Multi-Robot Object SLAM Using Distributed Variational Inference

Multi-robot simultaneous localization and mapping (SLAM) enables a robot team to achieve coordinated tasks by relying on a common map of the environment. Constructing a map by centralized processing of the robot observations is undesirable because it creates a single point of failure and requires pr...

Full description

Saved in:
Bibliographic Details
Published inIEEE robotics and automation letters Vol. 9; no. 10; pp. 8722 - 8729
Main Authors Cao, Hanwen, Shreedharan, Sriram, Atanasov, Nikolay
Format Journal Article
LanguageEnglish
Published IEEE 01.10.2024
Subjects
Distributed robot systems
Kalman filters
Mirrors
multi-robot SLAM
Multi-robot systems
Optimization
probability and statistical methods
Robot kinematics
Simultaneous localization and mapping
Static analysis
Trajectory
Online AccessGet full text

Cover

Abstract Multi-robot simultaneous localization and mapping (SLAM) enables a robot team to achieve coordinated tasks by relying on a common map of the environment. Constructing a map by centralized processing of the robot observations is undesirable because it creates a single point of failure and requires pre-existing infrastructure and significant communication throughput. This letter formulates multi-robot object SLAM as a variational inference problem over a communication graph subject to consensus constraints on the object estimates maintained by different robots. To solve the problem, we develop a distributed mirror descent algorithm with regularization enforcing consensus among the communicating robots. Using Gaussian distributions in the algorithm, we also derive a distributed multi-state constraint Kalman filter (MSCKF) for multi-robot object SLAM. Experiments on real and simulated data show that our method improves the trajectory and object estimates, compared to individual-robot SLAM, while achieving better scaling to large robot teams, compared to centralized multi-robot SLAM.
AbstractList Multi-robot simultaneous localization and mapping (SLAM) enables a robot team to achieve coordinated tasks by relying on a common map of the environment. Constructing a map by centralized processing of the robot observations is undesirable because it creates a single point of failure and requires pre-existing infrastructure and significant communication throughput. This letter formulates multi-robot object SLAM as a variational inference problem over a communication graph subject to consensus constraints on the object estimates maintained by different robots. To solve the problem, we develop a distributed mirror descent algorithm with regularization enforcing consensus among the communicating robots. Using Gaussian distributions in the algorithm, we also derive a distributed multi-state constraint Kalman filter (MSCKF) for multi-robot object SLAM. Experiments on real and simulated data show that our method improves the trajectory and object estimates, compared to individual-robot SLAM, while achieving better scaling to large robot teams, compared to centralized multi-robot SLAM.
Author Cao, Hanwen
Shreedharan, Sriram
Atanasov, Nikolay
Author_xml – sequence: 1
  givenname: Hanwen
  orcidid: 0000-0003-2606-7433
  surname: Cao
  fullname: Cao, Hanwen
  email: h1cao@ucsd.edu
  organization: Department of Electrical and Computer Engineering, University of California, San Diego, CA, USA
– sequence: 2
  givenname: Sriram
  orcidid: 0000-0003-2216-7867
  surname: Shreedharan
  fullname: Shreedharan, Sriram
  email: sshreedharan@ucsd.edu
  organization: Department of Electrical and Computer Engineering, University of California, San Diego, CA, USA
– sequence: 3
  givenname: Nikolay
  orcidid: 0000-0003-0272-7580
  surname: Atanasov
  fullname: Atanasov, Nikolay
  email: natanasov@ucsd.edu
  organization: Department of Electrical and Computer Engineering, University of California, San Diego, CA, USA
BookMark eNp9kD1PwzAQhi1UJErpzsCQP5DibycTqgqFSqkqFcoa2e4ZuQoJst2Bf09KO1QMTPcuz917zzUatF0LCN0SPCEEl_fVejqhmPIJ44KworxAQ8qUypmScnCWr9A4xh3GmAiqWCmG6GG5b5LP153pUrYyO7Ape62my2wTffuRPfqYgjf7BNvsXQevk-9a3WSL1kGA1sINunS6iTA-zRHazJ_eZi95tXpezKZVbqnkKTdOGw2G9x21tYAJL4zDBcFbV0jJKCeOGdDCcVsaqoWihmiClWKcGmENGyF83GtDF2MAV38F_6nDd01wfXBQ9w7qg4P65KBH5B_E-vT7QAraN_-Bd0fQA8DZHSk4I4T9AIY3as8
CODEN IRALC6
CitedBy_id crossref_primary_10_1109_LRA_2024_3451389
Cites_doi 10.1109/tro.2024.3422003
10.1109/LRA.2020.2965893
10.23919/ACC.2017.7962962
10.1109/ICRA.2018.8460664
10.1201/9780203509128
10.1109/IROS.2018.8593941
10.1109/TRO.2021.3137751
10.1109/LRA.2020.2967681
10.1109/IVS.2011.5940405
10.1109/LRA.2024.3451389
10.1109/ICRA.2013.6631323
10.1109/ICCV.2019.00939
10.1109/LRA.2018.2793349
10.1177/0278364920937608
10.1109/RCAR.2016.7784092
10.1109/ICRA40945.2020.9196524
10.1109/ACCESS.2023.3249661
10.1109/ICRA.2018.8460217
10.1109/TRO.2016.2624754
10.1137/15M1024950
10.1016/S0167-6377(02)00231-6
10.1109/ROBOT.2007.364024
10.1177/0278364911430419
10.1109/CVPR.2012.6248074
10.1109/ROBOT.2008.4543634
10.1109/TRO.2023.3327635
10.15607/RSS.2009.V.009
10.1109/LCSYS.2022.3167654
10.1109/TRO.2021.3072346
10.1109/TRA.2002.803461
10.1177/0278364904045479
10.1016/S0262-8856(97)00056-5
10.1016/j.eswa.2022.117734
10.1177/0278364906072768
10.1016/j.robot.2014.08.007
10.1109/IROS51168.2021.9636687
10.1177/0278364917732640
10.1109/TRO.2020.3001664
10.1109/IVS.2010.5548123
10.1109/IROS51168.2021.9636031
10.1109/TSP.2009.2016247
10.1017/9781316671528
10.1109/TRO.2008.2006706
10.1109/ICRA.2019.8793604
10.1109/IROS.2010.5652875
10.1007/11744023_32
ContentType Journal Article
DBID 97E
RIA
RIE
AAYXX
CITATION
DOI 10.1109/LRA.2024.3451389
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998-Present
IEEE Electronic Library (IEL)
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2377-3766
EndPage 8729
ExternalDocumentID 10_1109_LRA_2024_3451389
10654311
Genre orig-research
GrantInformation_xml – fundername: NSF FRR CAREER
  grantid: 2045945
– fundername: ARL DCIST CRA
  grantid: W911NF-17-2-0181
GroupedDBID 0R~
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFS
AGQYO
AGSQL
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
EJD
IFIPE
IPLJI
JAVBF
KQ8
M43
M~E
O9-
OCL
RIA
RIE
AAYXX
CITATION
RIG
ID FETCH-LOGICAL-c264t-bfabaeb4024acce0148bf0810df8663241f3bea5f4c9b2a572b1a1077342b5cb3
IEDL.DBID RIE
ISSN 2377-3766
IngestDate Thu Apr 24 22:53:59 EDT 2025
Tue Jul 01 00:21:14 EDT 2025
Wed Aug 27 02:29:07 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 10
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c264t-bfabaeb4024acce0148bf0810df8663241f3bea5f4c9b2a572b1a1077342b5cb3
ORCID 0000-0003-2216-7867
0000-0003-2606-7433
0000-0003-0272-7580
PageCount 8
ParticipantIDs ieee_primary_10654311
crossref_citationtrail_10_1109_LRA_2024_3451389
crossref_primary_10_1109_LRA_2024_3451389
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2024-10-01
PublicationDateYYYYMMDD 2024-10-01
PublicationDate_xml – month: 10
  year: 2024
  text: 2024-10-01
  day: 01
PublicationDecade 2020
PublicationTitle IEEE robotics and automation letters
PublicationTitleAbbrev LRA
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
References ref13
ref12
ref15
ref14
ref11
ref10
ref17
Kinnari (ref2) 2024
ref16
ref19
ref18
Lucas (ref43) 1981; 2
ref46
ref45
ref48
ref47
ref42
ref41
ref44
ref49
Li (ref6) 2022
ref8
ref7
ref9
ref4
ref3
ref5
ref40
ref35
ref34
ref37
ref36
ref31
ref30
ref33
ref32
ref1
ref39
ref38
ref24
ref23
ref26
ref25
ref20
ref22
ref21
ref28
ref27
ref29
References_xml – ident: ref26
  doi: 10.1109/tro.2024.3422003
– ident: ref23
  doi: 10.1109/LRA.2020.2965893
– ident: ref48
  doi: 10.23919/ACC.2017.7962962
– ident: ref12
  doi: 10.1109/ICRA.2018.8460664
– ident: ref38
  doi: 10.1201/9780203509128
– ident: ref47
  doi: 10.1109/IROS.2018.8593941
– ident: ref22
  doi: 10.1109/TRO.2021.3137751
– ident: ref24
  doi: 10.1109/LRA.2020.2967681
– ident: ref39
  doi: 10.1109/IVS.2011.5940405
– ident: ref36
  doi: 10.1109/LRA.2024.3451389
– ident: ref17
  doi: 10.1109/ICRA.2013.6631323
– ident: ref45
  doi: 10.1109/ICCV.2019.00939
– ident: ref40
  doi: 10.1109/LRA.2018.2793349
– ident: ref34
  doi: 10.1177/0278364920937608
– ident: ref4
  doi: 10.1109/RCAR.2016.7784092
– ident: ref41
  doi: 10.1109/ICRA40945.2020.9196524
– ident: ref13
  doi: 10.1109/ACCESS.2023.3249661
– ident: ref25
  doi: 10.1109/ICRA.2018.8460217
– ident: ref1
  doi: 10.1109/TRO.2016.2624754
– ident: ref27
  doi: 10.1137/15M1024950
– ident: ref7
  doi: 10.1016/S0167-6377(02)00231-6
– ident: ref8
  doi: 10.1109/ROBOT.2007.364024
– ident: ref10
  doi: 10.1177/0278364911430419
– ident: ref42
  doi: 10.1109/CVPR.2012.6248074
– ident: ref3
  doi: 10.1109/ROBOT.2008.4543634
– ident: ref21
  doi: 10.1109/TRO.2023.3327635
– ident: ref30
  doi: 10.15607/RSS.2009.V.009
– ident: ref35
  doi: 10.1109/LCSYS.2022.3167654
– ident: ref15
  doi: 10.1109/TRO.2021.3072346
– ident: ref28
  doi: 10.1109/TRA.2002.803461
– ident: ref29
  doi: 10.1177/0278364904045479
– ident: ref5
  doi: 10.1016/S0262-8856(97)00056-5
– ident: ref14
  doi: 10.1016/j.eswa.2022.117734
– ident: ref18
  doi: 10.1177/0278364906072768
– ident: ref31
  doi: 10.1016/j.robot.2014.08.007
– year: 2022
  ident: ref6
  article-title: YOLOv6: A single-stage object detection framework for industrial applications
– ident: ref20
  doi: 10.1109/IROS51168.2021.9636687
– ident: ref19
  doi: 10.1177/0278364917732640
– ident: ref32
  doi: 10.1109/TRO.2020.3001664
– ident: ref44
  doi: 10.1109/IVS.2010.5548123
– ident: ref33
  doi: 10.1109/IROS51168.2021.9636031
– ident: ref49
  doi: 10.1109/TSP.2009.2016247
– ident: ref37
  doi: 10.1017/9781316671528
– ident: ref9
  doi: 10.1109/TRO.2008.2006706
– ident: ref11
  doi: 10.1109/ICRA.2019.8793604
– year: 2024
  ident: ref2
  article-title: SOS-SLAM: Segmentation for open-set SLAM in unstructured environments
– ident: ref16
  doi: 10.1109/IROS.2010.5652875
– ident: ref46
  doi: 10.1007/11744023_32
– volume: 2
  start-page: 674
  volume-title: Proc. Int. Joint Conf. Artif. Intell.
  year: 1981
  ident: ref43
  article-title: An iterative image registration technique with an application to stereo vision
SSID ssj0001527395
Score 2.2837186
Snippet Multi-robot simultaneous localization and mapping (SLAM) enables a robot team to achieve coordinated tasks by relying on a common map of the environment....
SourceID crossref
ieee
SourceType Enrichment Source
Index Database
Publisher
StartPage 8722
SubjectTerms Distributed robot systems
Kalman filters
Mirrors
multi-robot SLAM
Multi-robot systems
Optimization
probability and statistical methods
Robot kinematics
Simultaneous localization and mapping
Static analysis
Trajectory
Title Multi-Robot Object SLAM Using Distributed Variational Inference
URI https://ieeexplore.ieee.org/document/10654311
Volume 9
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV07T8MwELZoJxh4FlEeVQYWhqRt_Eg8oQpaFdQWqVDULfI5zgJqEUoXBn47PieBggRiiyLbsny2fN_5vu8IOaeQcQZS-CaKqM9oas8cFZjhKIWOUs4jQHLyeCKGM3Y75_OSrO64MMYYl3xmAvx0b_npUq8wVGZPODIhkclbs8itIGt9BVRQSkzy6imyI9ujac8CwJAFlHF8j_t29azVUnFXyWCHTKpJFBkkT8Eqh0C__dBn_Pcsd8l26VR6vWIX7JENs9gnW2tSgwfk0jFt_ekSlrl3Bxh98e5HvbHncga8a9TPxdJXJvUeLXwuQ4TeTcUHbJDZoP9wNfTL4gm-tj5O7kOmQBmw8JAprQ0GDiGz938nzWKBGu3djIJRPGNaQqh4FEJXWSwYURYC10APSX2xXJgj4kUxzaSwnpakjFk8qYDGQsVhquxgIoUmaVfrmuhSWRwLXDwnDmF0ZGItkaAlktISTXLx2eOlUNX4o20D13itXbG8x7_8PyGb2L1IuDsl9fx1Zc6s45BDi9TG7_2W2zYfb5i_tA
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV05T8MwFLZQGYCBs4hyemBhSNrGR5IJVRxqIS1SaVG3yM9xFlCDULrw6_HLAQUJxBZFtmX52Xrn9z1CzhmkgkMoHeP7zOEssW-OSaxwDKX2EyF8QHDycCT7U343E7MKrF5gYYwxRfGZcfGzyOUnmV5gqMy-cERCIpJ31Sp-0S3hWl8hFSQTC0WdjOyE7Wjcsy6gx13GBWbkvimfpW4qhTK53SKjehtlDcmzu8jB1e8_GBr_vc9tslmZlbRX3oMdsmLmu2RjiWxwj1wWWFtnnEGW0wfA-At9jHpDWlQN0Gtk0MXmVyahT9aBroKEdFAjAptkenszueo7VfsER1srJ3cgVaAMWAeRK60Nhg4htRZAJ0kDiSzt3ZSBUSLlOgRPCd-DrrLeoM-4B0ID2yeNeTY3B4T6AUtDaW2tkHFuPUoFLJAq8BJlF5MJtEi7PtdYV9zi2OLiJS58jE4YW0nEKIm4kkSLXHzOeC15Nf4Y28QzXhpXHu_hL__PyFp_MoziaDC6PyLruFRZfndMGvnbwpxYMyKH0-LyfAAUB8HM
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Multi-Robot+Object+SLAM+Using+Distributed+Variational+Inference&rft.jtitle=IEEE+robotics+and+automation+letters&rft.au=Cao%2C+Hanwen&rft.au=Shreedharan%2C+Sriram&rft.au=Atanasov%2C+Nikolay&rft.date=2024-10-01&rft.pub=IEEE&rft.eissn=2377-3766&rft.volume=9&rft.issue=10&rft.spage=8722&rft.epage=8729&rft_id=info:doi/10.1109%2FLRA.2024.3451389&rft.externalDocID=10654311
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2377-3766&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2377-3766&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2377-3766&client=summon