Evolving Robotic Hand Morphology Through Grasping and Learning

Creatures can co-evolve their biological structures and behaviors under environmental pressures. Leveraging biomimetic evolution algorithms (referred to as co-design or co-optimization), a diverse range of robots with environmental adaptation has been generated. However, implementing these evolution...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE robotics and automation letters Ročník 9; číslo 10; s. 8475 - 8482
Hlavní autoři:	Yang, Bangchu, Jiang, Li, Wu, Wenhao, Zhen, Ruichen
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	IEEE 01.10.2024
Témata:	Deep learning deep learning in grasping and manipulation Evolutionary robotics Grasping Hands Hardware hardware gradient methods and tools for robot system design Morphology Optimization Reconfigurable devices reconfigurable hand Robot programming Stability analysis
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	Creatures can co-evolve their biological structures and behaviors under environmental pressures. Leveraging biomimetic evolution algorithms (referred to as co-design or co-optimization), a diverse range of robots with environmental adaptation has been generated. However, implementing these evolutionary methods or results in real-world robots, especially in the case of robotic hands, was not easy. In this context, this work presents a comprehensive self-optimization scheme for robotic hands that encompasses both software and hardware components. This scheme enables robots to autonomously refine their morphology through the integration of hardware gradients and reinforcement learning within parallel environments, thereby enhancing their adaptability to a variety of grasping tasks. For the hardware aspect, we developed a reconfigurable hand prototype with 37 variable hardware parameters (i.e., joint stiffness, the length of phalanges, finger location, and palm curvature) adjusted by mechanical components. Leveraging the adjustable hardware and 20 motors, this hand achieves full actuation and can dynamically adjust its morphology. The training results indicate that the fitness score of the self-optimizing hand exceeds that of original designs in this instance. The hardware parameters can be further fine-tuned in response to task variations. Moreover, the evolved hardware parameters are transferred to a real-world reconfigurable hand, demonstrating its grasping and adaptivity capabilities.
AbstractList	Creatures can co-evolve their biological structures and behaviors under environmental pressures. Leveraging biomimetic evolution algorithms (referred to as co-design or co-optimization), a diverse range of robots with environmental adaptation has been generated. However, implementing these evolutionary methods or results in real-world robots, especially in the case of robotic hands, was not easy. In this context, this work presents a comprehensive self-optimization scheme for robotic hands that encompasses both software and hardware components. This scheme enables robots to autonomously refine their morphology through the integration of hardware gradients and reinforcement learning within parallel environments, thereby enhancing their adaptability to a variety of grasping tasks. For the hardware aspect, we developed a reconfigurable hand prototype with 37 variable hardware parameters (i.e., joint stiffness, the length of phalanges, finger location, and palm curvature) adjusted by mechanical components. Leveraging the adjustable hardware and 20 motors, this hand achieves full actuation and can dynamically adjust its morphology. The training results indicate that the fitness score of the self-optimizing hand exceeds that of original designs in this instance. The hardware parameters can be further fine-tuned in response to task variations. Moreover, the evolved hardware parameters are transferred to a real-world reconfigurable hand, demonstrating its grasping and adaptivity capabilities.
Author	Zhen, Ruichen Jiang, Li Yang, Bangchu Wu, Wenhao
Author_xml	– sequence: 1 givenname: Bangchu orcidid: 0000-0002-9969-9995 surname: Yang fullname: Yang, Bangchu email: bcyang@hit.edu.cn organization: State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China – sequence: 2 givenname: Li orcidid: 0000-0003-1740-5525 surname: Jiang fullname: Jiang, Li email: jiangli01@hit.edu.cn organization: State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China – sequence: 3 givenname: Wenhao orcidid: 0000-0001-8818-8017 surname: Wu fullname: Wu, Wenhao email: 21b908021@stu.hit.edu.cn organization: State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China – sequence: 4 givenname: Ruichen orcidid: 0000-0002-1212-6538 surname: Zhen fullname: Zhen, Ruichen email: rczhen@stu.hit.edu.cn organization: State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China
BookMark	eNp9kE1rwkAQhpdiodZ676GH_IHY2Q9nk0tBxGohpSD2HGaTjW5Js7JJBf99DXqQHnqaGd73mcNzzwaNbyxjjxwmnEP6nK1nEwFCTaRSoEHfsKGQWsdSIw6u9js2btsvAOBToWU6HbKXxcHXB9dso7U3vnNFtKKmjN592O987bfHaLML_me7i5aB2n1f7PPMUmhOxwO7rahu7fgyR-zzdbGZr-LsY_k2n2VxIVB1MRnJZaGpSlUC3GDKNaAWpZEIJSYqMZXSU1RSmtJURWoEEWnCBI3VAlGOGJ7_FsG3bbBVXriOOuebLpCrcw55LyI_ich7EflFxAmEP-A-uG8Kx_-QpzPirLVXdZQcEy5_AQSZag4
CODEN	IRALC6
CitedBy_id	crossref_primary_10_3390_act14050234
Cites_doi	10.1007/BF02382073 10.1109/ICRA48506.2021.9561256 10.1098/rstb.2011.0035 10.1109/ICRA.2019.8793926 10.1016/j.jtbi.2017.12.026 10.1109/ICRA.2019.8793663 10.1109/IROS.2012.6386109 10.4067/S0717-95022010000300015 10.1109/IROS51168.2021.9636305 10.1109/ICRA48506.2021.9562092 10.1038/s42256-021-00320-3 10.1088/1748-3190/ac884e 10.1098/rspb.2016.1923 10.1145/3414685.3417831 10.1109/ICRA48506.2021.9561818 10.1109/TRA.2003.814499 10.7551/mitpress/2871.001.0001 10.1126/scirobotics.aao4900 10.1109/tnnls.2023.3272068 10.1098/rsif.2015.0176 10.1109/ICRA.2019.8793537 10.1109/TRO.2023.3284362 10.1109/ICRA48891.2023.10161134 10.1126/scirobotics.abg2133 10.1038/ncomms8717 10.1007/978-3-642-00616-6_5 10.15607/RSS.2021.XVII.008 10.1038/s41467-021-25874-z 10.1080/01691864.2017.1402703 10.1177/0278364917700714 10.1109/ICRA40945.2020.9196539 10.1109/IROS.2017.8202294
ContentType	Journal Article
DBID	97E RIA RIE AAYXX CITATION
DOI	10.1109/LRA.2024.3440707
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://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	2377-3766
EndPage	8482
ExternalDocumentID	10_1109_LRA_2024_3440707 10631681
Genre	orig-research
GrantInformation_xml	– fundername: National Natural Science Foundation of China grantid: 91948302; U1813209; 51875120 funderid: 10.13039/501100001809
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
ID	FETCH-LOGICAL-c264t-ab313c7af94801b69170672db360d6848bf4756433bdbfc9b2aaa7a686be72663
IEDL.DBID	RIE
ISICitedReferencesCount	1
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001300991000006&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 29 01:34:37 EST 2025 Tue Nov 18 22:12:15 EST 2025 Wed Aug 27 02:29:06 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-ab313c7af94801b69170672db360d6848bf4756433bdbfc9b2aaa7a686be72663
ORCID	0000-0003-1740-5525 0000-0001-8818-8017 0000-0002-9969-9995 0000-0002-1212-6538
PageCount	8
ParticipantIDs	crossref_citationtrail_10_1109_LRA_2024_3440707 crossref_primary_10_1109_LRA_2024_3440707 ieee_primary_10631681
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 ref36 ref31 ref30 ref11 ref33 ref10 ref32 Feix (ref35); 2 ref2 ref1 ref17 ref16 ref19 ref18 ref24 ref23 ref26 ref25 ref22 ref21 Chen (ref29) Weber (ref3) 2003 ref28 ref27 ref8 ref7 ref9 ref4 ref6 ref5 Haarnoja (ref34) Gupta (ref20)
References_xml	– ident: ref2 doi: 10.1007/BF02382073 – ident: ref9 doi: 10.1109/ICRA48506.2021.9561256 – start-page: 1861 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref34 article-title: Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor – ident: ref4 doi: 10.1098/rstb.2011.0035 – ident: ref25 doi: 10.1109/ICRA.2019.8793926 – ident: ref7 doi: 10.1016/j.jtbi.2017.12.026 – ident: ref23 doi: 10.1109/ICRA.2019.8793663 – ident: ref33 doi: 10.1109/IROS.2012.6386109 – ident: ref36 doi: 10.4067/S0717-95022010000300015 – ident: ref31 doi: 10.1109/IROS51168.2021.9636305 – ident: ref27 doi: 10.1109/ICRA48506.2021.9562092 – ident: ref22 doi: 10.1038/s42256-021-00320-3 – volume: 2 start-page: 58 volume-title: Proc. Robot., Sci. Syst.: Workshop Understanding Hum. Hand Adv. Robot. Manipulation ident: ref35 article-title: A comprehensive grasp taxonomy – ident: ref26 doi: 10.1088/1748-3190/ac884e – ident: ref6 doi: 10.1098/rspb.2016.1923 – ident: ref16 doi: 10.1145/3414685.3417831 – ident: ref17 doi: 10.1109/ICRA48506.2021.9561818 – ident: ref15 doi: 10.1109/TRA.2003.814499 – start-page: 1 volume-title: Evolution and Learning: The Baldwin Effect Reconsidered year: 2003 ident: ref3 doi: 10.7551/mitpress/2871.001.0001 – ident: ref32 doi: 10.1126/scirobotics.aao4900 – ident: ref18 doi: 10.1109/tnnls.2023.3272068 – ident: ref5 doi: 10.1098/rsif.2015.0176 – start-page: 1 volume-title: Proc. Int. Conf. Learn. Represent ident: ref20 article-title: MetaMorph: Learning universal controllers with transformers – ident: ref11 doi: 10.1109/ICRA.2019.8793537 – ident: ref13 doi: 10.1109/TRO.2023.3284362 – ident: ref12 doi: 10.1109/ICRA48891.2023.10161134 – start-page: 1158 volume-title: Proc. Conf. Robot Learn. ident: ref29 article-title: Hardware as policy: Mechanical and computational co-optimization using deep reinforcement learning – ident: ref8 doi: 10.1126/scirobotics.abg2133 – ident: ref1 doi: 10.1038/ncomms8717 – ident: ref10 doi: 10.1007/978-3-642-00616-6_5 – ident: ref30 doi: 10.15607/RSS.2021.XVII.008 – ident: ref19 doi: 10.1038/s41467-021-25874-z – ident: ref24 doi: 10.1080/01691864.2017.1402703 – ident: ref14 doi: 10.1177/0278364917700714 – ident: ref21 doi: 10.1109/ICRA40945.2020.9196539 – ident: ref28 doi: 10.1109/IROS.2017.8202294
SSID	ssj0001527395
Score	2.276869
Snippet	Creatures can co-evolve their biological structures and behaviors under environmental pressures. Leveraging biomimetic evolution algorithms (referred to as...
SourceID	crossref ieee
SourceType	Enrichment Source Index Database Publisher
StartPage	8475
SubjectTerms	Deep learning deep learning in grasping and manipulation Evolutionary robotics Grasping Hands Hardware hardware gradient methods and tools for robot system design Morphology Optimization Reconfigurable devices reconfigurable hand Robot programming Stability analysis
Title	Evolving Robotic Hand Morphology Through Grasping and Learning
URI	https://ieeexplore.ieee.org/document/10631681
Volume	9
WOSCitedRecordID	wos001300991000006&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 (ISSN International Center) 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/eLvHCXMwlV07T8MwED7RigEGnkWUR-WBhSFtWjt2vCBVqKVDW6GqSN0in-0gJNSgPhj57dhJCmUAiS1KzlL0Oc59d_Z9B3DDnVfRMowDFtEoYG2tA1ShcgvPOD5gqdKFuv5QjMfxbCYfy2L1vBbGWpsfPrNNf5nv5ZtMr32qzK1w7vssuWCnIoQoirW-EypeSkxGm63IULaGk64LADusSRnzqjY_XM9WL5XclfQP__kSR3BQckbSLSb5GHbs_AT2t5QET-Gu534zPjdAJhlmzo4M1NyQUeZgzBPnZFo05CEPC7X0NVLEPy_VVZ9r8NTvTe8HQdkaIdCOwawChbRNtVCp9PIvyKVXwREdg5SHhscsxpSJyLENigZTLbGjlBKKxxytcD6ZnkF1ns3tORDUaRQyZWPONDMiRCUsmtRSRGMc_6pDa4NaokvdcN--4jXJ44dQJg7nxOOclDjX4fZrxFuhmfGHbc1DvGVXoHvxy_1L2PPDi-N0V1BdLdb2Gnb1--pluWhAZfTRa-TfxSdgZ7WE
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS8MwFA8yBfXg58T5mYMXD926Jk2aizBkc2I3ZEzYreQl6RCklX3495u0nc6DgrfSvpbyS9P3ey95v4fQDbNeRQk_8mhIQo-2lfJA-tJOPG35gCFSler6MR8Oo8lEPFfF6kUtjDGm2Hxmmu6wWMvXuVq6VJmd4cz1WbLBzmZIadAuy7W-UypOTEyEq8VIX7TiUceGgAFtEkqdrs0P57PWTaVwJr39f77GAdqrWCPulMN8iDZMdoR217QEj9Fd1_5oXHYAj3LIrR3uy0zjQW6BLFLneFy25MEPMzl3VVLYXa_0Vad19NLrju_7XtUcwVOWwyw8CaRNFJepcAIwwITTweGBBsJ8zSIaQUp5aPkGAQ2pEhBIKblkEQPDrVcmJ6iW5Zk5RRhUGvpUmohRRTX3QXIDOjUEQGvLwBqotUItUZVyuGtg8ZYUEYQvEotz4nBOKpwb6PbrjvdSNeMP27qDeM2uRPfsl_PXaLs_HsRJ_Dh8Okc77lHl5roLVFvMluYSbamPxet8dlV8HZ-xFrea
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=Evolving+Robotic+Hand+Morphology+Through+Grasping+and+Learning&rft.jtitle=IEEE+robotics+and+automation+letters&rft.au=Yang%2C+Bangchu&rft.au=Jiang%2C+Li&rft.au=Wu%2C+Wenhao&rft.au=Zhen%2C+Ruichen&rft.date=2024-10-01&rft.issn=2377-3766&rft.eissn=2377-3766&rft.volume=9&rft.issue=10&rft.spage=8475&rft.epage=8482&rft_id=info:doi/10.1109%2FLRA.2024.3440707&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_LRA_2024_3440707
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