Leveraging Geometric Modeling-Based Computer Vision for Context Aware Control in a Hip Exosuit

Human beings adapt their motor patterns in response to their surroundings, utilizing sensory modalities such as visual inputs. This context-informed adaptive motor behavior has increased interest in integrating computer vision (CV) algorithms into robotic assistive technologies, marking a shift towa...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on robotics Jg. 41; S. 3462 - 3479
Hauptverfasser: Tricomi, Enrica, Piccolo, Giuseppe, Russo, Federica, Zhang, Xiaohui, Missiroli, Francesco, Ferrari, Sandro, Gionfrida, Letizia, Ficuciello, Fanny, Xiloyannis, Michele, Masia, Lorenzo
Format: Journal Article
Sprache:Englisch
Veröffentlicht: IEEE 2025
Schlagworte:
ISSN:1552-3098, 1941-0468
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Human beings adapt their motor patterns in response to their surroundings, utilizing sensory modalities such as visual inputs. This context-informed adaptive motor behavior has increased interest in integrating computer vision (CV) algorithms into robotic assistive technologies, marking a shift toward context aware control . However, such integration has rarely been achieved so far, with current methods mostly relying on data-driven approaches. In this study, we introduce a novel control framework for a soft hip exosuit, employing instead a physics-informed CV method grounded on geometric modeling of the captured scene for assistance tuning during stairs and level walking. This approach promises to provide a viable solution that is more computationally efficient and does not depend on training examples. Evaluating the controller with six subjects on a path comprising level walking and stairs, we achieved an overall detection accuracy of <inline-formula><tex-math notation="LaTeX">93.0\pm 1.1\%</tex-math></inline-formula>. CV-based assistance provided significantly greater metabolic benefits compared to non-vision-based assistance, with larger energy reductions relative to being unassisted during stair ascent (<inline-formula><tex-math notation="LaTeX">-18.9 \pm 4.1\%</tex-math></inline-formula> versus <inline-formula><tex-math notation="LaTeX">-5.2 \pm 4.1\%</tex-math></inline-formula>) and descent (<inline-formula><tex-math notation="LaTeX">-10.1 \pm 3.6\%</tex-math></inline-formula> versus <inline-formula><tex-math notation="LaTeX">-4.7 \pm 4.8\%</tex-math></inline-formula>). Such a result is a consequence of the adaptive nature of the device, enabled by the context aware controller that allowed for more effective walking support, i.e., the assistive torque showed a significant increase while ascending stairs (<inline-formula><tex-math notation="LaTeX">+33.9\pm 8.8\%</tex-math></inline-formula>) and decrease while descending stairs (<inline-formula><tex-math notation="LaTeX">-17.4\pm 6.0\%</tex-math></inline-formula>) compared to a condition without assistance modulation enabled by vision. These results highlight the potential of the approach, promoting effective real-time embedded applications in assistive robotics.
AbstractList Human beings adapt their motor patterns in response to their surroundings, utilizing sensory modalities such as visual inputs. This context-informed adaptive motor behavior has increased interest in integrating computer vision (CV) algorithms into robotic assistive technologies, marking a shift toward context aware control . However, such integration has rarely been achieved so far, with current methods mostly relying on data-driven approaches. In this study, we introduce a novel control framework for a soft hip exosuit, employing instead a physics-informed CV method grounded on geometric modeling of the captured scene for assistance tuning during stairs and level walking. This approach promises to provide a viable solution that is more computationally efficient and does not depend on training examples. Evaluating the controller with six subjects on a path comprising level walking and stairs, we achieved an overall detection accuracy of <inline-formula><tex-math notation="LaTeX">93.0\pm 1.1\%</tex-math></inline-formula>. CV-based assistance provided significantly greater metabolic benefits compared to non-vision-based assistance, with larger energy reductions relative to being unassisted during stair ascent (<inline-formula><tex-math notation="LaTeX">-18.9 \pm 4.1\%</tex-math></inline-formula> versus <inline-formula><tex-math notation="LaTeX">-5.2 \pm 4.1\%</tex-math></inline-formula>) and descent (<inline-formula><tex-math notation="LaTeX">-10.1 \pm 3.6\%</tex-math></inline-formula> versus <inline-formula><tex-math notation="LaTeX">-4.7 \pm 4.8\%</tex-math></inline-formula>). Such a result is a consequence of the adaptive nature of the device, enabled by the context aware controller that allowed for more effective walking support, i.e., the assistive torque showed a significant increase while ascending stairs (<inline-formula><tex-math notation="LaTeX">+33.9\pm 8.8\%</tex-math></inline-formula>) and decrease while descending stairs (<inline-formula><tex-math notation="LaTeX">-17.4\pm 6.0\%</tex-math></inline-formula>) compared to a condition without assistance modulation enabled by vision. These results highlight the potential of the approach, promoting effective real-time embedded applications in assistive robotics.
Author Piccolo, Giuseppe
Gionfrida, Letizia
Missiroli, Francesco
Russo, Federica
Zhang, Xiaohui
Tricomi, Enrica
Ficuciello, Fanny
Xiloyannis, Michele
Ferrari, Sandro
Masia, Lorenzo
Author_xml – sequence: 1
  givenname: Enrica
  orcidid: 0000-0002-9117-4385
  surname: Tricomi
  fullname: Tricomi, Enrica
  email: enrica.tricomi@ziti.uni-heidelberg.de
  organization: Institut für Technische Informatik (ZITI), Heidelberg University, Heidelberg, Germany
– sequence: 2
  givenname: Giuseppe
  surname: Piccolo
  fullname: Piccolo, Giuseppe
  organization: ICAROS Center, University of Naples Federico II, Naples, Italy
– sequence: 3
  givenname: Federica
  surname: Russo
  fullname: Russo, Federica
  organization: ICAROS Center, University of Naples Federico II, Naples, Italy
– sequence: 4
  givenname: Xiaohui
  orcidid: 0000-0001-8438-546X
  surname: Zhang
  fullname: Zhang, Xiaohui
  email: xiaohui.zhang@ziti.uni-heidelberg.de
  organization: Institut für Technische Informatik (ZITI), Heidelberg University, Heidelberg, Germany
– sequence: 5
  givenname: Francesco
  orcidid: 0000-0002-2184-9981
  surname: Missiroli
  fullname: Missiroli, Francesco
  organization: Institut für Technische Informatik (ZITI), Heidelberg University, Heidelberg, Germany
– sequence: 6
  givenname: Sandro
  orcidid: 0000-0002-1635-3746
  surname: Ferrari
  fullname: Ferrari, Sandro
  organization: Institut für Technische Informatik (ZITI), Heidelberg University, Heidelberg, Germany
– sequence: 7
  givenname: Letizia
  orcidid: 0000-0002-0992-6526
  surname: Gionfrida
  fullname: Gionfrida, Letizia
  organization: Department of Informatics, Faculty of Natural Mathematics and Engineering Sciences, King's College London, London, U.K
– sequence: 8
  givenname: Fanny
  orcidid: 0000-0001-9214-9977
  surname: Ficuciello
  fullname: Ficuciello, Fanny
  organization: ICAROS Center, University of Naples Federico II, Naples, Italy
– sequence: 9
  givenname: Michele
  orcidid: 0000-0001-8415-7854
  surname: Xiloyannis
  fullname: Xiloyannis, Michele
  organization: Akina AG, Zürich, Switzerland
– sequence: 10
  givenname: Lorenzo
  orcidid: 0000-0003-2402-7139
  surname: Masia
  fullname: Masia, Lorenzo
  organization: Department of Computer Engineering, School of Computation, Information and Technology, Technical University of Munich (TUM), Munich, Germany
BookMark eNpNkEFPAjEUhBuDiYDePXjoH1h83ba72yMSBBMMiUGPbtrtW1IDW9IuCv_eRTh4evMmM3P4BqTX-AYJuWcwYgzU4-ptOUohlSMus1wU6or0mRIsAZEVvU5LmSYcVHFDBjF-AaRCAe-TzwV-Y9Br16zpDP0W2-Aq-uotbjoredIRLZ347W7fYqAfLjrf0NqHzmtaPLR0_KMD_n3Bb6hrqKZzt6PTg497196S61pvIt5d7pC8P09Xk3myWM5eJuNFUqVMtQnLTQGCQ26FAZUbBUIaY1SukVkuwHImBZoUpE2V1FUlKmWNzqzITKZ1zYcEzrtV8DEGrMtdcFsdjiWD8sSn7PiUJz7lhU9XeThXHCL-i6tCScH5Lw3HZDU
CODEN ITREAE
Cites_doi 10.1109/LRA.2023.3256135
10.1109/AIM.2001.936909
10.1109/34.295913
10.1109/CVPR.2012.6247665
10.1038/s41597-023-02840-6
10.1109/TRO.2021.3084466
10.3389/fnbot.2021.730965
10.1109/TCYB.2020.2978216
10.1139/apnm-2017-0781
10.1186/1743-0003-12-1
10.1109/TBME.2017.2776157
10.1186/s12984-021-00946-9
10.1109/LRA.2022.3173426
10.1109/EMBC.2019.8857420
10.1109/EMBC.2018.8513442
10.1152/japplphysiol.00445.2014
10.1016/S0966-6362(01)00181-3
10.1186/s12938-024-01216-0
10.1145/358669.358692
10.1109/IROS.2010.5649411
10.1109/TMRB.2024.3349602
10.1109/LRA.2022.3183791
10.1007/978-3-319-16199-0_32
10.1109/TMECH.2023.3322269
10.1109/IRC.2019.00031
10.1109/LRA.2021.3136240
10.1016/j.cviu.2016.04.007
10.3389/frobt.2020.562061
10.1109/ROBOT.2005.1570837
10.1109/LRA.2023.3337693
10.1109/TNSRE.2019.2895221
10.1109/EMBC.2016.7591863
10.1038/s42256-023-00662-0
10.1016/S0966-6362(01)00162-X
10.1109/ICORR55369.2022.9896501
10.1186/s12984-015-0090-9
10.1038/s41598-021-04540-w
10.1109/ICORR.2019.8779540
10.1016/j.bdr.2015.04.001
10.1109/TNSRE.2016.2521160
10.1002/9780470549148
10.1016/j.image.2017.05.009
10.3390/s19224887
10.1109/TBME.2015.2448457
10.1007/978-981-19-6901-0_116
10.1126/scirobotics.aah4416
10.1302/0301-620X.49B4.774
10.1126/scirobotics.aav2949
10.1109/EMBC46164.2021.9630064
ContentType Journal Article
DBID 97E
RIA
RIE
AAYXX
CITATION
DOI 10.1109/TRO.2025.3567489
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Xplore
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
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 3479
ExternalDocumentID 10_1109_TRO_2025_3567489
10989543
Genre orig-research
GrantInformation_xml – fundername: Carl Zeiss Foundation
  grantid: P2019-01-003
– fundername: Istituto nazionale per l'assicurazione contro gli infortuni sul lavoro
  grantid: PR23-RR-P1
– fundername: Robotics Institute Germany
– fundername: German Federal Ministry of Education and Research
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
ID FETCH-LOGICAL-c219t-17b804307d4b097b9045bbb97ae1d340d3154eb205d295acc4c9dba6d46b6aaf3
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001497954000012&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 Sat Nov 29 07:53:31 EST 2025
Wed Aug 27 01:50:38 EDT 2025
IsPeerReviewed true
IsScholarly true
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-c219t-17b804307d4b097b9045bbb97ae1d340d3154eb205d295acc4c9dba6d46b6aaf3
ORCID 0000-0001-9214-9977
0000-0002-1635-3746
0000-0001-8438-546X
0000-0003-2402-7139
0000-0002-9117-4385
0000-0002-2184-9981
0000-0001-8415-7854
0000-0002-0992-6526
PageCount 18
ParticipantIDs ieee_primary_10989543
crossref_primary_10_1109_TRO_2025_3567489
PublicationCentury 2000
PublicationDate 20250000
2025-00-00
PublicationDateYYYYMMDD 2025-01-01
PublicationDate_xml – year: 2025
  text: 20250000
PublicationDecade 2020
PublicationTitle IEEE transactions on robotics
PublicationTitleAbbrev TRO
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
References ref13
ref12
ref15
ref14
ref53
ref52
ref11
ref10
ref16
ref19
ref18
ref51
ref50
ref46
Khademi (ref17) 2019
ref45
ref48
ref47
ref42
ref41
ref43
ref49
ref8
ref7
ref9
Peronnet (ref44) 1991; 16
ref4
ref3
ref6
ref5
ref40
ref35
ref34
ref36
ref31
ref30
ref33
ref32
Changizi (ref1) 2010
ref2
ref39
ref38
(ref37) 1997
ref24
ref23
ref26
ref25
ref20
ref22
ref21
ref28
ref27
ref29
References_xml – ident: ref5
  doi: 10.1109/LRA.2023.3256135
– ident: ref31
  doi: 10.1109/AIM.2001.936909
– ident: ref36
  doi: 10.1109/34.295913
– ident: ref38
  doi: 10.1109/CVPR.2012.6247665
– ident: ref3
  doi: 10.1038/s41597-023-02840-6
– ident: ref52
  doi: 10.1109/TRO.2021.3084466
– ident: ref7
  doi: 10.3389/fnbot.2021.730965
– ident: ref48
  doi: 10.1109/TCYB.2020.2978216
– ident: ref45
  doi: 10.1139/apnm-2017-0781
– ident: ref13
  doi: 10.1186/1743-0003-12-1
– ident: ref28
  doi: 10.1109/TBME.2017.2776157
– ident: ref47
  doi: 10.1186/s12984-021-00946-9
– ident: ref11
  doi: 10.1109/LRA.2022.3173426
– ident: ref19
  doi: 10.1109/EMBC.2019.8857420
– ident: ref16
  doi: 10.1109/EMBC.2018.8513442
– volume-title: International Building Code
  year: 1997
  ident: ref37
– ident: ref46
  doi: 10.1152/japplphysiol.00445.2014
– issue: V001T07A005
  volume-title: Proc. Dynamic Syst. Control Conf.
  year: 2019
  ident: ref17
  article-title: Convolutional neural networks for environmentally aware locomotion mode recognition of lower-limb amputees
– ident: ref50
  doi: 10.1016/S0966-6362(01)00181-3
– ident: ref53
  doi: 10.1186/s12938-024-01216-0
– ident: ref35
  doi: 10.1145/358669.358692
– ident: ref30
  doi: 10.1109/IROS.2010.5649411
– ident: ref32
  doi: 10.1109/TMRB.2024.3349602
– ident: ref41
  doi: 10.1109/LRA.2022.3183791
– ident: ref26
  doi: 10.1007/978-3-319-16199-0_32
– ident: ref12
  doi: 10.1109/TMECH.2023.3322269
– ident: ref15
  doi: 10.1109/IRC.2019.00031
– ident: ref39
  doi: 10.1109/LRA.2021.3136240
– ident: ref33
  doi: 10.1016/j.cviu.2016.04.007
– ident: ref23
  doi: 10.3389/frobt.2020.562061
– ident: ref27
  doi: 10.1109/ROBOT.2005.1570837
– ident: ref9
  doi: 10.1109/LRA.2023.3337693
– volume-title: The Vision Revolution: How the Latest Research Overturns Everything We Thought we Knew About Human Vision
  year: 2010
  ident: ref1
– ident: ref20
  doi: 10.1109/TNSRE.2019.2895221
– ident: ref29
  doi: 10.1109/EMBC.2016.7591863
– ident: ref25
  doi: 10.1038/s42256-023-00662-0
– ident: ref40
  doi: 10.1016/S0966-6362(01)00162-X
– ident: ref49
  doi: 10.1109/ICORR55369.2022.9896501
– ident: ref43
  doi: 10.1186/s12984-015-0090-9
– ident: ref2
  doi: 10.1038/s41598-021-04540-w
– ident: ref18
  doi: 10.1109/ICORR.2019.8779540
– ident: ref21
  doi: 10.1016/j.bdr.2015.04.001
– ident: ref4
  doi: 10.1109/TNSRE.2016.2521160
– ident: ref42
  doi: 10.1002/9780470549148
– ident: ref34
  doi: 10.1016/j.image.2017.05.009
– ident: ref14
  doi: 10.3390/s19224887
– ident: ref24
  doi: 10.1109/TBME.2015.2448457
– ident: ref22
  doi: 10.1007/978-981-19-6901-0_116
– ident: ref8
  doi: 10.1126/scirobotics.aah4416
– ident: ref51
  doi: 10.1302/0301-620X.49B4.774
– ident: ref10
  doi: 10.1126/scirobotics.aav2949
– volume: 16
  start-page: 23
  issue: 1
  year: 1991
  ident: ref44
  article-title: Table of nonprotein respiratory quotient: An update
  publication-title: Can. J. Sport Sci.
– ident: ref6
  doi: 10.1109/EMBC46164.2021.9630064
SSID ssj0024903
Score 2.4431818
Snippet Human beings adapt their motor patterns in response to their surroundings, utilizing sensory modalities such as visual inputs. This context-informed adaptive...
SourceID crossref
ieee
SourceType Index Database
Publisher
StartPage 3462
SubjectTerms Adaptive walking assistance
Cameras
Computer vision
exosuits
Geometric modeling
geometric modeling (GM)
Hip
Legged locomotion
physics-informed computer vision (CV)
Real-time systems
Robot vision systems
Robots
Stairs
Training
Title Leveraging Geometric Modeling-Based Computer Vision for Context Aware Control in a Hip Exosuit
URI https://ieeexplore.ieee.org/document/10989543
Volume 41
WOSCitedRecordID wos001497954000012&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/eLvHCXMwlV07T8MwELZoxQADzyLKSx5YGFLSxIntsaCWDlVBqKBORH5FqgRJlabQn8_ZSUUZGNjsyImiO-cevtz3IXQdyBQ8g60PRmACiVAp2EGeekoylnLKmTYOxHVEx2M2nfKnulnd9cIYY9zPZ6Zjh66Wr3O1tEdl8IVzxiMSNlCDUlo1a_0A63FHg2whxbwQFq5rkj6_nTw_QiYYRJ0wstwa_JcP2iBVcT5lsP_PtzlAe3XwiHuVtg_RlsmO0O4GpOAxehsZ2JyOegg_mPzDEmYpbBnPbN-5dwdOS-M1lQN-dZ3lGAJX7GCqViXufYnCuFmRv-NZhgUezua4v8oXy1nZQi-D_uR-6NUcCp4CW1R6XSqZhfWimkifU8khhJNScipMV4fE1yHEUJBd-5EOeCSUIoprKWJNYhkLkYYnqJnlmTlFWAYwZV3FpSFEMlCjDOBxMQy1AYPbRjdrqSbzCiojcSmGzxPQQGI1kNQaaKOWFejGukqWZ39cP0c79vbq7OMCNctiaS7RtvosZ4viym2Eb9cbsYk
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELagIAEDzyLK0wMLQ0oeTmKPBRWKCAWhgjoRxY9IkSCp0hT68zk7rSgDA5sdWVZ059zDl_s-hM5dnoJn0PVBH0wgSUQKdpClluCUpixkVCoD4hqF_T4dDtnTrFnd9MIopczPZ6qth6aWLwsx0Vdl8IUzynziLaMVnxDXqdu1fqD1mCFC1qBilgdL51VJm10Onh8hF3T9tudrdg32ywst0KoYr3Kz9c_32Uabs_ARd2p976Alle-ijQVQwT30Fik4noZ8CN-q4kNTZgmsOc9057l1BW5L4jmZA341veUYQldsgKqmFe58JaUys7J4x1mOE9zLRrg7LcaTrGqil5vu4LpnzVgULAHWqLKckFMN7BVKwm0WcgZBHOechYlypEds6UEUBfm17UuX-YkQRDDJk0CSgAdJknr7qJEXuTpAmLswpY5gXBHCKSiSu7BdAEOpwOS20MVcqvGoBsuITZJhsxg0EGsNxDMNtFBTC3RhXS3Lwz-en6G13uAhiqO7_v0RWtdb1Tchx6hRlRN1glbFZ5WNy1NzKL4BQei00A
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=Leveraging+Geometric+Modeling-Based+Computer+Vision+for+Context+Aware+Control+in+a+Hip+Exosuit&rft.jtitle=IEEE+transactions+on+robotics&rft.au=Tricomi%2C+Enrica&rft.au=Piccolo%2C+Giuseppe&rft.au=Russo%2C+Federica&rft.au=Zhang%2C+Xiaohui&rft.date=2025&rft.pub=IEEE&rft.issn=1552-3098&rft.volume=41&rft.spage=3462&rft.epage=3479&rft_id=info:doi/10.1109%2FTRO.2025.3567489&rft.externalDocID=10989543
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