Research Article
Real-Time Multipath Mitigation in Multi-GNSS Short Baseline
Positioning via CNN-LSTM Method
Yuan Tao,
1
Chao Liu ,
1,2,3
Tianyang Chen,
4
Xingwang Zhao,
1
Chunyang Liu ,
1,2
Haojie Hu,
1
Tengfei Zhou,
5
and Haiqiang Xin
6
1
School of Spatial Information and Geomatics Engineering, Anhui University of Science and Technology, Huainan 232001, China
2
Jiangsu Key Laboratory of Resources and Environmental Information Engineering, China University of Mining and Technology,
Xuzhou 221116, China
3
School of Mining and Geomatics, Hebei University of Engineering, Handan 056038, China
4
Department of Geography and Earth Science, e University of North Carolina at Charlotte, Charlotte 28223, USA
5
College of Surveying and Geo-informatics, Tongji University, Shanghai 200092, China
6
Xinjiang Academy of Surveying and Mapping, Urumqi 830002, China
CorrespondenceshouldbeaddressedtoChaoLiu;chaoliu0202@gmail.com
Received 28 July 2020; Revised 17 December 2020; Accepted 23 December 2020; Published 5 January 2021
AcademicEditor:AdrianNeagu
Copyright © 2021 Yuan Tao et al. is is an open access article distributed under the Creative Commons Attribution License,
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Multipath is the main systematic error of the Global Navigation Satellite System (GNSS) short baseline positioning. Multipath
cannot be eliminated by the double-differenced technique and is difficult to parameterize, which severely restrict the high-
precision GNSS positioning application. Based on the spatiotemporal repeatability of multipath, the sidereal filtering in co-
ordinate-domain(SF-CD),thesiderealfilteringinobservation-domain(SF-OD),andthemultipathhemisphericalmap(MHM)
can be used to mitigate the multipath in real-time. However, the multipath model with large matrix for multi-GNSS multipath
mitigationisdifficulttoachievelightweightcalculationandtheSF-CDcannotbeappliedtomitigatethemulti-GNSSmultipath.In
thispaper,weproposeanewmultipathmitigationstrategyinthecoordinate-domainthatshakesofftheformationmechanismof
multipath,aCNN(convolutionalneuralnetwork)-LSTM(longshort-termmemory)methodisusedtominethedeepmultipath
featuresinGNSScoordinateseries.Furthermore,multipathwillbemitigatedinreal-timebyconstantlypredictingthevalueofthe
nextepoch.eexperimentalresultsshowthattheCNN-LSTMeffectivelymitigatesthemulti-GNSSmultipath.emethodcan
reducetheaverageRMS(root-meansquare)ofmulti-GNSSpositioningerrorsintheeast,north,andverticaldirectionsby62.3%,
70.8%,and66.0%.Moreover,comparingwiththeSF-CD,SF-OD,andMHM,CNN-LSTMcanmoreeffectivelymitigatetheeffects
of the GPS multipath, and the ability of multipath mitigation is almost not affected over time.
1. Introduction
eGlobalNavigationSatelliteSystem(GNSS),asareal-
timeandhigh-precisionpositioningtechnology,iswidely
used in many fields such as navigation, geodesy, defor-
mation monitoring, and photogrammetry [1–4]. How-
ever, many errors limit the GNSS positioning accuracy
[5], such as receiver clock error, satellite clock error,
tropospheric delay error, ionospheric delay error, and
multipath. e double-differenced technique can elimi-
nate satellite and receiver clock errors and significantly
weaken tropospheric and ionospheric delay errors in
GNSS short baseline positioning; however, it cannot
eliminate or weaken multipath. erefore, the multipath
is the primary errors source in GNSS short baseline
positioning [6]. Research on multipath mitigation has
become an important research issue, and many scholars
have conducted lots of researches around this issue
[7–10]. In addition to site selection, current researches
can be divided into two categories: hardware-based and
software-based approaches. e hardware-based ap-
proaches mainly mitigate multipath by improving
Hindawi
Mathematical Problems in Engineering
Volume 2021, Article ID 6573230, 12 pages
https://doi.org/10.1155/2021/6573230