=1244336220336140289, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=EN, label=Fig.7, caption=Positioning trajectories of the single-model and the proposed algorithm, figureFileSmall=27mAY19V8UorAGKbGBrqQA==, figureFileBig=rA1ZarG/4ezNaCrN33s91A==, tableContent=null), ArticleFig(id=1244336220411637765, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=CN, label=图7, caption=单一模型与本文算法的定位轨迹, figureFileSmall=27mAY19V8UorAGKbGBrqQA==, figureFileBig=rA1ZarG/4ezNaCrN33s91A==, tableContent=null), ArticleFig(id=1244336220503912457, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=EN, label=Fig.8, caption=Error variation curves of the single-model, figureFileSmall=p68YjQ+SfGnRerFHEs1O8w==, figureFileBig=e44KK95x1UQYrYIAWVbWjA==, tableContent=null), ArticleFig(id=1244336220575215629, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=CN, label=图8, caption=单一模型误差变化曲线, figureFileSmall=p68YjQ+SfGnRerFHEs1O8w==, figureFileBig=e44KK95x1UQYrYIAWVbWjA==, tableContent=null), ArticleFig(id=1244336220650713104, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=EN, label=Fig.9, caption=Positioning trajectories of same-type seamless positioning algorithms, figureFileSmall=EaW6O9TgkgW3kQk+3ob++A==, figureFileBig=vBZEmm6x/yTm0cZYyMDavg==, tableContent=null), ArticleFig(id=1244336220726210579, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=CN, label=图9, caption=同类型无缝定位算法定位轨迹, figureFileSmall=EaW6O9TgkgW3kQk+3ob++A==, figureFileBig=vBZEmm6x/yTm0cZYyMDavg==, tableContent=null), ArticleFig(id=1244336220818485271, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=EN, label=Fig.10, caption=Error variation curves of Same-Type Seamless Positioning Algorithms, figureFileSmall=LMG7v2AsZp3Xjyl1Ho6KIQ==, figureFileBig=UtrTSMDtsUC7zo8qcF95UA==, tableContent=null), ArticleFig(id=1244336220906565658, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=CN, label=图10, caption=同类型无缝定位算法误差变化曲线, figureFileSmall=LMG7v2AsZp3Xjyl1Ho6KIQ==, figureFileBig=UtrTSMDtsUC7zo8qcF95UA==, tableContent=null), ArticleFig(id=1244336220986257437, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=EN, label=Tab.1, caption=

Set of region states

, figureFileSmall=null, figureFileBig=null, tableContent=
S状态列表区域标签
室外区域s11
室内外过渡区域s22
室内区域s33
), ArticleFig(id=1244336221095309345, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=CN, label=表1, caption=

区域状态集合

, figureFileSmall=null, figureFileBig=null, tableContent=
S状态列表区域标签
室外区域s11
室内外过渡区域s22
室内区域s33
), ArticleFig(id=1244336221204361253, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=EN, label=Tab.2, caption=

Comparison of classification accuracies for three regions

, figureFileSmall=null, figureFileBig=null, tableContent=
分类方式准确度分类方式准确度
PSO-SVM95.96%联合分类98.09%
HMM88.56%--
), ArticleFig(id=1244336221296635946, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=CN, label=表2, caption=

三种区域分类精度对比

, figureFileSmall=null, figureFileBig=null, tableContent=
分类方式准确度分类方式准确度
PSO-SVM95.96%联合分类98.09%
HMM88.56%--
), ArticleFig(id=1244336221384716334, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=EN, label=Tab.3, caption=

Mean localization errors of the single-model

, figureFileSmall=null, figureFileBig=null, tableContent=
误差均值室外/m室内外过渡/m室内/m总体/m
GNSS1.941.716.634.16
UWB5.883.100.542.85
ODR1.901.705.93.74
I-OTR1.661.161.321.41
IDR5.793.090.442.82
本文算法1.940.910.531.08
), ArticleFig(id=1244336221476991027, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=CN, label=表3, caption=

单一模型的定位误差均值

, figureFileSmall=null, figureFileBig=null, tableContent=
误差均值室外/m室内外过渡/m室内/m总体/m
GNSS1.941.716.634.16
UWB5.883.100.542.85
ODR1.901.705.93.74
I-OTR1.661.161.321.41
IDR5.793.090.442.82
本文算法1.940.910.531.08
), ArticleFig(id=1244336221669929014, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=EN, label=Tab.4, caption=

Mean positioning error of same-type seamless positioning algorithms (Unit: m)

, figureFileSmall=null, figureFileBig=null, tableContent=
误差均值室外室内外过渡室内总体
FKF1.791.522.181.92
IMM1.661.041.331.39
本文算法1.940.910.531.08
), ArticleFig(id=1244336221799952443, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=CN, label=表4, caption=

同类型无缝定位算法定位误差均值(单位:米)

, figureFileSmall=null, figureFileBig=null, tableContent=
误差均值室外室内外过渡室内总体
FKF1.791.522.181.92
IMM1.661.041.331.39
本文算法1.940.910.531.08
), ArticleFig(id=1244336221925781568, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=EN, label=Tab.5, caption=

Root mean square errors (RMSE) in the X-axis of same-type seamless positioning algorithms (Unit: m)

, figureFileSmall=null, figureFileBig=null, tableContent=
均方根误差室外室内外过渡室内总体
FKF1.221.290.831.05
IMM1.241.220.530.91
本文算法1.231.360.260.80
), ArticleFig(id=1244336222022250563, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=CN, label=表5, caption=

同类型无缝定位算法X轴方向均方根误差(单位:米)

, figureFileSmall=null, figureFileBig=null, tableContent=
均方根误差室外室内外过渡室内总体
FKF1.221.290.831.05
IMM1.241.220.530.91
本文算法1.231.360.260.80
), ArticleFig(id=1244336222118719559, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=EN, label=Tab.6, caption=

Root mean square errors (RMSE) in the Y-axis of same-type seamless positioning algorithms (Unit: m)

, figureFileSmall=null, figureFileBig=null, tableContent=
均方根误差室外室内外过渡室内总体
FKF1.721.802.181.87
IMM1.500.891.191.16
本文算法1.280.490.420.88
), ArticleFig(id=1244336222219382859, tenantId=1146029695717560320, journalId=1244323073571209252, articleId=1244336190690800003, language=CN, label=表6, caption=

同类型无缝定位算法Y轴方向误差均值(单位:米)

, figureFileSmall=null, figureFileBig=null, tableContent=
均方根误差室外室内外过渡室内总体
FKF1.721.802.181.87
IMM1.500.891.191.16
本文算法1.280.490.420.88
)], attaches=null, journal=Journal(id=1244322988720439331, delFlag=0, nameCn=中国惯性技术学报, nameEn=Journal of Chinese Inertial Technology, nameHistory1=null, nameHistory2=null, issn=1005-6734, eissn=null, cn=12-1222/O3, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=7nvD63MqplRkIkJ92cFBSg==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Chinese Inertial Technology, journalRemark=null, publicationField=null, createdTime=1774599318917, updatedTime=1774599470892, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=J, firstLetterEn=J, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=7nvD63MqplRkIkJ92cFBSg==, picEn=Hm2jABG2m8rYJTbG/YkinA==, jcr=null, cjcr=null, exts=[JournalExt(id=1244323626233741507, language=CN, name=中国惯性技术学报, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1774599470909, updatedTime=1774599470909, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.zggxjsxb.com/journalx_zggxjs/authorLogOn.action, submissionEditorUrl=http://www.zggxjsxb.com/journalx_zggxjs/editorLogOn.action, submissionReviewUrl=http://www.zggxjsxb.com/journalx_zggxjs/expertLogOn.action, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1244323626288267460, language=EN, name=Journal of Chinese Inertial 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=1774599470922, updatedTime=1774599470922, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.zggxjsxb.com/journalx_zggxjs/authorLogOn.action, submissionEditorUrl=http://www.zggxjsxb.com/journalx_zggxjs/editorLogOn.action, submissionReviewUrl=http://www.zggxjsxb.com/journalx_zggxjs/expertLogOn.action, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1244323073571209252, websiteList=[Website(id=1244323687596409029, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1244323073571209252, 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/zggxjsxb/CN, language=CN, createTime=1774599485546, createBy=18614031015, updateTime=1774599505954, updateBy=18614031015, name=中国惯性技术学报-中文, tplId=1146099689490845704, title=中国惯性技术学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1244325136388698877, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244323687596409029, code=articleTextType, value=kx, createTime=1774599830958, updateTime=1774599830958, creator=18614031015, updator=18614031015), WebsiteProps(id=1244325136342561530, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244323687596409029, code=banner, value=null, createTime=1774599830947, updateTime=1774599830947, creator=18614031015, updator=18614031015), WebsiteProps(id=1244325136443224832, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244323687596409029, code=grayFlag, value=0, createTime=1774599830971, updateTime=1774599830971, creator=18614031015, updator=18614031015), WebsiteProps(id=1244325136313201401, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244323687596409029, code=logo, value=https://castjournals.cast.org.cn/joweb/zggxjsxb/CN/file/pic?fileId=ouj3QpSM21aiIQie73dEiw==, createTime=1774599830940, updateTime=1774599830940, creator=18614031015, updator=18614031015), WebsiteProps(id=1244325136468390658, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244323687596409029, code=minRunFlag, value=0, createTime=1774599830977, updateTime=1774599830977, creator=18614031015, updator=18614031015), WebsiteProps(id=1244325136371921660, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244323687596409029, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zggxjsxb/CN/file/pic, createTime=1774599830954, updateTime=1774599830954, creator=18614031015, updator=18614031015), WebsiteProps(id=1244325136460002049, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244323687596409029, code=silenceFlag, value=0, createTime=1774599830975, updateTime=1774599830975, creator=18614031015, updator=18614031015), WebsiteProps(id=1244325136355144443, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244323687596409029, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1774599830950, updateTime=1774599830950, creator=18614031015, updator=18614031015), WebsiteProps(id=1244325136401281790, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244323687596409029, code=themeColor, value=null, createTime=1774599830961, updateTime=1774599830961, creator=18614031015, updator=18614031015), WebsiteProps(id=1244325136409670399, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244323687596409029, code=themeStyle, value=null, createTime=1774599830964, updateTime=1774599830964, creator=18614031015, updator=18614031015)]), Website(id=1244323687697072327, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1244323073571209252, 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/zggxjsxb/EN, language=EN, createTime=1774599485564, createBy=18614031015, updateTime=1774599521174, updateBy=18614031015, name=中国惯性技术学报-英文, tplId=1146101810881728533, title=Journal of Chinese Inertial Technology, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1244325165878850311, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244323687697072327, code=articleTextType, value=kx, createTime=1774599837989, updateTime=1774599837989, creator=18614031015, updator=18614031015), WebsiteProps(id=1244325165849490180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244323687697072327, code=banner, value=null, createTime=1774599837982, updateTime=1774599837982, creator=18614031015, updator=18614031015), WebsiteProps(id=1244325165899821834, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244323687697072327, code=grayFlag, value=0, createTime=1774599837994, updateTime=1774599837994, creator=18614031015, updator=18614031015), WebsiteProps(id=1244325165841101571, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244323687697072327, code=logo, value=https://castjournals.cast.org.cn/joweb/zggxjsxb/EN/file/pic?fileId=ouj3QpSM21aiIQie73dEiw==, createTime=1774599837980, updateTime=1774599837980, creator=18614031015, updator=18614031015), WebsiteProps(id=1244325165916599052, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244323687697072327, code=minRunFlag, value=0, createTime=1774599837998, updateTime=1774599837998, creator=18614031015, updator=18614031015), WebsiteProps(id=1244325165870461702, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244323687697072327, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zggxjsxb/EN/file/pic, createTime=1774599837987, updateTime=1774599837987, creator=18614031015, updator=18614031015), WebsiteProps(id=1244325165908210443, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244323687697072327, code=silenceFlag, value=0, createTime=1774599837996, updateTime=1774599837996, creator=18614031015, updator=18614031015), WebsiteProps(id=1244325165862073093, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244323687697072327, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1774599837985, updateTime=1774599837985, creator=18614031015, updator=18614031015), WebsiteProps(id=1244325165887238920, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244323687697072327, code=themeColor, value=null, createTime=1774599837991, updateTime=1774599837991, creator=18614031015, updator=18614031015), WebsiteProps(id=1244325165895627529, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244323687697072327, code=themeStyle, value=null, createTime=1774599837993, updateTime=1774599837993, creator=18614031015, updator=18614031015)])], journalTitle=中国惯性技术学报, weixinUrl=null, journalUrl=http://www.zggxjsxb.com/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Chinese Inertial Technology, journalPhotoCn=7nvD63MqplRkIkJ92cFBSg==, journalPhotoEn=Hm2jABG2m8rYJTbG/YkinA==, journalFirstLetter=J, 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/zggxjsxb/CN/10.13695/j.cnki.12-1222/o3.2025.10.008, detailUrlEn=https://castjournals.cast.org.cn/joweb/zggxjsxb/EN/10.13695/j.cnki.12-1222/o3.2025.10.008, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zggxjsxb/CN/PDF/10.13695/j.cnki.12-1222/o3.2025.10.008, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zggxjsxb/EN/PDF/10.13695/j.cnki.12-1222/o3.2025.10.008, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
无人车辆室内外无缝定位的区域识别方法
收藏切换
PDF下载
杨秀建 , 杨义兴 , 张生斌
中国惯性技术学报 | 组合导航技术 2025,33(10): 1016-1025
收起
收藏切换
中国惯性技术学报 | 组合导航技术 2025, 33(10): 1016-1025
无人车辆室内外无缝定位的区域识别方法
全屏
杨秀建, 杨义兴, 张生斌
作者信息
  • 昆明理工大学 交通工程学院,昆明 650500
  • 杨秀建(1980—),男,教授,博士生导师,从事车辆动力学控制、智能车辆技术研究。

通讯作者:

张生斌(1981—),男,讲师,博士,从事车辆测试技术研究。
A regional recognition method for seamless indoor-outdoor localization of unmanned vehicles
Xiujian YANG, Yixing YANG, Shengbin ZHANG
Affiliations
  • Faculty of Transportation Engineering, Kunming University of Science and Technology, Kunming 650500, China
出版时间: 2025-10-30 doi: 10.13695/j.cnki.12-1222/o3.2025.10.008
文章导航
收藏切换

针对无人车辆室内外无缝定位过程中难以准确判定车辆所处区域的问题,提出了一种无人车辆室内外无缝定位的区域识别方法。首先,设计基于粒子群优化的支持向量机(PSO-SVM)与隐马尔可夫模型(HMM)的联合预测模型,并利用传感器获取环境特征数据作为模型输入,得到区域识别结果;然后,引入三种环境模型描述车辆所处环境,根据区域识别结果选择相应的量测信息;最后,利用区域切换概率更新交互式多模型算法(IMM)中三个环境子模型的切换概率,从而提高无人车辆的室内外无缝定位环境区域识别的准确性和定位精度。实车实验结果表明,联合识别方法在区域识别中的准确性为98.09%,相较于单独使用PSO-SVM或HMM分别提升了2.13%和9.53%。进一步实验表明,与传统的联邦卡尔曼滤波算法(FKF)以及IMM算法相比,采用所提区域识别方法的平均定位精度分别提高了43.75%和22.30%。

无人车辆  /  区域识别  /  多源融合  /  交互多模型算法  /  室内外无缝定位

To address the challenge of accurately determining the environmental region of unmanned vehicles during seamless indoor-outdoor positioning, a regional recognition method for seamless indoor-outdoor localization is proposed. Firstly, a joint prediction model integrating particle swarm optimization-support vector machine (PSO-SVM) and hidden Markov model (HMM) is designed. Environmental feature data acquired by sensors serve as model inputs to generate regional recognition results. Secondly, three environmental models are introduced to describe the vehicle's operational environment, with corresponding measurement information selected based on the regional recognition outcomes. Finally, the regional transition probabilities are utilized to update the switching probabilities of the three environmental sub-models in the interactive multiple model (IMM) algorithm, thereby enhancing the accuracy of environmental region recognition and positioning precision for seamless indoor-outdoor navigation. The results of real-vehicle experiment show that the proposed joint recognition method achieves an accuracy of 98.09% in region recognition, representing improvements of 2.13% and 9.53% compared to using PSO-SVM or HMM alone. Further experiments indicate that the proposed seamless positioning method enhances the average positioning accuracy by 43.75% and 22.30% compared to the traditional federated Kalman filter (FKF) algorithm and IMM algorithm, respectively.

unmanned vehicles  /  regional recognition  /  multi-source fusion  /  interactive multiple model algorithm  /  seamless indoor-outdoor positioning
杨秀建, 杨义兴, 张生斌. 无人车辆室内外无缝定位的区域识别方法. 中国惯性技术学报, 2025 , 33 (10) : 1016 -1025 . DOI: 10.13695/j.cnki.12-1222/o3.2025.10.008
Xiujian YANG, Yixing YANG, Shengbin ZHANG. A regional recognition method for seamless indoor-outdoor localization of unmanned vehicles[J]. Journal of Chinese Inertial Technology, 2025 , 33 (10) : 1016 -1025 . DOI: 10.13695/j.cnki.12-1222/o3.2025.10.008
近年来,无人驾驶技术迅猛发展,其中,高精度的车辆定位是无人驾驶规划环节的关键所在[1]。在城市复杂场景下,全球导航卫星系统(Global Navigation Satellite System,GNSS)易受建筑物干扰,从而导致信号衰减,造成定位性能显著下降,甚至无法提供定位服务[2]。此外,在GNSS信号受阻情况下,仅依靠车辆搭载的单一传感器难以实现精准定位[3]。惯性导航系统(Inertial Navigation System,INS)可以提供相对姿态、速度以及位置估计,通过GNSS/INS组合导航系统可以有效弥补GNSS短期失效的问题,提升整体室外定位精度[4-6]。然而,在室内环境下,GNSS/INS组合导航系统的定位能力有限,因此将超宽带(Ultra Wide Band,UWB)与GNSS和惯性测量单元(Inertial Measurement Unit,IMU)结合,形成GNSS/IMU/UWB定位系统[7],可以有效解决室内外过渡区域及室内区域定位问题,实现无人车辆在城市复杂环境无缝定位。
室内外无缝定位技术利用不同的定位算法和传感器组合,旨在满足多种情况下对高精度定位的要求[8]。为了应对这一具有挑战性的任务,Tao Feng等人[9]提出了CrowdLOC-S框架,该框架通过综合运用众包WiFi指纹、GNSS和低成本传感器,结合扩展卡尔曼滤波(Extended Kalman Filter,EKF)多源融合模型,实现了稳健的室内外无缝定位,但其整体框架的实现相对复杂,涉及多种技术和算法,难以在实际应用中进行优化和平衡。Xingxing Li等人[10]提出了一种紧密耦合的PPP/INS/UWB集成系统,该系统通过融合多种测量值,并采用UWB两步加权模型和运动约束,实现了高精度的室内外无缝定位,并且采用UWB信号辅助识别室内外区域(Indoor-Outdoor,IO),但由于UWB通讯范围有限,尤其是当其受到非视距(Non Line of Sight,NLOS)干扰时,通信范围会迅速减少,无法作为室内外环境区分的准确依据。张威奕等人[11]引入无迹卡尔曼滤波来改进GPS/蜂窝网无缝定位算法,以克服现有算法的不足,提高其定位精度和鲁棒性。Linghan Yao等人[12]则提出了一种基于联邦滤波的定位算法,以解决现有研究中处理非视距误差和粗差方面的局限性,从而提高室内外无缝定位的精度和可靠性。张容阁[13]通过比较交互式多模型算法(Interacting Multiple Model,IMM)与联邦卡尔曼滤波算法(Federated Kalman Filter,FKF)在噪声和模型不匹配条件下的精度测试结果,验证了在室内外无缝定位中IMM算法的优势。
上述研究人员在室内外定位算法方面取得了重要进展,但要构建高鲁棒性的室内外无缝定位系统,还需解决运动区域的准确识别问题[9]。针对此问题,王琳[14]利用GNSS特征信息结合K近邻算法,将运动区域划分为室外与室内场景,验证了场景识别的可行性,但是仅依靠单一的K近邻算法并不足以准确的进行区域识别。Li M等人[15]通过隐马尔可夫模型(Hidden Markov Model,HMM),结合光接收器、蜂窝网络和磁力计,开发了I-O识别算法,实验中达到了90%以上的识别准确率,但是光信号并非总是可用,并且只通过光探测器难以明确区分室外和半室外环境。Zhu Y,Luo H等人[16]基于接收到GNSS信号的空间几何分布,提出了一种针对室内外过渡快速IO检测方法,但未涉及室内或室外环境内更细致的定位或状态检测。
综合以上研究,本文提出了一种粒子群优化支持向量机(Particle Swarm Optimization-Support Vector Machine,PSO-SVM)算法,旨在提升无人车辆的定位精度。将车辆运动区域划分为室外区域模型(Outdoor Region,ODR)、室内外过渡区域模型(Indoor-Outdoor Transition Region,I-OTR)与室内区域模型(Indoor Region,IDR)三类,使用低成本GNSS(Low-Cost GNSS,LC-GNSS)/IMU/UWB构建室内外无缝定位框架,通过PSO-SVM与HMM相结合对车辆运动区域进行环境识别,并根据识别结果选择相应量测作为IMM算法输入。同时,根据区域识别结果更新子模型切换概率,提升定位精度。最后通过实车实验对本文所述方法进行评价验证。
图1所示,本文提出的无缝定位框架核心包含区域识别算法与多模型融合策略两部分。其中环境识别模块采用PSO-SVM与HMM结合的策略,以LC-GNSS的可见卫星数与信噪比均值作为输入,并通过粒子群算法(Particle Swarm Optimization,PSO)对SVM的惩罚参数与核函数参数进行寻优,实现对三类区域的初步识别。考虑到整体定位的时序性,利用HMM对运动区域进行动态识别,并通过维特比算法(Viterbi Algorithm,VA)找到隐藏状态序列。最后,将两种识别结果加权融合,得到最终的联合识别结果,同时将HMM过程中得到的区域转移概率输入至后续的IMM步骤中,优化IMM的子模型切换概率。在多模型融合策略中定义三种融合子模型为EKF-ODR、EKF-I-OTR以及EKF-IDR对车辆定位进行描述,使用EKF作为子模型滤波器,并根据前序得出的区域识别结果与区域转移概率调整IMM算法中子模型量测信息以及子模型切换概率;最后,将三种子模型输入至IMM算法中进行加权融合,输出最终预测的车辆定位结果。
支持向量机(Support Vector Machine,SVM)最初由Vapink等人于20世纪90年代提出[17],如图2所示SVM本身针对的是二分类问题,但在本文中分类目标为多分类,使用一对余类法(One Versus Rest,OVR)[18]将多分类问题拆解为k个二分类问题进行聚类。
将LC-GNSS的总可见卫星数(Total Number of Visible Satellites,TNVS)与信噪比均值(Mean Signal-to-Noise Ratio,Mean SNR)作为特征值样本xi,设定包含n个训练样本的训练数据集为:
其中,表示m阶的特征向量(在本文中m=2),是对应的区域类别标签,其中yi=1代表室外区域,yi=2代表室内外过渡区域,yi=3代表室内区域。由于本文所针对的分类对象共有三类,因此,对于第k个分类器,将属于第k个分类器的样本定义为正类,其余样本定义为负类。则重新定义第k个分类器的标签为:
对于第k个SVM分类器,模型训练目标是找到超平面使得超平面到两类样本点的间隔最大化,对于任意样本点到超平面的距离可以表示为:
式(3)中wk表示在第k个SVM分类器中超平面的法向量,bk代表截距,间隔表示为:,则需要优化的目标函数表示为:
其中,C>0是惩罚参数,用于控制对错误分类的惩罚程度。是松弛变量,用于处理样本线性不可分的情况。
引入拉格朗日乘子,构造拉格朗日函数:
对优化目标求偏导并令其为零,得:
将式(6)~式(9)的结果与式(5)联立得到对偶问题的解:
求解上述对偶问题,得到最优的ak)*,进而得到wkbk
对于待测样本x,分别计算k=1,2,3时的决策函数值:
由于进行分类训练时,数据不一定都是线性可分的,因此需要引入核参数将训练集数据映射至高维空间中,则式(10)更新为:
其中,jxi)为样本xi在高维空间中的映射,Kjxi),jxj))为SVM的核函数。
在PSO算法中,引入核参数g与惩罚因子C作为粒子的位置向量x=(Cg)进行优化,从而获得最优参数估计,其中,g>0,C>0。
待测样本分类为使fkx)的值为最大的类别,并将最终分类结果定义为:
从时域角度分析,无人车辆在室内外运动是一个连续的过程。当前所处的环境区域与前一时刻的状态有关,而与先前位置无关,并且会直接影响下一时刻的状态。与此同时,在室内外区域判断过程中,我们只能获取到LC-GNSS源的特征数据,而无法直接观测到无人车辆所处的环境区域状态。进一步地,LC-GNSS源的特征数据仅与当前所处的环境有关。因此,本文建立了基于室内外区域识别的隐马尔可夫模型l=(SOAB,π),HMM过程如图3所示。
其中S表示区域状态集合,其具体取值如表1所示,包含了三种区域状态与三类区域标签。
在构建的HMM模型中,O={o1o2}表示由TNVS与Mean SNR构成的观测向量;A=[aij]表示从状态si到状态sj的概率,其中aij=Pqt+1=sj|qt=si),对于任意的ij∈{1,2,3}满足B=[biot)]表示在隐藏状态为sj时观测到序列ot的概率,其中bjot)=Pot|qt=sj);p={pi}表示初始时刻处于状态si的概率,其中pi=Pq1=si)。
HMM模型训练目标是通过给定的观测序列O及其对应的状态序列S,估计HMM的ABp的最佳参数。其中,
本文所涉及的问题属于HMM解码问题,通过VA找到测试集最有可能的隐藏状态序列为:
其中,代表路径回溯指针。通过式(16)得到测试集的隐藏状态序列为:
单一的分类预测结果在不同环境区域内的精度并非最优,因此对PSO-SVM的分类结果与HMM的分类结果进行联合预测,并使用联合预测的结果作为最终的分类结果。
设验证集有N个样本,真实类别标签为:
则PSO-SVM对验证集的分类结果为:
HMM对验证集的分类结果为:
在区域k中定义NkY中类别为k的总真实样本数,Nsk为PSO-SVM正确分类的样本个数,Nhk为HMM正确分类的样本个数,PSK代表PSO-SVM的分类精度,PHK代表HMM的分类精度,则:
总精确度记为:
在联合分类预测中,定义分别表示在区域k中,PSO-SVM的分类预测结果为i,HMM分类预测结果为j时(ij∈{1,2,3})两种分类器的权重系数,其中PSO-SVM权重系数表示为:
同理,HMM权重系数表示为:
最终输出的联合分类结果记为:
本文将车辆的运动过程分为了室外区域、室内外过渡区域以及室内区域三种,对应有ODR、I-OTR以及IDR三种模型,即存在三个状态转移方程。利用IMM将三种模型估计出的结果加权融合从而得到车辆的预测轨迹,其中,第j个模型表示的目标状态方程为:
量测方程为:
式(30)中,f(·)和h(·)分别表示k-1时刻的非线性状态方程函数和量测方程函数;Wk-1)和Vk-1)分别表示k-1时刻的状态噪声和量测噪声。
在IMM算法中模型转移概率矩阵定义为:
其中pij表示目标由子模型i切换至子模型j的概率。区域模型的预测概率为:
其中,uik-1)表示在t-1时刻可能为区域模型i的概率且r=3。
模型i到模型j的混合概率:
模型j的混合状态估计和协方差估计:
模型j的协方差估计:
其中,Pik-1|k-1)分别为模型i的状态预测和协方差。
根据式(28)得到联合分类的区域识别结果,设区域转移矩阵为CT=[cij]3´3,其中cij表示从区域转移到区域的转移次数:若,则cij=cij+1,其中,表示t时刻对应的分类标签。设表示从区域出发的总转移次数,区域切换概率矩阵表示为:
其中mij表示为:
由式(31)与式(36)联立更新模型转移概率Pm
其中,分别表示区域切换概率的权重系数与模型转移概率的权重系数。
因此,式(32)、式(33)更新为:
将更新后的结果与量测Zj一同输入IMM算法的后续步骤中,得到最终的交互结果。
本文通过图4所示无人车辆实验平台,对提出的室内外无缝定位方法进行了系统分析和评价。评价指标包括区域识别准确度以及采样点误差均值。本实验平台基于Ubuntu 20.04和ROS Noetic系统环境,配备了由北京星宇达公司研制的XW-GI类GNSS接收机,用于输出RTK真实轨迹。LC-GNSS产品则采用移远通信的LC29H-E系列GNSS模块。UWB定位基站及标签使用了DecaWave公司研制的DW1000定位芯片。
本文在室外区域以及室内外过渡区域中使用千寻公司提供的RTK轨迹作为真实路径,在室内区域中使用预先规定好的路径作为真实路径。通过中海达ZTS-420系列彩屏全站仪对UWB基站进行位置标定,UWB定位标签布置于车辆的几何中心,LC-GNSS接收机则布置于车辆几何中心的两侧。
选择包含室内外环境的典型实验场地如图5所示,红色实线表示室外及室内外过渡区域的无人车辆真实运动路径,蓝色虚线表示室内区域的无人车辆真实运动路径,蓝色圆表示起点,红色圆表示终点。建立X轴方向指向车辆运动方向的右向,Y轴方向指向车辆运动方向前向的运动坐标系,将LC-GNSS、UWB以及IMU数据转换到该基准坐标系下,描述无人车辆的室内外无缝定位过程。
图6展示了本文所建立的PSO-SVM分类预测模型、HMM分类预测模型以及联合分类预测模型的区域分类结果,其中标签1代表室外区域、标签2代表室内外过渡区域,标签3则代表室内区域。区域识别结果显示,在实验车辆的实际行驶轨迹中,室外区域占比为34.3%,室内外过渡区域占比为19.1%,室内区域占比为46.6%。
图6中可以看出,HMM在由室外出发向其他区域转移时的预测结果准确度更高,但是由室内出发向半室外区域转移时会出现预测偏差。因为HMM模型在处理时序数据时能够有效捕捉到室内外环境变化的动态特征,但是由于从室内环境向室外环境转移过程中,传感器特征信号源变化更新不及时,并且HMM依赖于前序时间下的环境特征,这导致了从室内环境出发时HMM预测的滞后性;PSO-SVM在室外及室内外过渡区域的预测准确度更高,但是从室内外过渡环境向室内转移过程中会出现预测偏差。因为PSO优化算法能够有效提升SVM的参数选择,从而在环境边界区域提供更精确的分类结果,但是从半室外环境转移至室内环境的边界训练样本不充分,导致了边界模糊性,通过增加准确的训练样本可以有效降低PSO-SVM的分类误差;联合分类预测结合了两种方法的优点,在时间维度保留HMM的状态转移先验以抑制传感器噪声的短期干扰,在空间维度集成PSO-SVM的实时分类结果以修正状态转移矩阵的累积偏差,使得识别结果更贴合真实环境标签,并且该模型在不同区域中表现均衡,能够综合处理室内外环境变化时的区域分类问题,为无人车辆提供贴合真实环境标签的区域识别结果,有效支撑多场景无缝定位系统的环境决策。
三种区域预测模型的准确度如表2所示,对比真实标签,PSO-SVM的总体分类准确度为95.96%,HMM的总体分类精度为88.56%,而联合预测的总体分类精度可以达到98.09%,可看出本文所建立联合分类模型的分类准确度明显优于单一分类模型,能够更有效地利用多种分类方法的优势,提高整体区域性能。
图7展示了在本文实验场地中,实验车辆从室内出发沿真实运动轨迹回到室内过程中本文所提算法与单一传感器、单一定位模型的定位轨迹对比。从图中可以看出,LC-GNSS在室内环境下无法执行定位,但随着实验车辆向室外运动,LC-GNSS逐渐恢复定位功能,定位误差逐渐减小;当实验车辆运动至室外边界并开始向室内环境转移时,LC-GNSS的误差逐渐增大,当实验车辆完全进入室内环境后,LC-GNSS信号丢失,无法继续提供定位功能。UWB在室内环境中可以提供有效的定位信息,但随着实验车辆由室内向室外运动,UWB的误差逐渐增大;当实验车辆离开室内环境边界时,UWB受到严重的NLOS干扰,使其定位误差迅速增加,当实验车辆完全行驶至室外环境并且离开UWB基站通讯范围后,UWB基站无法接收到标签信号,导致其在室外区域中无法执行定位功能;随着实验车辆由室外向室内运动,UWB的定位能力逐步恢复。
ODR定位模型依靠LC-GNSS提供量测,IMU提供状态,并通过EKF耦合。当LC-GNSS无法提供定位信息时,依靠IMU推算定位轨迹,提升定位精度。I-OTR定位模型依靠LC-GNSS与UWB同时提供量测,IMU提供状态信息,并通过EKF滤波耦合。由于LC-GNSS与UWB表现出相反的定位特性,在两者同时输出定位信息时根据权重信息动态选择量测,可以有效提升整体定位精度,尤其是在室内外过渡区域中,EKF-I-OTR表现出了较好的定位效果。IDR与EKF-ODR效果类似,当UWB无法提供定位信息时,通过IMU推算定位轨迹,提升定位精度。本文算法相较于单一传感器与单一定位模型,均表现出了更优秀的定位能力,尤其是在室内外过渡区域中输出的定位结果更贴合真实运动轨迹,表明了本文所提算法在无人车辆完整室内外运动过程中的优越性。
表3则展示了实验车辆采用不同定位方案的定位误差均值。从表3中可以看出,本文所提算法相比于单一传感器、单一定位模型的整体定位精度显著提升。具体而言,本文算法的整体定位平均误差最小,特别是在室内外过渡区域,本文算法的定位误差对比单一传感器分别减小了0.8 m和2.19 m,定位精度分别提升了46.78%和70.65%;对比单一定位模型(ODR、I-OTR、IDR),定位误差分别减小了0.79 m、0.25 m以及2.18 m,定位精度分别提升了46.47%、21.56%以及70.55%。此外,相较于其他定位方案,本文算法的总体误差仅为1.08 m,相较于I-OTR模型减小了0.33 m,定位精度提升了23.4%,在本次实验中本文算法实现了全面的定位精度提升。
图8展示了本文方法与单一传感器、单一定位模型在不同方向上的误差变化曲线。可以看出,本文方法通过实时环境特征感知与多模型协同优化,有效抑制了定位误差在多维度上的累积,尤其在室内外过渡区域的复杂场景中表现出更强的鲁棒性。实验结果从定量角度验证了所提方法通过多模态信息融合与模型互补策略,在无人车辆全场景无缝定位中实现了定位精度与可靠性的显著提升,为复杂环境下的高精度定位系统设计提供了重要的理论与实验支撑。
图9展示了在本文实验场地中,实验车辆从室内出发沿真实运动轨迹回到室内过程中,本文所提算法与传统IMM算法以及FKF算法的定位轨迹比较。从图中可以看出,在室内外过渡区域,IMM算法相较于FKF在定位轨迹贴合度上表现更优。这一差异的核心机制在于,IMM算法通过马尔可夫转移概率矩阵实现对动态环境和模型不确定性的自适应建模,而FKF算法依赖主滤波器预设阈值进行融合权重分配,其静态权重策略无法有效利用过渡区域的特征先验信息,导致子模型切换存在滞后性,进而影响定位精度。本文方法相较于传统IMM算法与FKF方法定位效果显著提升,其核心原因在于本文算法对实验车辆预先进行了区域识别,明确了车辆运动的区域边界,在实验车辆行驶至对应区域时可以正确选择子模型量测,其次,本文算法优化了子模型切换概率,增强了算法对非结构化场景的动态适应能力,使得本文算法在过渡区域的定位轨迹与真实运动路径吻合度更高,验证了所提方法在复杂环境下的鲁棒性和精确性。
表4展示了在不同区域中,实验车辆采用不同定位方案时的定位误差均值。从表4中可以看出,本文所提出的算法相比于FKF和IMM算法的整体定位精度均有显著提升。具体而言,本文算法的整体定位精度为1.08 m,相较于FKF与IMM,定位误差分别减小了0.84 m和0.31 m,整体定位精度分别提升了43.75%和22.30%,从量化指标中可以有效反映出本文算法在无缝定位过程中的优越性。
图10展示了FKF和IMM算法以及本文算法在X和Y方向上的误差变化曲线,通过对比可见,本文算法在全方向定位过程中展现出显著优势,其误差曲线波动幅度始终低于对比算法,且在动态场景中保持更小的偏差范围,呈现更优的收敛特性。有效验证了其在多维度定位任务中相较于传统无缝定位方案的鲁棒性与精确性提升。
表5呈现了实验车辆在不同区域采用各类定位方案时,在既定坐标系X轴方向上的均方根误差(RMSE)。
表5可见,本文提出的算法相较于FKF与IMM算法,在整体定位精度上实现了显著提升。具体而言,所提算法在X轴方向的整体RMSE为0.80 m,较FKF算法降低0.25 m、精度提升23.80%,较IMM算法降低0.11 m、精度提升12.09%。
表6呈现了实验车辆在不同区域采用各类定位方案时,在既定坐标系Y轴方向上的均方根误差(RMSE)。由表6可见,本文提出的算法相较于FKF与IMM算法,在整体定位精度上实现了显著提升。具体而言,所提算法在Y轴方向的整体RMSE为0.88 m,较FKF算法降低0.99 m、精度提升52.94%,较IMM算法降低0.28 m、精度提升24.14%。这些量化结果充分印证了本文算法在无缝定位场景中的优越性。
本文针对无人车辆室内外无缝定位过程中区域识别模糊导致的定位精度退化问题,提出了一种粒子群优化支持向量机(PSO-SVM)算法。通过实验验证得出,本文所述方法能够有效进行环境区域识别,弥补了LC-GNSS以及UWB在信号受阻情况下定位缺失的不足,同时优化了IMM算法中子模型切换概率,提升了整体融合定位精度。并且相较于单一传感器、单一定位模型、FKF算法以及传统的IMM算法,本文算法具有明显优势,通过本文算法输出的车辆定位精度在多维度下表现均衡,可以有效提高无人车辆室内外无缝定位的准确性和连续性,展现出优越、稳定的定位性能以及对复杂环境的良好适应性。
  • 云南省基础研究计划项目(202501AS070115)
  • 云南省重大科技专项计划(202402AE090009)
参考文献 引证文献
排序方式:
[1]
杨秀建, 敖鹏, 沈世全, . 面向复杂环境的UWB/LiDAR/IMU组合定位方法[J]. 中国惯性技术学报, 2024, 32(07): 654-662.
Yang X, Ao P, Shen S, et al. UWB/LiDAR/IMU combined localization method for complex environment[J]. Journal of Chinese Inertial Technology, 2024, 32(07): 654-662.
[2]
Zhao X, Tang P, Song Q, et al. Experimental analysis of multipath effects on GNSS positioning in urban canyon[C]//2021 IEEE 4th International Conference on Electronic Information and Communication Technology (ICEICT). China, August 18-20, 2021: 557-562.
[3]
李旭, 孔鑫, 刘锡祥, . 基于交互多模型距离平滑的UWB/IMU因子图组合导航方法[J]. 中国惯性技术学报, 2022, 30(3): 322-327.
Li X, Kong X, Liu X, et al. UWB/IMU factor graph integrated navigation method based on interactive multi-model distance smoothing[J]. Journal of Chinese Inertial Technology, 2022, 30(3): 322-327.
[4]
Fernandez-Prades C, Presti L, Falletti E. Satellite radio localization from GPS to GNSS and beyond: novel technologies and applications for civil mass market[J]. Proceedings of the IEEE, 2011, 99(11): 1882-1904.
[5]
Li Y, Chen R, Niu X, et al. Inertial sensing meets machine learning: Opportunity or challenge[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 23(8): 9995-10011.
[6]
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(04): 354-362.
Wu W, Lyu Z, Zhou W, et al. GNSS/INS spoofing detection method based on combined epoch innovation robustness[J]. Journal of Chinese Inertial Technology, 2024, 32(04): 354-362.
[7]
Zhang S, Tang H, Chen L, et al. A seamless pedestrian localization system based on GNSS/IMU/UWB/MAP integration[J]. IEEE Internet of Things Journal, 2025, 12(11): 16653-16667.
[8]
Kohtake N, Morimoto S, Kogure S, et al. Indoor and outdoor seamless positioning using indoor messaging system and GPS[C]//Proceedings of the international conference on indoor positioning and indoor navigation (IPIN2011), Guimarães, Portugal. 2011: 21-23.
[9]
Feng T, Liu Y, Yu Y, et al. CrowdLOC-S: Crowdsourced seamless localization framework based on CNN-LSTM-MLP enhanced quality indicator[J]. Expert Systems with Applications, 2024, 243: 122852.
[10]
Li X, Wu Z, Shen Z, et al. An indoor and outdoor seamless positioning system for low-cost UGV using PPP/INS/UWB tightly coupled integration[J]. IEEE Sensors Journal, 2023, 23(20): 24895-24906.
[11]
张威奕, 曾庆喜, 张鹏娜, . 基于UKF的车辆GPS/蜂窝网无缝定位算法[J]. 中国惯性技术学报, 2015, 23(01): 76-80.
Zhang W, Zeng Q, Zhang P, et al. Vehicle GPS/cellular network seamless positioning algorithm based on UKF[J]. Journal of Chinese Inertial Technology, 2015, 23(01): 76-80.
[12]
Yao L, Li M, Xu T, et al. GNSS/UWB/INS indoor and outdoor seamless positioning algorithm based on federal filtering[J]. Measurement Science and Technology, 2023, 35(1): 015135.
[13]
张容阁. 基于UWB/GNSS/IMU的机器人室内外无缝定位技术研究[D]. 哈尔滨: 哈尔滨工业大学, 2020.
Zhang R. Research on indoor-outdoor seamless robot positioning technology based on UWB/GNSS/IMU[D]. Harbin: Harbin Institute of Technology, 2020.
[14]
王琳. 室内外无缝定位中的情境感知方法研究[D]. 上海: 上海交通大学, 2017.
Wang L. Research on context awareness in indoor and outdoor seamless positioning[D]. Shanghai: Shanghai Jiao Tong University, 2017.
[15]
Li M, Zhou P, Zheng Y, et al. IODetector: A generic service for indoor/outdoor detection[J]. ACM Transactions on Sensor Networks (TOSN), 2014, 11(2): 1-29.
[16]
Zhu Y, Luo H, Wang Q, et al. A fast indoor/outdoor transition detection algorithm based on machine learning[J]. Sensors, 2019, 19(4): 786.
[17]
曾庆栋, 陈光辉, 李文鑫, . 基于粒子群-支持向量机算法的激光诱导击穿光谱钢铁快速检测与分类[J]. 光谱学与光谱分析, 2024, 44(06): 1559-1565.
Zeng Q, Chen G, Li W, et al. Classification of special steel based on LIBS combined with particle swarm optimization and support vector machine[J]. Spectroscopy and Spectral Analysis, 2024, 44(06): 1559-1565.
[18]
Xu J. An extended one-versus-rest support vector machine for multi-label classification[J]. Neurocomputing, 2011, 74(17): 3114-3124.
2025年第33卷第10期
PDF下载
158
80
引用本文
BibTeX
文章信息
doi: 10.13695/j.cnki.12-1222/o3.2025.10.008
  • 接收时间:2024-11-14
  • 首发时间:2026-03-27
  • 出版时间:2025-10-30
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-11-14
  • 录用日期:2025-08-20
基金
云南省基础研究计划项目(202501AS070115)
云南省重大科技专项计划(202402AE090009)
作者信息
    昆明理工大学 交通工程学院,昆明 650500

通讯作者:

张生斌(1981—),男,讲师,博士,从事车辆测试技术研究。
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zggxjsxb/CN/10.13695/j.cnki.12-1222/o3.2025.10.008
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