Learning Deformable Linear Object Dynamics From a Single Trajectory

The dynamic manipulation of deformable objects poses a significant challenge in robotics. While model-based approaches for controlling such objects hold significant potential, their effectiveness hinges on the availability of an accurate and computationally efficient dynamics model. This work focuse...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE robotics and automation letters Ročník 10; číslo 7; s. 7635 - 7642
Hlavní autoři: Mamedov, Shamil, Geist, A. Rene, Viljoen, Ruan, Trimpe, Sebastian, Swevers, Jan
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 01.07.2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
and learning for soft robots
Computational modeling
control
Deformable models
Deformation
Discretization
Dynamics
flexible robotics
Formability
Heuristic algorithms
Kinematics
Learning
Mathematical models
Model learning for control
modeling
Neural networks
Numerical models
Physical properties
Predictive models
Rigid structures
Robotics
Robots
ISSN:2377-3766, 2377-3766
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract The dynamic manipulation of deformable objects poses a significant challenge in robotics. While model-based approaches for controlling such objects hold significant potential, their effectiveness hinges on the availability of an accurate and computationally efficient dynamics model. This work focuses on sample-efficient learning of models to capture the dynamic behavior of deformable linear objects (DLOs). Inspired by the pseudo-rigid body method, we present a physics-informed neural ODE that approximates a DLO as a serial chain of rigid bodies interconnected by passive elastic joints. However, unlike traditional uniform spatial discretization and linear spring-damper joints, our approach involves learning-based discretization and nonlinear elastic joints that characterize interaction forces via a neural network. Through real-world and simulation experiments involving DLOs with markedly different physical properties, we demonstrate the model's ability to accurately predict DLO motion.
AbstractList The dynamic manipulation of deformable objects poses a significant challenge in robotics. While model-based approaches for controlling such objects hold significant potential, their effectiveness hinges on the availability of an accurate and computationally efficient dynamics model. This work focuses on sample-efficient learning of models to capture the dynamic behavior of deformable linear objects (DLOs). Inspired by the pseudo-rigid body method, we present a physics-informed neural ODE that approximates a DLO as a serial chain of rigid bodies interconnected by passive elastic joints. However, unlike traditional uniform spatial discretization and linear spring-damper joints, our approach involves learning-based discretization and nonlinear elastic joints that characterize interaction forces via a neural network. Through real-world and simulation experiments involving DLOs with markedly different physical properties, we demonstrate the model's ability to accurately predict DLO motion.
Author Swevers, Jan
Mamedov, Shamil
Geist, A. Rene
Trimpe, Sebastian
Viljoen, Ruan
Author_xml – sequence: 1
  givenname: Shamil
  orcidid: 0000-0002-5381-7976
  surname: Mamedov
  fullname: Mamedov, Shamil
  email: shamilnmamedov@gmail.com
  organization: MECO Research Team, KU Leuven and Flanders Make@KU Leuven, Heverlee, Belgium
– sequence: 2
  givenname: A. Rene
  orcidid: 0000-0003-2551-2419
  surname: Geist
  fullname: Geist, A. Rene
  organization: Institute for Data Science in Mechanical Engineering, RWTH Aachen University, Aachen, Germany
– sequence: 3
  givenname: Ruan
  orcidid: 0000-0001-7883-9381
  surname: Viljoen
  fullname: Viljoen, Ruan
  organization: MECO Research Team, KU Leuven and Flanders Make@KU Leuven, Heverlee, Belgium
– sequence: 4
  givenname: Sebastian
  orcidid: 0000-0002-2785-2487
  surname: Trimpe
  fullname: Trimpe, Sebastian
  organization: Institute for Data Science in Mechanical Engineering, RWTH Aachen University, Aachen, Germany
– sequence: 5
  givenname: Jan
  orcidid: 0000-0003-2034-5519
  surname: Swevers
  fullname: Swevers, Jan
  organization: MECO Research Team, KU Leuven and Flanders Make@KU Leuven, Heverlee, Belgium
BookMark eNpNkE1LAzEQhoMoWGvvHjwEPG_Nx2anOZbWqrBQ0HoO2e1EtnSTmrSH_ntTWtDLzDDzzMzLe0euffBIyANnY86Zfq4_pmPBhBpLBVAKfkUGQgIUEqrq-l99S0YpbRhjXAmQWg3IrEYbfee_6RxdiL1ttkjrzucuXTYbbPd0fvS279pEFzH01NLPTGdoFe1pHOLxntw4u004uuQh-Vq8rGZvRb18fZ9N66IVJewLi6WVKHHNmHOV4roFXDfK2WY9kaVoWu0AFNPCZYHCApbQZpFOQ9MgF1YOydP57i6GnwOmvdmEQ_T5pZGC64kWOWaKnak2hpQiOrOLXW_j0XBmTm6Z7JY5uWUubuWVx_NKh4h_OGcCKuDyF8rHZsI
CODEN IRALC6
Cites_doi 10.1007/978-1-4899-7560-7
10.1177/0278364918779698
10.1007/978-3-319-76965-3
10.1109/LRA.2024.3357310
10.1109/IROS51168.2021.9636663
10.1007/978-94-007-0335-3
10.1016/j.robot.2022.104258
10.3389/frobt.2020.00082
10.1109/ICRA.2019.8793509
10.1145/1360612.1360662
10.1023/B:BITN.0000046811.70614.38
10.1007/s42235-024-00534-2
10.23919/ECC57647.2023.10178402
10.1016/j.neunet.2017.12.012
10.1109/TRO.2022.3231360
10.1109/LRA.2020.2969931
10.1007/s12532-018-0139-4
10.1109/ICRA48506.2021.9561636
10.1109/ROBOT.2005.1570251
10.1016/j.jmsy.2017.02.001
10.1109/TRO.2022.3200546
10.1109/IROS58592.2024.10802305
10.1109/LRA.2017.2729659
10.1109/IROS.2012.6386109
10.1115/1.4026300
10.1109/ICRA48506.2021.9560955
10.1109/ICRA46639.2022.9812189
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
DOI 10.1109/LRA.2025.3577421
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
Technology 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
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
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 2377-3766
EndPage 7642
ExternalDocumentID 10_1109_LRA_2025_3577421
11027671
Genre orig-research
GrantInformation_xml – fundername: RWTH Aachen University
  grantid: S001821
  funderid: 10.13039/501100007210
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
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c247t-ae4a3e3ed00ff6519c7edb5fabd8342bc9f775092f0002a7e47c739f97bbe12a3
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001511061400018&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2377-3766
IngestDate Sat Nov 22 13:41:17 EST 2025
Sat Nov 29 07:50:37 EST 2025
Wed Aug 27 01:42:16 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 7
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-c247t-ae4a3e3ed00ff6519c7edb5fabd8342bc9f775092f0002a7e47c739f97bbe12a3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0001-7883-9381
0000-0003-2551-2419
0000-0002-2785-2487
0000-0002-5381-7976
0000-0003-2034-5519
PQID 3219892219
PQPubID 4437225
PageCount 8
ParticipantIDs ieee_primary_11027671
crossref_primary_10_1109_LRA_2025_3577421
proquest_journals_3219892219
PublicationCentury 2000
PublicationDate 2025-07-01
PublicationDateYYYYMMDD 2025-07-01
PublicationDate_xml – month: 07
  year: 2025
  text: 2025-07-01
  day: 01
PublicationDecade 2020
PublicationPlace Piscataway
PublicationPlace_xml – name: Piscataway
PublicationTitle IEEE robotics and automation letters
PublicationTitleAbbrev LRA
PublicationYear 2025
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 ref12
ref34
ref15
ref37
ref14
ref36
ref31
Sutanto (ref35) 2020
ref11
ref10
Loshchilov (ref33) 2019
ref2
ref1
Buisson-Fenet (ref23) 2022
ref17
ref39
ref16
ref38
ref18
Bradbury (ref29) 2018
Wittbrodt (ref7) 2007
Rawlings (ref27) 2017; 2
Geist (ref40) 2024
ref26
ref20
Battaglia (ref13) 2016; 29
Chen (ref19) 2024
ref22
ref21
ref28
Kidger (ref32) 2021
ref8
ref9
ref4
Beintema (ref25) 2023
ref3
Chen (ref24) 2018; 31
ref6
ref5
Kidger (ref30) 2021
References_xml – ident: ref26
  doi: 10.1007/978-1-4899-7560-7
– ident: ref2
  doi: 10.1177/0278364918779698
– ident: ref28
  doi: 10.1007/978-3-319-76965-3
– volume: 29
  start-page: 4509
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  year: 2016
  ident: ref13
  article-title: Interaction networks for learning about objects, relations and physics
– ident: ref15
  doi: 10.1109/LRA.2024.3357310
– volume-title: Proc. Int. Conf. Learn. Representations
  year: 2019
  ident: ref33
  article-title: Decoupled weight decay regularization
– ident: ref16
  doi: 10.1109/IROS51168.2021.9636663
– ident: ref6
  doi: 10.1007/978-94-007-0335-3
– ident: ref14
  doi: 10.1016/j.robot.2022.104258
– ident: ref1
  doi: 10.3389/frobt.2020.00082
– year: 2018
  ident: ref29
  article-title: JAX: Composable transformations of python NumPy programs
– start-page: 1
  volume-title: Proc. 11th Int. Conf. Learn. Representations
  year: 2023
  ident: ref25
  article-title: Continuous-time identification of dynamic state-space models by deep subspace encoding
– start-page: 804
  volume-title: Proc. Learn. Dyn. Control
  year: 2020
  ident: ref35
  article-title: Encoding physical constraints in differentiable newton-euler algorithm
– ident: ref21
  doi: 10.1109/ICRA.2019.8793509
– volume-title: Dynamics of Flexible Multibody Systems: Rigid Finite Element Method
  year: 2007
  ident: ref7
– ident: ref20
  doi: 10.1145/1360612.1360662
– ident: ref31
  doi: 10.1023/B:BITN.0000046811.70614.38
– ident: ref17
  doi: 10.1007/s42235-024-00534-2
– ident: ref39
  doi: 10.23919/ECC57647.2023.10178402
– year: 2022
  ident: ref23
  article-title: Recognition models to learn dynamics from partial observations with neural odes
  publication-title: Trans. Mach. Learn. Res.
– ident: ref36
  doi: 10.1016/j.neunet.2017.12.012
– ident: ref11
  doi: 10.1109/TRO.2022.3231360
– ident: ref3
  doi: 10.1109/LRA.2020.2969931
– ident: ref38
  doi: 10.1007/s12532-018-0139-4
– start-page: 15331
  volume-title: Proc. 41st Int. Conf. Mach. Learn.
  year: 2024
  ident: ref40
  article-title: Learning with 3D rotations, a Hitchhiker’s guide to SO(3)
– volume-title: Proc. Differentiable Program. Workshop Neural Inf. Process. Syst.
  year: 2021
  ident: ref30
  article-title: Equinox: Neural networks in JAX via callable PyTrees and filtered transformations
– volume: 2
  volume-title: Model Predictive Control: Theory, Computation, and Design
  year: 2017
  ident: ref27
– ident: ref4
  doi: 10.1109/ICRA48506.2021.9561636
– ident: ref9
  doi: 10.1109/ROBOT.2005.1570251
– ident: ref10
  doi: 10.1016/j.jmsy.2017.02.001
– ident: ref5
  doi: 10.1109/TRO.2022.3200546
– ident: ref8
  doi: 10.1109/IROS58592.2024.10802305
– year: 2021
  ident: ref32
  article-title: On neural differential equations
– ident: ref34
  doi: 10.1109/LRA.2017.2729659
– ident: ref37
  doi: 10.1109/IROS.2012.6386109
– volume: 31
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  year: 2018
  ident: ref24
  article-title: Neural ordinary differential equations
– ident: ref22
  doi: 10.1115/1.4026300
– volume-title: Proc. 8th Annu. Conf. Robot Learn.
  year: 2024
  ident: ref19
  article-title: Differentiable discrete elastic rods for real-time modeling of deformable linear objects
– ident: ref12
  doi: 10.1109/ICRA48506.2021.9560955
– ident: ref18
  doi: 10.1109/ICRA46639.2022.9812189
SSID ssj0001527395
Score 2.2960854
Snippet The dynamic manipulation of deformable objects poses a significant challenge in robotics. While model-based approaches for controlling such objects hold...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Index Database
Publisher
StartPage 7635
SubjectTerms and learning for soft robots
Computational modeling
control
Deformable models
Deformation
Discretization
Dynamics
flexible robotics
Formability
Heuristic algorithms
Kinematics
Learning
Mathematical models
Model learning for control
modeling
Neural networks
Numerical models
Physical properties
Predictive models
Rigid structures
Robotics
Robots
Title Learning Deformable Linear Object Dynamics From a Single Trajectory
URI https://ieeexplore.ieee.org/document/11027671
https://www.proquest.com/docview/3219892219
Volume 10
WOSCitedRecordID wos001511061400018&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: 2377-3766
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001527395
  issn: 2377-3766
  databaseCode: RIE
  dateStart: 20160101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2377-3766
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001527395
  issn: 2377-3766
  databaseCode: M~E
  dateStart: 20160101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV05T8MwFLZoxQADZxGFUnlgYUgP24ntseohhlIQh9Qt8vGCQNCiHkgs_HZsJ1VBiIEliqKXKP7ivMvvfUboXCbEJJmxERXKk2pTpwcFVRGxbgYIw9pcB3b9IR-NxHgsb4pm9dALAwCh-Awa_jSs5dupWfpUWdOZKsIT3zFe4jzJm7XWCRVPJSbj1VJkSzaHtx0XAJK4QWPn5JD2D9MT9lL5pYCDVRns_vN99tBO4T7iTv6999EGTA7Q9jdSwUPULShTH3EPgkeqXwC7kNNdxdfap11wL9-Gfo4Hs-krVvjOSTshZ7eeQxL_o4IeBv377mVUbJUQGcL4IlLAFAUKttXKssR5ZYaD1XGmtBWUEW1kxr1vQDKvAhUHxo1DK5Nca2gTRY9QeTKdwDHCSkvB3FBVohizRGljBGTU2FgkIDRU0cUKxfQtZ8RIQyTRkqlDPPWIpwXiVVTxqK3lCsCqqLbCPS3-mXlKia_fIu548sdtp2jLPz2vlq2h8mK2hDO0ad4XT_NZHZWuPvv1MCm-AEqhtfI
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS8MwFA8yBfXg58Tp1By8eOjWJWmTHsfmmDin6ITdSpK-iKKb7EPwvzdJO6aIBy-llFfa_Jq-r7z3C0LnSUx0bHQWUCEdqTa1elBQGZDMzgChWYMrz67f4_2-GA6Tu6JZ3ffCAIAvPoOaO_Vr-dlYz12qrG5NFeGx6xhfjRgjYd6utUypODKxJFosRoZJvXfftCEgiWo0sm4OafwwPn43lV8q2NuVzvY_32gHbRUOJG7mX3wXrcBoD21-oxXcR62CNPUJt8H7pOoVsA067VV8q1ziBbfzjeinuDMZv2GJH6y0FbKW68Wn8T_L6LFzOWh1g2KzhEATxmeBBCYpUMjC0JjY-mWaQ6YiI1UmKCNKJ4Y774AYpwQlB8a1RcskXCloEEkPUGk0HsEhwlIlgtmhylgylhGptBZgqM4iEYNQUEEXCxTT95wTI_WxRJikFvHUIZ4WiFdQ2aG2lCsAq6DqAve0-GumKSWugovY49Eft52h9e7gppf2rvrXx2jDPSmvna2i0mwyhxO0pj9mz9PJqZ8aX5w9uAg
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=Learning+Deformable+Linear+Object+Dynamics+From+a+Single+Trajectory&rft.jtitle=IEEE+robotics+and+automation+letters&rft.au=Mamedov%2C+Shamil&rft.au=Geist%2C+A+Rene&rft.au=Viljoen%2C+Ruan&rft.au=Trimpe%2C+Sebastian&rft.date=2025-07-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.eissn=2377-3766&rft.volume=10&rft.issue=12&rft.spage=7635&rft.epage=7642&rft_id=info:doi/10.1109%2FLRA.2025.3577421&rft.externalDBID=NO_FULL_TEXT
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