Outlier-Robust Estimation: Hardness, Minimally Tuned Algorithms, and Applications

Nonlinear estimation in robotics and vision is typically plagued with outliers due to wrong data association or incorrect detections from signal processing and machine learning methods. This article introduces two unifying formulations for outlier-robust estimation, generalized maximum consensus (&l...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on robotics Jg. 38; H. 1; S. 281 - 301
Hauptverfasser: Antonante, Pasquale, Tzoumas, Vasileios, Yang, Heng, Carlone, Luca
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 01.02.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Adaptive algorithms
Algorithms
Approximation algorithms
autonomous systems
Combinatorial analysis
computational complexity
computer vision
Estimation
Formulations
Inliers (landforms)
Machine learning
maximum likelihood estimation
Measurement uncertainty
Object recognition
Optimization
Outliers (statistics)
Particle measurements
Polynomials
Probabilistic logic
resilient perception
Robotics
robust estimation
Robustness
Signal processing
Signal processing algorithms
Simultaneous localization and mapping
ISSN:1552-3098, 1941-0468
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Nonlinear estimation in robotics and vision is typically plagued with outliers due to wrong data association or incorrect detections from signal processing and machine learning methods. This article introduces two unifying formulations for outlier-robust estimation, generalized maximum consensus (<inline-formula><tex-math notation="LaTeX">\text{G}</tex-math></inline-formula>-<inline-formula><tex-math notation="LaTeX">\text{MC}</tex-math></inline-formula>) and generalized truncated least squares (<inline-formula><tex-math notation="LaTeX">\text{G-TLS}</tex-math></inline-formula>), and investigates fundamental limits, practical algorithms, and applications. Our first contribution is a proof that outlier-robust estimation is inapproximable: In the worst case, it is impossible to (even approximately) find the set of outliers, even with slower-than-polynomial-time algorithms (particularly, algorithms running in quasi-polynomial time). As a second contribution, we review and extend two general-purpose algorithms. The first, adaptive trimming (<inline-formula><tex-math notation="LaTeX">\text{ADAPT}</tex-math></inline-formula>), is combinatorial and is suitable for <inline-formula><tex-math notation="LaTeX">\text{G}</tex-math></inline-formula>-<inline-formula><tex-math notation="LaTeX">\text{MC}</tex-math></inline-formula>; the second, graduated nonconvexity (<inline-formula><tex-math notation="LaTeX">\text{GNC}</tex-math></inline-formula>), is based on homotopy methods and is suitable for <inline-formula><tex-math notation="LaTeX">\text{G-TLS}</tex-math></inline-formula>. We extend <inline-formula><tex-math notation="LaTeX">\text{ADAPT}</tex-math></inline-formula> and <inline-formula><tex-math notation="LaTeX">\text{GNC}</tex-math></inline-formula> to the case where the user does not have prior knowledge of the inlier-noise statistics (or the statistics may vary over time) and is unable to guess a reasonable threshold to separate inliers from outliers (as the one commonly used in RANdom SAmple Consensus <inline-formula><tex-math notation="LaTeX">(\text{RANSAC})</tex-math></inline-formula>. We propose the first minimally tuned algorithms for outlier rejection, which dynamically decide how to separate inliers from outliers. Our third contribution is an evaluation of the proposed algorithms on robot perception problems: mesh registration, image-based object detection ( shape alignment ), and pose graph optimization. <inline-formula><tex-math notation="LaTeX">\text{ADAPT}</tex-math></inline-formula> and <inline-formula><tex-math notation="LaTeX">\text{GNC}</tex-math></inline-formula> execute in real time, are deterministic, outperform <inline-formula><tex-math notation="LaTeX">\text{RANSAC}</tex-math></inline-formula>, and are robust up to 80-90% outliers. Their minimally tuned versions also compare favorably with the state of the art, even though they do not rely on a noise bound for the inliers.
AbstractList Nonlinear estimation in robotics and vision is typically plagued with outliers due to wrong data association or incorrect detections from signal processing and machine learning methods. This article introduces two unifying formulations for outlier-robust estimation, generalized maximum consensus ([Formula Omitted]-[Formula Omitted]) and generalized truncated least squares ([Formula Omitted]), and investigates fundamental limits, practical algorithms, and applications. Our first contribution is a proof that outlier-robust estimation is inapproximable: In the worst case, it is impossible to (even approximately) find the set of outliers, even with slower-than-polynomial-time algorithms (particularly, algorithms running in quasi-polynomial time). As a second contribution, we review and extend two general-purpose algorithms. The first, adaptive trimming ([Formula Omitted]), is combinatorial and is suitable for [Formula Omitted]-[Formula Omitted]; the second, graduated nonconvexity ([Formula Omitted]), is based on homotopy methods and is suitable for [Formula Omitted]. We extend [Formula Omitted] and [Formula Omitted] to the case where the user does not have prior knowledge of the inlier-noise statistics (or the statistics may vary over time) and is unable to guess a reasonable threshold to separate inliers from outliers (as the one commonly used in RANdom SAmple Consensus [Formula Omitted]. We propose the first minimally tuned algorithms for outlier rejection, which dynamically decide how to separate inliers from outliers. Our third contribution is an evaluation of the proposed algorithms on robot perception problems: mesh registration, image-based object detection ( shape alignment ), and pose graph optimization. [Formula Omitted] and [Formula Omitted] execute in real time, are deterministic, outperform [Formula Omitted], and are robust up to 80–90% outliers. Their minimally tuned versions also compare favorably with the state of the art, even though they do not rely on a noise bound for the inliers.
Nonlinear estimation in robotics and vision is typically plagued with outliers due to wrong data association or incorrect detections from signal processing and machine learning methods. This article introduces two unifying formulations for outlier-robust estimation, generalized maximum consensus (<inline-formula><tex-math notation="LaTeX">\text{G}</tex-math></inline-formula>-<inline-formula><tex-math notation="LaTeX">\text{MC}</tex-math></inline-formula>) and generalized truncated least squares (<inline-formula><tex-math notation="LaTeX">\text{G-TLS}</tex-math></inline-formula>), and investigates fundamental limits, practical algorithms, and applications. Our first contribution is a proof that outlier-robust estimation is inapproximable: In the worst case, it is impossible to (even approximately) find the set of outliers, even with slower-than-polynomial-time algorithms (particularly, algorithms running in quasi-polynomial time). As a second contribution, we review and extend two general-purpose algorithms. The first, adaptive trimming (<inline-formula><tex-math notation="LaTeX">\text{ADAPT}</tex-math></inline-formula>), is combinatorial and is suitable for <inline-formula><tex-math notation="LaTeX">\text{G}</tex-math></inline-formula>-<inline-formula><tex-math notation="LaTeX">\text{MC}</tex-math></inline-formula>; the second, graduated nonconvexity (<inline-formula><tex-math notation="LaTeX">\text{GNC}</tex-math></inline-formula>), is based on homotopy methods and is suitable for <inline-formula><tex-math notation="LaTeX">\text{G-TLS}</tex-math></inline-formula>. We extend <inline-formula><tex-math notation="LaTeX">\text{ADAPT}</tex-math></inline-formula> and <inline-formula><tex-math notation="LaTeX">\text{GNC}</tex-math></inline-formula> to the case where the user does not have prior knowledge of the inlier-noise statistics (or the statistics may vary over time) and is unable to guess a reasonable threshold to separate inliers from outliers (as the one commonly used in RANdom SAmple Consensus <inline-formula><tex-math notation="LaTeX">(\text{RANSAC})</tex-math></inline-formula>. We propose the first minimally tuned algorithms for outlier rejection, which dynamically decide how to separate inliers from outliers. Our third contribution is an evaluation of the proposed algorithms on robot perception problems: mesh registration, image-based object detection ( shape alignment ), and pose graph optimization. <inline-formula><tex-math notation="LaTeX">\text{ADAPT}</tex-math></inline-formula> and <inline-formula><tex-math notation="LaTeX">\text{GNC}</tex-math></inline-formula> execute in real time, are deterministic, outperform <inline-formula><tex-math notation="LaTeX">\text{RANSAC}</tex-math></inline-formula>, and are robust up to 80-90% outliers. Their minimally tuned versions also compare favorably with the state of the art, even though they do not rely on a noise bound for the inliers.
Author Yang, Heng
Antonante, Pasquale
Carlone, Luca
Tzoumas, Vasileios
Author_xml – sequence: 1
  givenname: Pasquale
  orcidid: 0000-0002-4319-3135
  surname: Antonante
  fullname: Antonante, Pasquale
  email: antonap@mit.edu
  organization: Laboratory for Information & Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA
– sequence: 2
  givenname: Vasileios
  orcidid: 0000-0001-9951-5255
  surname: Tzoumas
  fullname: Tzoumas, Vasileios
  email: vtzoumas@umich.edu
  organization: Laboratory for Information & Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA
– sequence: 3
  givenname: Heng
  orcidid: 0000-0003-0074-7836
  surname: Yang
  fullname: Yang, Heng
  email: hankyang@mit.edu
  organization: Laboratory for Information & Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA
– sequence: 4
  givenname: Luca
  orcidid: 0000-0003-1884-5397
  surname: Carlone
  fullname: Carlone, Luca
  email: lcarlone@mit.edu
  organization: Laboratory for Information & Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA
BookMark eNp9kD1PwzAQhi1UJNrCjsQSiZUU27HTmK2qCkUqiqjKbDnJBVylTrCdof8e90MMDEw--97nznpGaGBaAwjdEjwhBIvHzTqfUEzJJMGCiYxdoCERjMSYpdkg1JzTOLSyKzRybosxZQInQ_Se977RYON1W_TORwvn9U553ZqnaKlsZcC5h-hNm_DaNPto0xuoolnz2Vrtv3ahp0y4d12jyyPmrtFlrRoHN-dzjD6eF5v5Ml7lL6_z2SouqSA-BiwgLThQQqeYJnzKBcUlCJYWWBFGahC1AlZlJVesTipWKqJUxUUoWCEgGaP709zOtt89OC-3bW9NWClpSlMxpZwnIZWeUqVtnbNQy1L740e9VbqRBMuDPhn0yYM-edYXQPwH7GxwYPf_IXcnRAPAb1ykJNgmyQ_wwn0O
CODEN ITREAE
CitedBy_id crossref_primary_10_1109_LRA_2021_3116313
crossref_primary_10_1109_TPAMI_2022_3179463
crossref_primary_10_1109_TIM_2025_3600832
crossref_primary_10_1109_TRO_2023_3277273
crossref_primary_10_1109_TAES_2023_3290142
crossref_primary_10_1007_s10107_022_01912_6
crossref_primary_10_1109_TIM_2024_3364269
crossref_primary_10_1177_02783649241229725
crossref_primary_10_3390_a18030174
crossref_primary_10_1016_j_sigpro_2023_109293
crossref_primary_10_1109_TGRS_2024_3404959
crossref_primary_10_1109_TRO_2021_3094984
crossref_primary_10_1109_LRA_2022_3143298
crossref_primary_10_1155_2023_8674641
crossref_primary_10_1109_TRO_2021_3137751
crossref_primary_10_1109_TAES_2023_3300264
crossref_primary_10_1109_TCSVT_2023_3264451
crossref_primary_10_1109_TRO_2024_3484608
crossref_primary_10_4173_mic_2022_2_3
crossref_primary_10_4173_mic_2024_4_3
Cites_doi 10.1016/j.actaastro.2012.08.011
10.1145/2185520.2185526
10.1109/ICCV.2019.00175
10.1109/34.121791
10.1109/ICRA.2011.5979612
10.1109/ICRA.2012.6224709
10.1007/978-3-319-10590-1_8
10.1561/2300000047
10.1109/CVPR.2019.00446
10.1109/ICCVW.2019.00343
10.1016/j.cviu.2018.08.001
10.1109/WACV.2014.6836101
10.1109/CDC.2018.8619401
10.1109/CVPR.2016.445
10.1109/ICRA.2011.5979949
10.1016/j.isprsjprs.2016.01.010
10.1016/S1361-8415(00)00014-1
10.1109/CVPR.2016.631
10.1115/1.3662552
10.1109/CVPR.2014.71
10.15607/RSS.2012.VIII.040
10.1002/SERIES1345
10.1109/TPAMI.2018.2816031
10.1093/imaiai/iat005
10.1109/FOCS.2016.85
10.1109/TRO.2021.3094984
10.1109/TCNS.2016.2606880
10.1177/0278364914523689
10.1007/978-3-319-10593-2_31
10.1109/ICCV.1999.790410
10.1007/BF01588971
10.1063/1.3047921
10.1109/IROS.2013.6696406
10.1007/978-3-319-10602-1_50
10.1109/TRO.2020.3033695
10.1109/ICRA.2015.7139486
10.1109/ICRA.2013.6630557
10.1109/TPAMI.2016.2605097
10.1109/34.809117
10.1109/ISMAR.2007.4538852
10.2200/S00757ED1V01Y201702COV011
10.1109/CVPR.2019.00569
10.1109/TRO.2016.2544304
10.1007/978-3-642-37444-9_42
10.1109/TPAMI.2015.2513405
10.1007/BF00127126
10.1017/CBO9780511804441
10.1109/ROBOT.2009.5152473
10.1109/IROS40897.2019.8968174
10.1109/TRO.2016.2624754
10.1007/978-3-642-33765-9_41
10.1109/TPAMI.2017.2773482
10.1007/978-3-030-01258-8_43
10.1145/2897824.2925913
10.1109/TPAMI.1987.4767965
10.1109/LRA.2021.3061331
10.1109/TPAMI.2003.1217599
10.1109/CVPR42600.2020.00138
10.1109/TAC.2013.2266831
10.1109/IROS.2015.7353364
10.1007/978-3-319-14612-6_4
10.1109/LRA.2018.2793352
10.1002/widm.2
10.1109/ICCV.2009.5459398
10.1214/aoms/1177703732
10.15607/RSS.2019.XV.003
10.1109/CVPR.2017.595
10.1007/978-3-319-10605-2_52
10.1007/s11263-008-0186-9
10.1109/TSP.2017.2771720
10.1007/978-3-319-10590-1_9
10.1109/ICRA.2018.8460217
10.1109/ICRA.2015.7139836
10.1109/TIT.2011.2146690
10.1007/BF00131148
10.1109/CVPR.2011.5995640
10.1137/S0036144598345802
10.1109/CVPR.2008.4587757
10.1109/IROS.2012.6385590
10.1007/978-3-319-46475-6_47
10.1145/358669.358692
10.1109/ICCV.2013.70
10.1109/CVPR.2015.7299195
10.1364/josaa.4.000629
10.1109/LRA.2020.2965893
10.1007/978-3-030-28619-4_49
10.1109/LRA.2019.2894852
10.1177/0278364918784361
10.2307/2681802
10.1109/ICCV.2019.00905
10.1109/TIT.2005.858979
10.1109/CVPR.2017.536
10.1007/978-3-642-33718-5_53
10.1109/CVPR42600.2020.00070
10.1017/CBO9780511804090
10.7551/mitpress/9816.003.0035
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
7SP
7TB
8FD
FR3
JQ2
L7M
L~C
L~D
DOI 10.1109/TRO.2021.3094984
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Mechanical & Transportation Engineering Abstracts
Technology Research Database
Engineering Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Technology Research Database
Computer and Information Systems Abstracts – Academic
Mechanical & Transportation Engineering Abstracts
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Engineering Research Database
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
DatabaseTitleList Technology Research Database
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1941-0468
EndPage 301
ExternalDocumentID 10_1109_TRO_2021_3094984
9610021
Genre orig-research
GrantInformation_xml – fundername: Lincoln Laboratory's Resilient Perception in Degraded Environments program
– fundername: ARL DCIST CRA
  grantid: W911NF-17-2-0181
– fundername: MathWorks, NS CAREER
– fundername: ONR RAIDER
  grantid: N00014-18-1-2828
– fundername: Certifiable Perception for Autonomous Cyber-Physical Systems
GroupedDBID .DC
0R~
29I
4.4
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACIWK
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AIBXA
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
F5P
HZ~
H~9
IFIPE
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNS
VJK
AAYXX
CITATION
7SC
7SP
7TB
8FD
FR3
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c291t-e09e6b5e2127023575920ce946b0a141fe9fae4d8c5a4f3d4ca1aad594ca4b9e3
IEDL.DBID RIE
ISICitedReferencesCount 38
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000733164600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1552-3098
IngestDate Sun Nov 09 06:57:58 EST 2025
Tue Nov 18 22:37:10 EST 2025
Sat Nov 29 01:47:28 EST 2025
Wed Aug 27 02:49:41 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 1
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-c291t-e09e6b5e2127023575920ce946b0a141fe9fae4d8c5a4f3d4ca1aad594ca4b9e3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-4319-3135
0000-0003-0074-7836
0000-0003-1884-5397
0000-0001-9951-5255
PQID 2626972553
PQPubID 27625
PageCount 21
ParticipantIDs ieee_primary_9610021
crossref_primary_10_1109_TRO_2021_3094984
crossref_citationtrail_10_1109_TRO_2021_3094984
proquest_journals_2626972553
PublicationCentury 2000
PublicationDate 2022-Feb.
2022-2-00
20220201
PublicationDateYYYYMMDD 2022-02-01
PublicationDate_xml – month: 02
  year: 2022
  text: 2022-Feb.
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on robotics
PublicationTitleAbbrev TRO
PublicationYear 2022
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref57
ref56
ref59
ref58
Yang (ref69) 2020; 33
ref53
ref52
ref55
ref54
ref51
ref50
ref46
ref45
ref48
ref47
ref42
ref41
ref44
ref43
ref49
ref8
ref7
ref9
ref4
ref3
ref6
ref5
ref100
ref101
ref40
ref35
ref34
ref37
ref36
ref31
ref30
ref33
ref32
ref39
ref38
ref24
ref26
ref25
ref20
ref21
Liu (ref97)
ref28
ref27
ref29
ref13
ref12
ref15
ref14
Shalev-Shwartz (ref22) 2017
ref96
ref11
ref99
ref10
ref98
ref17
ref16
Bustos (ref72) 2019
ref19
ref18
ref93
ref92
ref95
ref94
ref91
ref90
ref89
ref86
ref85
ref88
ref87
ref82
ref81
ref84
ref83
ref80
ref79
ref78
ref75
ref74
ref105
ref77
ref102
ref76
ref103
ref2
ref1
EASA (ref23) 2020
ref71
ref70
ref73
ref68
ref67
ref64
ref63
ref66
ref65
Foster (ref104) 2015
ref60
ref62
ref61
References_xml – ident: ref87
  doi: 10.1016/j.actaastro.2012.08.011
– ident: ref9
  doi: 10.1145/2185520.2185526
– ident: ref32
  doi: 10.1109/ICCV.2019.00175
– ident: ref73
  doi: 10.1109/34.121791
– ident: ref86
  doi: 10.1109/ICRA.2011.5979612
– ident: ref21
  doi: 10.1109/ICRA.2012.6224709
– ident: ref65
  doi: 10.1007/978-3-319-10590-1_8
– ident: ref51
  doi: 10.1561/2300000047
– ident: ref56
  doi: 10.1109/CVPR.2019.00446
– ident: ref24
  doi: 10.1109/ICCVW.2019.00343
– ident: ref91
  doi: 10.1016/j.cviu.2018.08.001
– ident: ref39
  doi: 10.1109/WACV.2014.6836101
– ident: ref102
  doi: 10.1109/CDC.2018.8619401
– ident: ref53
  doi: 10.1109/CVPR.2016.445
– ident: ref20
  doi: 10.1109/ICRA.2011.5979949
– ident: ref42
  doi: 10.1016/j.isprsjprs.2016.01.010
– ident: ref11
  doi: 10.1016/S1361-8415(00)00014-1
– ident: ref63
  doi: 10.1109/CVPR.2016.631
– year: 2017
  ident: ref22
  article-title: On a formal model of safe and scalable self-driving cars
– ident: ref93
  doi: 10.1115/1.3662552
– ident: ref83
  doi: 10.1109/CVPR.2014.71
– ident: ref84
  doi: 10.15607/RSS.2012.VIII.040
– ident: ref18
  doi: 10.1002/SERIES1345
– ident: ref80
  doi: 10.1109/TPAMI.2018.2816031
– ident: ref90
  doi: 10.1093/imaiai/iat005
– ident: ref94
  doi: 10.1109/FOCS.2016.85
– ident: ref29
  doi: 10.1109/TRO.2021.3094984
– ident: ref101
  doi: 10.1109/TCNS.2016.2606880
– ident: ref48
  doi: 10.1177/0278364914523689
– ident: ref33
  article-title: Table of the standard normal distribution
– ident: ref40
  doi: 10.1007/978-3-319-10593-2_31
– ident: ref97
  article-title: High dimensional robust estimation of sparse models via trimmed hard thresholding
– ident: ref13
  doi: 10.1109/ICCV.1999.790410
– ident: ref35
  doi: 10.1007/BF01588971
– ident: ref38
  doi: 10.1063/1.3047921
– ident: ref89
  doi: 10.1109/IROS.2013.6696406
– ident: ref36
  doi: 10.1007/978-3-319-10602-1_50
– ident: ref4
  doi: 10.1109/TRO.2020.3033695
– ident: ref7
  doi: 10.1109/ICRA.2015.7139486
– ident: ref1
  doi: 10.1109/ICRA.2013.6630557
– ident: ref44
  doi: 10.1109/TPAMI.2016.2605097
– ident: ref76
  doi: 10.1109/34.809117
– ident: ref10
  doi: 10.1109/ISMAR.2007.4538852
– ident: ref16
  doi: 10.2200/S00757ED1V01Y201702COV011
– ident: ref14
  doi: 10.1109/CVPR.2019.00569
– ident: ref47
  doi: 10.1109/TRO.2016.2544304
– ident: ref79
  doi: 10.1007/978-3-642-37444-9_42
– ident: ref66
  doi: 10.1109/TPAMI.2015.2513405
– ident: ref49
  doi: 10.1007/BF00127126
– ident: ref103
  doi: 10.1017/CBO9780511804441
– year: 2019
  ident: ref72
  article-title: A practical maximum clique algorithm for matching with pairwise constraints
– ident: ref74
  doi: 10.1109/ROBOT.2009.5152473
– ident: ref25
  doi: 10.1109/IROS40897.2019.8968174
– ident: ref3
  doi: 10.1109/TRO.2016.2624754
– volume: 33
  volume-title: Proc. Conf. Neural Inf. Process. Syst.
  year: 2020
  ident: ref69
  article-title: One ring to rule them all: Certifiably robust geometric perception with outliers
– ident: ref43
  doi: 10.1007/978-3-642-33765-9_41
– ident: ref17
  doi: 10.1109/TPAMI.2017.2773482
– ident: ref15
  doi: 10.1007/978-3-030-01258-8_43
– ident: ref8
  doi: 10.1145/2897824.2925913
– volume-title: Concepts of Design Assurance for Neural Networks
  year: 2020
  ident: ref23
– ident: ref77
  doi: 10.1109/TPAMI.1987.4767965
– ident: ref57
  doi: 10.1109/LRA.2021.3061331
– ident: ref82
  doi: 10.1109/TPAMI.2003.1217599
– ident: ref52
  doi: 10.1109/CVPR42600.2020.00138
– ident: ref96
  doi: 10.1109/TAC.2013.2266831
– ident: ref46
  doi: 10.1109/IROS.2015.7353364
– ident: ref34
  article-title: Table of the Chi-square distribution
– ident: ref37
  doi: 10.1007/978-3-319-14612-6_4
– start-page: 696
  volume-title: Proc. Conf. Learn. Theory
  year: 2015
  ident: ref104
  article-title: Variable selection is hard
– ident: ref70
  doi: 10.1109/LRA.2018.2793352
– ident: ref98
  doi: 10.1002/widm.2
– ident: ref61
  doi: 10.1109/ICCV.2009.5459398
– ident: ref92
  doi: 10.1214/aoms/1177703732
– ident: ref30
  doi: 10.1002/SERIES1345
– ident: ref71
  doi: 10.15607/RSS.2019.XV.003
– ident: ref41
  doi: 10.1109/CVPR.2017.595
– ident: ref58
  doi: 10.1007/978-3-319-10605-2_52
– ident: ref59
  doi: 10.1007/s11263-008-0186-9
– ident: ref100
  doi: 10.1109/TSP.2017.2771720
– ident: ref81
  doi: 10.1007/978-3-319-10590-1_9
– ident: ref28
  doi: 10.1109/ICRA.2018.8460217
– ident: ref45
  doi: 10.1109/ICRA.2015.7139836
– ident: ref99
  doi: 10.1109/TIT.2011.2146690
– ident: ref19
  doi: 10.1007/BF00131148
– ident: ref60
  doi: 10.1109/CVPR.2011.5995640
– ident: ref50
  doi: 10.1137/S0036144598345802
– ident: ref68
  doi: 10.1109/CVPR.2008.4587757
– ident: ref85
  doi: 10.1109/IROS.2012.6385590
– ident: ref55
  doi: 10.1007/978-3-319-46475-6_47
– ident: ref2
  doi: 10.1145/358669.358692
– ident: ref54
  doi: 10.1109/ICCV.2013.70
– ident: ref6
  doi: 10.1109/CVPR.2015.7299195
– ident: ref78
  doi: 10.1364/josaa.4.000629
– ident: ref27
  doi: 10.1109/LRA.2020.2965893
– ident: ref64
  doi: 10.1007/978-3-030-28619-4_49
– ident: ref31
  doi: 10.1109/LRA.2019.2894852
– ident: ref12
  doi: 10.1177/0278364918784361
– ident: ref105
  doi: 10.2307/2681802
– ident: ref75
  doi: 10.1109/ICCV.2019.00905
– ident: ref95
  doi: 10.1109/TIT.2005.858979
– ident: ref62
  doi: 10.1109/CVPR.2017.536
– ident: ref67
  doi: 10.1007/978-3-642-33718-5_53
– ident: ref5
  doi: 10.1109/CVPR42600.2020.00070
– ident: ref26
  doi: 10.1017/CBO9780511804090
– ident: ref88
  doi: 10.7551/mitpress/9816.003.0035
SSID ssj0024903
Score 2.556039
Snippet Nonlinear estimation in robotics and vision is typically plagued with outliers due to wrong data association or incorrect detections from signal processing and...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 281
SubjectTerms Adaptive algorithms
Algorithms
Approximation algorithms
autonomous systems
Combinatorial analysis
computational complexity
computer vision
Estimation
Formulations
Inliers (landforms)
Machine learning
maximum likelihood estimation
Measurement uncertainty
Object recognition
Optimization
Outliers (statistics)
Particle measurements
Polynomials
Probabilistic logic
resilient perception
Robotics
robust estimation
Robustness
Signal processing
Signal processing algorithms
Simultaneous localization and mapping
Title Outlier-Robust Estimation: Hardness, Minimally Tuned Algorithms, and Applications
URI https://ieeexplore.ieee.org/document/9610021
https://www.proquest.com/docview/2626972553
Volume 38
WOSCitedRecordID wos000733164600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1941-0468
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0024903
  issn: 1552-3098
  databaseCode: RIE
  dateStart: 20040101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS8MwFA9zeNCDX1OcTunBi7BsaZt-xNuQDQ-66ZiyW0mzVx3UVrpW8L83Sbs5UQRvaZqU8l7z8l5_eb-H0IUT-lHkUI5JKAimlHqYM59iQTgH0wqdMov_6dYbDv3plN3XUHuVCwMA-vAZdFRTY_mzVBTqV1mXuYowVMY6G57nlrlaX7x6TFdBVoxi2CbMX0KShHUn45EMBC2zI_sp8-m3LUjXVPlhiPXuMtj933vtoZ3KizR6pdr3UQ2SA7S9xi3YQA-jIpf-ZYbHaVgscqMv13KZpnhlKLhembi2cTdPZG8cfxiTQhpcoxc_p9k8f3mV93gir9fw7UP0OOhPrm9wVT8BC4uZOQbCwA0dUCTumtbGYRYRwKgbEm5SMwIWcaAzXzicRvaMCm5yPnOYbNCQgX2E6kmawDEyFDoIQtGa-tKBElYo_TD5TG55ERUuQBN1lyINREUurmpcxIEOMggLpBICpYSgUkITXa5mvJXEGn-MbSihr8ZV8m6i1lJrQbXyFoElIzTmyUDJPvl91inaslQKgz553UL1PCvgDG2K93y-yM71R_UJT_3JUw
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dT8IwEL8QNFEf_EIjiroHX0wodKOD1TdiIBr5UIKGt6UrNyXBYWAz8b-3LQMxGhPfuq5dlrv1er9d73cAF27ghaHLBKGBpIQxViOCe4xIKgTaTuDOs_ifWrVOxxsM-H0GistcGEQ0h8-wpJsmlj-cyET_KivzqiYMVVhnTVfOSrO1vpj1uKmDrDnFSIVybxGUpLzc73UVFHTskupn3GPfNiFTVeWHKTb7S3Pnf2-2C9upH2nV54rfgwxG-7C1wi6Yg4duEisPc0p6kyCZxVZDreZ5ouKVpQP22sgVrfYoUr3j8YfVT5TJterj58l0FL-8qnsiUtcrEe4DeGw2-tc3JK2gQKTD7Zgg5VgNXNQ07obYxuUOlchZNaDCZnaIPBTIhp50BQsrQyaFLcTQ5arBAo6VQ8hGkwiPwNLxQZSa2NRTLpR0AuWJqWcKpxYyWUXMQ3khUl-m9OK6ysXYNzCDcl8pwddK8FMl5OFyOeNtTq3xx9icFvpyXCrvPBQWWvPTtTfzHYXReE1Bpcrx77POYeOm3275rdvO3QlsOjqhwZzDLkA2niZ4CuvyPR7NpmfmA_sE-MvMnA
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=Outlier-Robust+Estimation%3A+Hardness%2C+Minimally+Tuned+Algorithms%2C+and+Applications&rft.jtitle=IEEE+transactions+on+robotics&rft.au=Antonante%2C+Pasquale&rft.au=Tzoumas%2C+Vasileios&rft.au=Yang%2C+Heng&rft.au=Carlone%2C+Luca&rft.date=2022-02-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=1552-3098&rft.eissn=1941-0468&rft.volume=38&rft.issue=1&rft.spage=281&rft_id=info:doi/10.1109%2FTRO.2021.3094984&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1552-3098&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1552-3098&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1552-3098&client=summon