Tube Acceleration: Robust Dexterous Throwing Against Release Uncertainty

In robotic throwing, the release phase involves complex dynamic interactions due to object deformation and limited gripper opening speed, often resulting in inaccurate and nonrepeatable throws. While data-driven methods can be employed to compensate for the release uncertainty, the generalizability...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on robotics Jg. 40; S. 2831 - 2849
Hauptverfasser: Liu, Yang, Billard, Aude
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
ISSN:1552-3098, 1941-0468
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract In robotic throwing, the release phase involves complex dynamic interactions due to object deformation and limited gripper opening speed, often resulting in inaccurate and nonrepeatable throws. While data-driven methods can be employed to compensate for the release uncertainty, the generalizability of learned models to unseen objects is not guaranteed, and object-specific fine-tuning with new data may be required. This fine-tuning process raises concerns about the scalability of such methods for dexterous throwing, where the robot needs to execute diverse motions for throwing various objects. Instead of case-by-case fine-tuning, we aim at designing throwing motion robust against release uncertainty. We encapsulate all uncertainties resulting from complex contact dynamics in a surrogate model of their resulting effect on gripper opening delay . We introduce the notion of tube acceleration to model the class of constant-acceleration motion in joint space that guarantees a release within the set of valid throwing configurations. We propose a convex relaxation of the primal optimization problem with a tight error bound and evaluate its performance in terms of reliability and efficiency. Results show that the approach offers run-time performance to allow online computation of throws on a 7-DoF robot arm. It achieves a high accuracy and success rate (97% for planar throws) at throwing a variety of complex objects, even when using a simple ballistic model for the object's flying dynamics.
AbstractList In robotic throwing, the release phase involves complex dynamic interactions due to object deformation and limited gripper opening speed, often resulting in inaccurate and nonrepeatable throws. While data-driven methods can be employed to compensate for the release uncertainty, the generalizability of learned models to unseen objects is not guaranteed, and object-specific fine-tuning with new data may be required. This fine-tuning process raises concerns about the scalability of such methods for dexterous throwing, where the robot needs to execute diverse motions for throwing various objects. Instead of case-by-case fine-tuning, we aim at designing throwing motion robust against release uncertainty. We encapsulate all uncertainties resulting from complex contact dynamics in a surrogate model of their resulting effect on gripper opening delay . We introduce the notion of tube acceleration to model the class of constant-acceleration motion in joint space that guarantees a release within the set of valid throwing configurations. We propose a convex relaxation of the primal optimization problem with a tight error bound and evaluate its performance in terms of reliability and efficiency. Results show that the approach offers run-time performance to allow online computation of throws on a 7-DoF robot arm. It achieves a high accuracy and success rate (97% for planar throws) at throwing a variety of complex objects, even when using a simple ballistic model for the object's flying dynamics.
Author Liu, Yang
Billard, Aude
Author_xml – sequence: 1
  givenname: Yang
  orcidid: 0000-0003-2484-610X
  surname: Liu
  fullname: Liu, Yang
  email: yang.liuu@epfl.ch
  organization: Learning Algorithms and Systems Laboratory (LASA), EPFL, Ecublens, Switzerland
– sequence: 2
  givenname: Aude
  orcidid: 0000-0002-7076-8010
  surname: Billard
  fullname: Billard, Aude
  email: aude.billard@epfl.ch
  organization: Learning Algorithms and Systems Laboratory (LASA), EPFL, Ecublens, Switzerland
BookMark eNp9kM9rwjAYhsNwMHW777BDYee6JF8am93E_XAgCFLPIU1TV3GNS1Km__3i9DB22CUJX573e-EZoF5rW4PQLcEjQrB4KJaLEcWUjQByDoJcoD4RjKSY8bwX31lGU8Aiv0ID7zc4kgJDH82KrjTJRGuzNU6FxraPydKWnQ_Jk9kH42znk-Ld2a-mXSeTtWra-LWMtPImWbXauBBn4XCNLmu19ebmfA_R6uW5mM7S-eL1bTqZpxqAhbTiilNRl5yUJIcxVlBiUlY5q1Wp4iE41BQyHClOlKYi41jrmlZAmYYqhyG6P-3dOfvZGR_kxnaujZUScJaRcU6oiBQ-UdpZ752p5c41H8odJMHy6EtGX_LoS559xQj_E9FN-DESnGq2_wXvTsHGGPOrhwkmyBi-ARbYebg
CODEN ITREAE
CitedBy_id crossref_primary_10_1126_scirobotics_adu3922
crossref_primary_10_1109_ACCESS_2025_3561635
crossref_primary_10_1109_LRA_2025_3555381
Cites_doi 10.1109/CVPR.2009.5206848
10.1152/jn.00568.2011
10.1109/CDC.2017.8263977
10.1109/IROS.2012.6386267
10.1007/978-3-540-30301-5_28
10.1109/ROBOT.2009.5152525
10.1126/scirobotics.aau5872
10.1007/s10514-018-9773-y
10.1007/s00419-022-02173-7
10.1007/978-1-4419-8853-9
10.1109/ICRA.2012.6225319
10.1016/j.robot.2023.104481
10.1109/ICRA.2015.7139623
10.1038/s41592-019-0686-2
10.1109/IROS.2013.6697006
10.1109/IROS.2008.4651142
10.1017/CBO9780511804441
10.1177/027836499601500603
10.1201/9780203749319
10.1109/ICRA48506.2021.9561587
10.1109/TRO.2020.2988642
10.1177/02783649922066079
10.1109/LRA.2018.2801939
10.1109/TRO.2016.2536749
10.1109/LRA.2022.3229266
10.1007/s10514-023-10139-z
10.1145/1143844.1143936
10.1109/ROBOT.2009.5152438
10.1109/IROS47612.2022.9981231
10.1109/MRA.2022.3177355
10.1177/0278364918817116
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
DBID 97E
ESBDL
RIA
RIE
AAYXX
CITATION
7SC
7SP
7TB
8FD
FR3
JQ2
L7M
L~C
L~D
DOI 10.1109/TRO.2024.3386391
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE Xplore Open Access (Activated by CARLI)
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 2849
ExternalDocumentID 10_1109_TRO_2024_3386391
10494917
Genre orig-research
GrantInformation_xml – fundername: EU project DARKO
  grantid: H2020 ICT-46-2020
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
ESBDL
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-c334t-d6a629fb61b18370a3b01bd84faba4fa963f2350a6261ac29560ccf2d324c3d83
IEDL.DBID RIE
ISICitedReferencesCount 3
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001224407500003&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 07:57:08 EST 2025
Tue Nov 18 22:34:46 EST 2025
Sat Nov 29 01:47:33 EST 2025
Wed Aug 27 01:53:40 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language English
License https://creativecommons.org/licenses/by-nc-nd/4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c334t-d6a629fb61b18370a3b01bd84faba4fa963f2350a6261ac29560ccf2d324c3d83
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-7076-8010
0000-0003-2484-610X
OpenAccessLink https://ieeexplore.ieee.org/document/10494917
PQID 3055178129
PQPubID 27625
PageCount 19
ParticipantIDs ieee_primary_10494917
crossref_primary_10_1109_TRO_2024_3386391
proquest_journals_3055178129
crossref_citationtrail_10_1109_TRO_2024_3386391
PublicationCentury 2000
PublicationDate 20240000
2024-00-00
20240101
PublicationDateYYYYMMDD 2024-01-01
PublicationDate_xml – year: 2024
  text: 20240000
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on robotics
PublicationTitleAbbrev TRO
PublicationYear 2024
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 ref13
ref12
ref15
ref37
ref14
ref36
ref31
ref30
ref11
ref33
ref10
ref32
Okada (ref19) 2018; 5
ref2
ref1
ref17
ref39
ref16
ref38
ref18
Chen (ref21) 2021
Chen (ref28) 2018; 31
Diamond (ref35) 2016; 17
ref24
ref23
ref26
Chen (ref29) 2021
ref22
Khalil (ref25) 2002
ref27
ref8
ref7
ref9
ref3
ref6
ref5
Gai (ref4) 2013; 7
Fazlyab (ref34) 2019
ref40
Okada (ref20) 2021; 8
References_xml – ident: ref39
  doi: 10.1109/CVPR.2009.5206848
– ident: ref10
  doi: 10.1152/jn.00568.2011
– volume-title: Proc. Adv. Neural Inf. Process. Syst.
  year: 2019
  ident: ref34
  article-title: Efficient and accurate estimation of Lipschitz constants for deep neural networks
– ident: ref26
  doi: 10.1109/CDC.2017.8263977
– ident: ref13
  doi: 10.1109/IROS.2012.6386267
– start-page: 15084
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  year: 2021
  ident: ref21
  article-title: Decision transformer: Reinforcement learning via sequence modeling
– ident: ref12
  doi: 10.1007/978-3-540-30301-5_28
– volume-title: Nonlinear Systems
  year: 2002
  ident: ref25
– ident: ref3
  doi: 10.1109/ROBOT.2009.5152525
– ident: ref37
  doi: 10.1126/scirobotics.aau5872
– ident: ref7
  doi: 10.1007/s10514-018-9773-y
– ident: ref30
  doi: 10.1007/s00419-022-02173-7
– ident: ref33
  doi: 10.1007/978-1-4419-8853-9
– volume: 8
  start-page: 20
  issue: 1
  year: 2021
  ident: ref20
  article-title: Throwing motion design based on minimum sensitivity with respect to error covariance of robot dynamic parameters
  publication-title: Mech. Eng. J.
– ident: ref14
  doi: 10.1109/ICRA.2012.6225319
– ident: ref17
  doi: 10.1016/j.robot.2023.104481
– ident: ref18
  doi: 10.1109/ICRA.2015.7139623
– ident: ref36
  doi: 10.1038/s41592-019-0686-2
– ident: ref5
  doi: 10.1109/IROS.2013.6697006
– ident: ref2
  doi: 10.1109/IROS.2008.4651142
– ident: ref32
  doi: 10.1017/CBO9780511804441
– ident: ref11
  doi: 10.1177/027836499601500603
– ident: ref27
  doi: 10.1201/9780203749319
– ident: ref38
  doi: 10.1109/ICRA48506.2021.9561587
– ident: ref8
  doi: 10.1109/TRO.2020.2988642
– ident: ref1
  doi: 10.1177/02783649922066079
– ident: ref22
  doi: 10.1109/LRA.2018.2801939
– ident: ref24
  doi: 10.1109/TRO.2016.2536749
– ident: ref9
  doi: 10.1109/LRA.2022.3229266
– volume: 17
  start-page: 1
  issue: 83
  year: 2016
  ident: ref35
  article-title: CVXPY: A Python-embedded modeling language for convex optimization
  publication-title: J. Mach. Learn. Res.
– ident: ref23
  doi: 10.1007/s10514-023-10139-z
– volume: 5
  start-page: 17
  issue: 1
  year: 2018
  ident: ref19
  article-title: Robust throwing design based on dynamic sensitivity analysis
  publication-title: Mech. Eng. J.
– ident: ref31
  doi: 10.1145/1143844.1143936
– volume: 7
  start-page: 937
  issue: 7
  year: 2013
  ident: ref4
  article-title: Motion control of a ball throwing robot with a flexible robotic arm
  publication-title: Int. J. Comput. Inf. Eng.
– volume: 31
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  year: 2018
  ident: ref28
  article-title: Neural ordinary differential equations
– ident: ref6
  doi: 10.1109/ROBOT.2009.5152438
– ident: ref16
  doi: 10.1109/IROS47612.2022.9981231
– ident: ref15
  doi: 10.1109/MRA.2022.3177355
– volume-title: Proc. Int. Conf. Learn. Representations
  year: 2021
  ident: ref29
  article-title: Learning neural event functions for ordinary differential equations
– ident: ref40
  doi: 10.1177/0278364918817116
SSID ssj0024903
Score 2.4419923
Snippet In robotic throwing, the release phase involves complex dynamic interactions due to object deformation and limited gripper opening speed, often resulting in...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 2831
SubjectTerms Acceleration
Deformation
Dexterous manipulation
dynamic manipulation
Dynamics
Grippers
manipulation planning
Manipulator dynamics
Performance evaluation
Robot arms
Robots
robust/adaptive control of robotic systems
Robustness
Throwing
Uncertainty
Title Tube Acceleration: Robust Dexterous Throwing Against Release Uncertainty
URI https://ieeexplore.ieee.org/document/10494917
https://www.proquest.com/docview/3055178129
Volume 40
WOSCitedRecordID wos001224407500003&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/eLvHCXMwlV3PS8MwFA5ueNCDPydOp-TgxUO3punaxNtQxw4yZXSyW0nSRAeyydYK_ve-pJ1ORMFL6eGllO_l5b2X5H0PoQvCY66JMJ4MqPAspRvYXNf3MnAPtCuEZo6J6fEuHg7ZZMIfqmJ1VwujtXaXz3Tbvrqz_GyuCrtVBhZuuVRIXEO1OI7LYq0vYj3u2iBbSjGP-pytziR93klG95AJBmEb8jHwyOSbD3JNVX6sxM699Hf_-WN7aKeKI3GvVPw-2tCzA7S9xi54iAZJITXuKQWepdTzFR7NZbHM8Y1bkiHpx8kz5OEgjntPYgqhIh6BNHg2PIbZ4G4L5O8NNO7fJtcDr2qc4ClKw9zLIhEF3MiISGLJbQSVPpEZC42QAh5gdCagXR-kIiJUYHMkpUyQQXSlaMboEarP5jN9jDC1vdJDw5QiIlRSMCEZIYZnynR1JP0m6qygTFXFKm6bW7ykLrvweQrgpxb8tAK_iS4_R7yWjBp_yDYs2GtyJc5N1FqpK61sbpla7jISQ8DCT34Zdoq27NfLHZQWqueLQp-hTfWWT5eLczedPgA788cn
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dS8MwED90CuqDnxPnZx588aHaNG3X-DbUMXFOGVX2VpI01YFssnWC_72XtNOJKPhS-nCh5Xe53F2S-x3AMeV1rqnIHOkx4RhKN7S5wHVSdA8sEEJHlonpsV3vdKJej9-Xxeq2FkZrbS-f6VPzas_y06GamK0ytHDDpULr87AQ-L5Hi3KtL2o9bhshG1Ixh7k8mp5Kuvws7t5hLuj5p5iRoU-m37yQbavyYy22Dqa59s9fW4fVMpIkjUL1GzCnB5uwMsMvuAWteCI1aSiFvqXQ9DnpDuVknJNLuyhj2k_iZ8zEUZw0nkQfg0XSRWn0beQB54O9L5C_V-GheRVftJyydYKjGPNzJw1F6PFMhlRSQ28jmHSpTCM_E1LgA80u81jgolRIhfJMlqRU5qUYXymWRmwbKoPhQO8AYaZbup9FSlHhKykiISNKM56qLNChdGtwNoUyUSWvuGlv8ZLY_MLlCYKfGPCTEvwanHyOeC04Nf6QrRqwZ-QKnGuwP1VXUlrdODHsZbSOIQvf_WXYESy14tt20r7u3OzBsvlSsZ-yD5V8NNEHsKje8v54dGin1gfC1Mpu
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=Tube+Acceleration%3A+Robust+Dexterous+Throwing+Against+Release+Uncertainty&rft.jtitle=IEEE+transactions+on+robotics&rft.au=Liu%2C+Yang&rft.au=Billard%2C+Aude&rft.date=2024&rft.pub=IEEE&rft.issn=1552-3098&rft.volume=40&rft.spage=2831&rft.epage=2849&rft_id=info:doi/10.1109%2FTRO.2024.3386391&rft.externalDocID=10494917
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