Deep Learning Approaches to Grasp Synthesis: A Review

Grasping is the process of picking up an object by applying forces and torques at a set of contacts. Recent advances in deep learning methods have allowed rapid progress in robotic object grasping. In this systematic review, we surveyed the publications over the last decade, with a particular intere...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transactions on robotics Ročník 39; číslo 5; s. 1 - 22
Hlavní autori:	Newbury, Rhys, Gu, Morris, Chumbley, Lachlan, Mousavian, Arsalan, Eppner, Clemens, Leitner, Jurgen, Bohg, Jeannette, Morales, Antonio, Asfour, Tamim, Kragic, Danica, Fox, Dieter, Cosgun, Akansel
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	New York IEEE 01.10.2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Deep learning deep learning in robotics and automation Dexterous manipulation End effectors Force Grasping Grasping (robotics) Grippers perception for grasping and manipulation Shape Systematics Task analysis
ISSN:	1552-3098, 1941-0468, 1941-0468
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Grasping is the process of picking up an object by applying forces and torques at a set of contacts. Recent advances in deep learning methods have allowed rapid progress in robotic object grasping. In this systematic review, we surveyed the publications over the last decade, with a particular interest in grasping an object using all six degrees of freedom of the end-effector pose. Our review found four common methodologies for robotic grasping: sampling-based approaches, direct regression, reinforcement learning, and exemplar approaches In addition, we found two "supporting methods" around grasping that use deep learning to support the grasping process, shape approximation, and affordances. We have distilled the publications found in this systematic review (85 papers) into ten key takeaways we consider crucial for future robotic grasping and manipulation research.
AbstractList	Grasping is the process of picking up an object by applying forces and torques at a set of contacts. Recent advances in deep learning methods have allowed rapid progress in robotic object grasping. In this systematic review, we surveyed the publications over the last decade, with a particular interest in grasping an object using all six degrees of freedom of the end-effector pose. Our review found four common methodologies for robotic grasping: sampling-based approaches, direct regression, reinforcement learning, and exemplar approaches In addition, we found two 'supporting methods' around grasping that use deep learning to support the grasping process, shape approximation, and affordances. We have distilled the publications found in this systematic review (85 papers) into ten key takeaways we consider crucial for future robotic grasping and manipulation research.
Author	Morales, Antonio Newbury, Rhys Leitner, Jurgen Fox, Dieter Chumbley, Lachlan Eppner, Clemens Mousavian, Arsalan Asfour, Tamim Gu, Morris Cosgun, Akansel Bohg, Jeannette Kragic, Danica
Author_xml	– sequence: 1 givenname: Rhys orcidid: 0000-0002-5791-6461 surname: Newbury fullname: Newbury, Rhys organization: Monash University, Clayton, VIC, Australia – sequence: 2 givenname: Morris surname: Gu fullname: Gu, Morris organization: Monash University, Clayton, VIC, Australia – sequence: 3 givenname: Lachlan surname: Chumbley fullname: Chumbley, Lachlan organization: Monash University, Clayton, VIC, Australia – sequence: 4 givenname: Arsalan orcidid: 0000-0001-9356-9455 surname: Mousavian fullname: Mousavian, Arsalan organization: NVIDIA Corporation, Seattle, WA, USA – sequence: 5 givenname: Clemens orcidid: 0000-0002-5398-4037 surname: Eppner fullname: Eppner, Clemens organization: NVIDIA Corporation, Seattle, WA, USA – sequence: 6 givenname: Jurgen orcidid: 0000-0003-1319-5073 surname: Leitner fullname: Leitner, Jurgen organization: Monash University, Clayton, VIC, Australia – sequence: 7 givenname: Jeannette orcidid: 0000-0002-4921-7193 surname: Bohg fullname: Bohg, Jeannette organization: Stanford University, Stanford, CA, USA – sequence: 8 givenname: Antonio orcidid: 0000-0002-8478-0854 surname: Morales fullname: Morales, Antonio organization: Jaume I University, Castellón de la Plana, Spain – sequence: 9 givenname: Tamim orcidid: 0000-0003-4879-7680 surname: Asfour fullname: Asfour, Tamim organization: Karlsruhe Institute of Technology, Karlsruhe, Germany – sequence: 10 givenname: Danica orcidid: 0000-0003-2965-2953 surname: Kragic fullname: Kragic, Danica organization: KTH Royal Institute of Technology, Stockholm, Sweden – sequence: 11 givenname: Dieter surname: Fox fullname: Fox, Dieter organization: NVIDIA Corporation, Seattle, WA, USA – sequence: 12 givenname: Akansel orcidid: 0000-0003-4203-6477 surname: Cosgun fullname: Cosgun, Akansel organization: Deakin University, Burwood, VIC, Australia
BackLink	https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-349565$$DView record from Swedish Publication Index (Kungliga Tekniska Högskolan)
BookMark	eNp9UEtPwkAQ3hhMBPTuwUMTz8XZRx_rrQFFExISRK-bbbuFRezW3SLh37ukxBgPnmYy-R7zfQPUq02tELrGMMIY-N1yMR8RIHRESQoRT85QH3OGQ2Bx2vN7FJGQAk8v0MC5DQBhHGgfRROlmmCmpK11vQqyprFGFmvlgtYEUytdE7wc6tYftLsPsmChvrTaX6LzSm6dujrNIXp9fFiOn8LZfPo8zmZhQSm0oUwwJnFMWc5pWaU0yhkrmawiHOO0oBiXCc8hLYAyWsmkAih8hMKfWJkQmdAhCjtdt1fNLheN1R_SHoSRWkz0WyaMXYn3di0o41Ecefxth_cpPnfKtWJjdrb2LwqSJoTF3hk8CjpUYY1zVlU_uhjEsUzhyxTHMsWpTE-J_1AK3cpWm7q1Um__I950RK2U-uWDGU8Jpd93xoDT
CODEN	ITREAE
CitedBy_id	crossref_primary_10_1109_LRA_2025_3562005 crossref_primary_10_1109_TMECH_2024_3451228 crossref_primary_10_1109_TAI_2023_3341833 crossref_primary_10_3389_fnbot_2023_1293878 crossref_primary_10_1016_j_heliyon_2024_e28716 crossref_primary_10_1109_LRA_2024_3498776 crossref_primary_10_1109_TCYB_2024_3518975 crossref_primary_10_1109_LRA_2024_3444714 crossref_primary_10_1109_TASE_2025_3555206 crossref_primary_10_1109_TETCI_2024_3451709 crossref_primary_10_1109_TASE_2025_3585040 crossref_primary_10_3390_technologies13080357 crossref_primary_10_1088_1361_6501_ad1cc5 crossref_primary_10_1016_j_inffus_2023_102221 crossref_primary_10_1109_TASE_2025_3566461 crossref_primary_10_3390_s24010195 crossref_primary_10_1109_TRO_2023_3281153 crossref_primary_10_1007_s10462_025_11262_2 crossref_primary_10_1109_TEVC_2023_3338740 crossref_primary_10_1109_TRO_2024_3422054 crossref_primary_10_1002_widm_1554 crossref_primary_10_1109_TRO_2025_3567544 crossref_primary_10_1109_LRA_2024_3360810 crossref_primary_10_1109_LRA_2025_3601045 crossref_primary_10_3390_robotics14070096 crossref_primary_10_1186_s10033_025_01346_z crossref_primary_10_1007_s10489_025_06292_w crossref_primary_10_1109_TAI_2024_3420848 crossref_primary_10_1109_LRA_2024_3359553 crossref_primary_10_1109_LRA_2024_3388850 crossref_primary_10_1109_TIM_2025_3544720 crossref_primary_10_3390_electronics13173365 crossref_primary_10_1007_s10846_024_02092_5 crossref_primary_10_1016_j_future_2025_107723 crossref_primary_10_1109_LRA_2024_3364451 crossref_primary_10_3390_machines13030214 crossref_primary_10_1109_LRA_2025_3557753 crossref_primary_10_3390_biomimetics10030186 crossref_primary_10_1007_s11370_025_00630_0 crossref_primary_10_1016_j_aei_2024_102778 crossref_primary_10_1007_s00521_023_08957_4 crossref_primary_10_1007_s10845_025_02673_7 crossref_primary_10_1109_TEM_2023_3327069 crossref_primary_10_1002_aisy_202400576 crossref_primary_10_3390_mi16080902 crossref_primary_10_1007_s11633_025_1542_8 crossref_primary_10_1371_journal_pone_0311199 crossref_primary_10_1016_j_robot_2025_104921 crossref_primary_10_1108_IR_04_2024_0177 crossref_primary_10_1016_j_rcim_2025_103021 crossref_primary_10_1016_j_rcim_2024_102792 crossref_primary_10_1109_JSEN_2024_3487551 crossref_primary_10_1109_TRO_2024_3508194 crossref_primary_10_1109_TRO_2025_3588448 crossref_primary_10_1109_LRA_2024_3436336 crossref_primary_10_1007_s10514_025_10201_y crossref_primary_10_1109_TRO_2025_3588720 crossref_primary_10_3390_machines13060451 crossref_primary_10_3390_s24092924 crossref_primary_10_1109_LRA_2024_3497714 crossref_primary_10_1109_TASE_2025_3530795 crossref_primary_10_1109_LRA_2023_3297061 crossref_primary_10_1109_TASE_2024_3512005 crossref_primary_10_1145_3717059 crossref_primary_10_1109_TMECH_2025_3538052
Cites_doi	10.1109/IROS.2017.8206484 10.1109/ICRA.2014.6907062 10.1109/RO-MAN47096.2020.9223541 10.1109/ICRA.2012.6225116 10.1023/A:1022676722315 10.1109/LRA.2020.2976295 10.1109/LRA.2020.2992195 10.1109/ICRA48506.2021.9561802 10.1109/LRA.2021.3060669 10.1109/CVPR.2016.90 10.1109/ICRA48506.2021.9561428 10.1109/5.726791 10.1109/JSEN.2018.2868340 10.1109/ICRA48506.2021.9561954 10.1109/LRA.2019.2933815 10.1109/ICRA48506.2021.9561877 10.1017/S0263574700015332 10.1007/978-3-030-95459-8_9 10.1109/IROS.2016.7759429 10.1109/ACCESS.2020.3027923 10.1109/IROS.2018.8593933 10.15607/RSS.2020.XVI.066 10.1109/ICRA.2015.7139361 10.1109/ICRA48506.2021.9561868 10.1109/ICRA.2017.7989545 10.1109/ICAR.2015.7251504 10.1109/IROS51168.2021.9636012 10.1109/IROS.2015.7354004 10.1177/17298806221095974 10.1109/ICRA48506.2021.9561473 10.15607/RSS.2018.XIV.021 10.1109/ICRA40945.2020.9196916 10.1109/CW.2005.39 10.1109/LRA.2020.2975706 10.1109/ICRA48506.2021.9562046 10.1109/MRA.2020.2976322 10.1109/ROBOT.2003.1241860 10.1126/scirobotics.aau4984 10.1109/IROS.2017.8206060 10.1109/ICRA48506.2021.9560844 10.1109/IROS51168.2021.9636876 10.1016/j.robot.2022.104313 10.1109/ICRA40945.2020.9196740 10.1109/IROS.2017.8202237 10.1177/0278364914549607 10.1109/ICRA40945.2020.9196677 10.1109/TRO.2020.3033696 10.15607/RSS.2020.XVI.033 10.1038/nature14236 10.1109/IROS.2013.6696808 10.1109/IROS40897.2019.8967816 10.1007/s00138-020-01127-9 10.1109/ICRA48506.2021.9561228 10.1109/CCDC52312.2021.9601770 10.1109/ICRA40945.2020.9197413 10.1109/RoboSoft51838.2021.9479225 10.3389/frobt.2020.00120 10.1109/ICRA.2015.7139793 10.1109/ICRA.2018.8460609 10.1109/LRA.2020.3004787 10.1109/ICRA.2019.8793733 10.1109/ICRA.2018.8461039 10.1109/HORA52670.2021.9461271 10.1109/CRV55824.2022.00021 10.1109/ICRA.2014.6906903 10.1109/LRA.2020.2969946 10.1109/ICRA.2019.8794435 10.1109/IROS40897.2019.8968115 10.1109/LRA.2017.2651945 10.1109/TASE.2021.3128639 10.1109/IROS.2014.6942539 10.1109/LRA.2018.2799743 10.1109/ICRA.2018.8460902 10.1109/IROS.2006.282367 10.1109/LRA.2018.2810544 10.1109/SMI.2004.1314504 10.1109/ROMAN.2014.6926343 10.1109/ACCESS.2020.3028740 10.1177/0278364919868017 10.1007/s43154-020-00021-6 10.1109/LRA.2021.3096239 10.1109/ICRA40945.2020.9197185 10.1109/CVPR.2017.243 10.1109/ICRA40945.2020.9196678 10.1016/S0003-6870(84)90121-2 10.1007/s10514-020-09907-y 10.1177/0278364919865338 10.1109/ICRA.2016.7487342 10.1109/ROBOT.2000.844081 10.1109/ROBOT.1994.351378 10.1177/0278364907087172 10.1177/0278364914559753 10.1007/s10514-013-9365-9 10.1109/ICCV48922.2021.01566 10.1109/ICRA.2018.8460887 10.1109/ROBOT.1999.770385 10.1109/AIM43001.2020.9158850 10.1177/0278364919887447 10.1109/ICRA48506.2021.9560901 10.1109/ICRA40945.2020.9197134 10.1109/IROS.2016.7759114 10.1109/MRA.2021.3064754 10.1016/j.smhl.2018.03.002 10.1109/ICRA.2018.8460875 10.1109/ICRA48506.2021.9561828 10.1080/01691864.2021.1897674 10.1007/978-3-319-24574-4_28 10.1109/ICRA.2018.8463204 10.1016/j.compag.2020.105694 10.1109/LRA.2018.2852779 10.1109/TRO.2013.2289018 10.1016/j.robot.2019.103274 10.1109/TPAMI.2016.2577031 10.1109/LRA.2019.2895878 10.1109/ICRA46639.2022.9811568 10.1109/ACIT49673.2020.9208918 10.1109/IROS.2015.7354264 10.1109/CRC52766.2021.9620132 10.15607/RSS.2012.VIII.023 10.1177/0278364915592961 10.1561/2200000056 10.1109/CVPR.2016.91 10.1109/COASE.2018.8560417 10.1109/LRA.2021.3063074 10.1109/CVPR.2017.16 10.1109/CVPR42600.2020.01146 10.1109/ICRA40945.2020.9197320 10.1109/Humanoids43949.2019.9035002 10.1109/ROBOT.1987.1088014 10.1007/978-3-540-77457-0_4 10.1109/ROBOT.1996.506534 10.1109/ICRA40945.2020.9197318 10.1007/978-3-319-46484-8_10 10.1109/TRO.2011.2132870 10.1109/ICRA48506.2021.9561920 10.1177/0278364917735594 10.1177/0278364909105606 10.1109/IROS40897.2019.8968263 10.1177/0278364917710318 10.1109/ICCV.2019.00299 10.1109/IROS.2007.4399052 10.1007/978-3-319-32552-1_38 10.1109/MRA.2004.1371616 10.1109/IROS.2015.7353481 10.1088/1748-3190/abe345 10.1109/70.246063 10.1142/S0219843622500116 10.1016/j.compag.2022.106716 10.1109/CVPR.2019.00891 10.1109/IROS47612.2022.9981955 10.1109/LRA.2018.2852777 10.1109/ROBOT.1992.219918 10.1109/COASE.2019.8843059 10.1007/978-3-030-58548-8_34 10.3389/fnbot.2021.658280 10.1109/ISIE.2006.296116 10.1109/ICRA.2012.6225101 10.1109/CVPR.2019.01291 10.15607/RSS.2021.XVII.024 10.15607/RSS.2017.XIII.058 10.1177/0278364912445831 10.1109/ICRA48506.2021.9561409 10.1109/IROS45743.2020.9340783
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 7TB 8FD FR3 JQ2 L7M L~C L~D ADTPV AOWAS D8V
DOI	10.1109/TRO.2023.3280597
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 SwePub SwePub Articles SWEPUB Kungliga Tekniska Högskolan
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	22
ExternalDocumentID	oai_DiVA_org_kth_349565 10_1109_TRO_2023_3280597 10149823
Genre	orig-research
GroupedDBID	.DC 0R~ 29I 4.4 5GY 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACIWK AENEX AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS F5P HZ~ IFIPE IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNS 5VS AAYXX AETIX AGSQL AIBXA CITATION EJD H~9 VJK 7SC 7SP 7TB 8FD FR3 JQ2 L7M L~C L~D ADTPV AOWAS D8V
ID	FETCH-LOGICAL-c330t-a71126634b93df835b44d4af51618c311d79b08c0343fa7f00c202cb084d72a73
IEDL.DBID	RIE
ISICitedReferencesCount	121
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001019463600001&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 1941-0468
IngestDate	Tue Nov 04 16:38:58 EST 2025 Sun Nov 09 08:18:12 EST 2025 Sat Nov 29 01:47:31 EST 2025 Tue Nov 18 21:39:57 EST 2025 Wed Aug 27 02:14:04 EDT 2025
IsDoiOpenAccess	false
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	5
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-c330t-a71126634b93df835b44d4af51618c311d79b08c0343fa7f00c202cb084d72a73
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0003-2965-2953 0000-0002-5791-6461 0000-0002-4921-7193 0000-0002-8478-0854 0000-0003-4879-7680 0000-0001-9356-9455 0000-0003-1319-5073 0000-0002-5398-4037 0000-0003-4203-6477
PQID	2872465160
PQPubID	27625
PageCount	22
ParticipantIDs	proquest_journals_2872465160 swepub_primary_oai_DiVA_org_kth_349565 crossref_primary_10_1109_TRO_2023_3280597 ieee_primary_10149823 crossref_citationtrail_10_1109_TRO_2023_3280597
PublicationCentury	2000
PublicationDate	2023-10-01
PublicationDateYYYYMMDD	2023-10-01
PublicationDate_xml	– month: 10 year: 2023 text: 2023-10-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on robotics
PublicationTitleAbbrev	TRO
PublicationYear	2023
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 ref207 ref59 ref205 gal (ref145) 0 ref58 ref206 ref53 ref203 ref52 ref204 ref55 ref201 ref54 ref202 lynch (ref12) 2022 krizhevsky (ref34) 2012; 25 ref210 kawakami (ref130) 2021 ref211 ref51 ref46 ref42 ref44 ref212 ref43 ref213 ref49 ref8 ref9 ref3 ref5 eppner (ref4) 0 ref100 agrawal (ref73) 0 murali (ref56) 0 ref101 ref35 vafaeikia (ref146) 2020 ref37 ref36 ref31 ref30 schulman (ref125) 0 ref39 ref38 brohan (ref11) 2022 ref24 sohn (ref113) 0 ref26 ref25 li (ref115) 2017 ref20 kalashnikov (ref118) 0 ref22 ref21 ardón (ref153) 2020 murray (ref23) 1994 ref28 ref27 kingma (ref77) 0 chang (ref162) 2015 ref200 wang (ref132) 0 ref128 ref129 ref97 ref126 ref96 ref127 ref99 ref124 ref98 lenz (ref109) 2013; 34 morales (ref33) 0 riedlinger (ref48) 0 jiang (ref29) 0 ref93 ref134 ref95 ref131 ref91 ref90 ref86 ref137 ref85 ref138 ref88 ref135 ref136 ref82 ref144 ref81 ref84 ref142 ref83 ref143 ref140 ref141 ref80 ref79 ref108 ref106 ref107 ref75 ref104 ref105 ref102 ref76 ref103 ref111 ref70 ref112 ref72 ref110 schulman (ref123) 2017 ref68 ref119 ref67 ref117 ref69 ref64 ref63 ref116 ref66 breyer (ref94) 0 ref60 ref122 ref62 ref61 ref121 ref168 ref169 kroemer (ref14) 2021; 22 ref170 avigal (ref147) 2020 wu (ref165) 0 ref177 ref175 ref176 ref173 ref174 ref171 ref172 vahrenkamp (ref74) 2013 khosla (ref185) 0 ref179 ref180 ref181 zhang (ref139) 0 ref188 ref189 ref186 ref187 ref184 ref182 ref183 ref148 ref149 carbines (ref209) 1999 gonçalves (ref47) 0 ref155 ref156 ref154 ref151 ref152 ref150 ref159 ref157 ref158 gualtieri (ref120) 0 simonyan (ref178) 0; 38 gandhi (ref208) 2020 bishop (ref78) 1994 munoz (ref65) 2021 ref166 ref167 ref164 ref163 ref160 ref161 ref13 ref15 ref10 wu (ref92) 0; 33 ref17 ref19 ref18 saxena (ref32) 0; 3 catalano (ref6) 2016 zhou (ref41) 0; 2 levine (ref7) 2016; 17 qi (ref114) 0 lillicrap (ref133) 2015 lu (ref45) 2019 ref2 ref191 ref192 ref190 ref199 ref197 ref198 ref195 asada (ref1) 1979 ref196 ref193 ref194 merwe (ref50) 0 qin (ref87) 0 gibson (ref16) 1977 ten pas (ref40) 2017; 36 pas (ref71) 2018; 1 jeng (ref89) 0
References_xml	– ident: ref157 doi: 10.1109/IROS.2017.8206484 – ident: ref196 doi: 10.1109/ICRA.2014.6907062 – ident: ref154 doi: 10.1109/RO-MAN47096.2020.9223541 – ident: ref163 doi: 10.1109/ICRA.2012.6225116 – ident: ref128 doi: 10.1023/A:1022676722315 – ident: ref172 doi: 10.1109/LRA.2020.2976295 – ident: ref167 doi: 10.1109/LRA.2020.2992195 – ident: ref126 doi: 10.1109/ICRA48506.2021.9561802 – ident: ref143 doi: 10.1109/LRA.2021.3060669 – ident: ref176 doi: 10.1109/CVPR.2016.90 – start-page: 2263 year: 0 ident: ref139 article-title: Learning to reconstruct shapes from unseen classes publication-title: Proc 32nd Int Conf Neural Inf Process Syst – ident: ref138 doi: 10.1109/ICRA48506.2021.9561428 – ident: ref179 doi: 10.1109/5.726791 – ident: ref204 doi: 10.1109/JSEN.2018.2868340 – year: 2020 ident: ref147 article-title: 6-DoF grasp planning using fast 3D reconstruction and grasp quality CNN – ident: ref102 doi: 10.1109/ICRA48506.2021.9561954 – year: 1994 ident: ref78 article-title: Mixture density networks – volume: 1 start-page: 307 year: 2018 ident: ref71 article-title: Using geometry to detect grasp poses in 3D point clouds publication-title: Robot Res – ident: ref17 doi: 10.1109/LRA.2019.2933815 – ident: ref99 doi: 10.1109/ICRA48506.2021.9561877 – volume: 17 start-page: 1334 year: 2016 ident: ref7 article-title: End-to-end training of deep visuomotor policies publication-title: J Mach Learn Res – ident: ref211 doi: 10.1017/S0263574700015332 – year: 2020 ident: ref153 article-title: Affordances in robotic tasks-A survey – ident: ref158 doi: 10.1007/978-3-030-95459-8_9 – ident: ref156 doi: 10.1109/IROS.2016.7759429 – ident: ref116 doi: 10.1109/ACCESS.2020.3027923 – year: 2015 ident: ref162 article-title: ShapeNet: An information-rich 3D model repository – ident: ref183 doi: 10.1109/IROS.2018.8593933 – ident: ref95 doi: 10.15607/RSS.2020.XVI.066 – ident: ref108 doi: 10.1109/ICRA.2015.7139361 – ident: ref103 doi: 10.1109/ICRA48506.2021.9561868 – ident: ref189 doi: 10.1109/ICRA.2017.7989545 – ident: ref159 doi: 10.1109/ICAR.2015.7251504 – ident: ref104 doi: 10.1109/IROS51168.2021.9636012 – ident: ref37 doi: 10.1109/IROS.2015.7354004 – ident: ref199 doi: 10.1177/17298806221095974 – ident: ref59 doi: 10.1109/ICRA48506.2021.9561473 – year: 2015 ident: ref133 article-title: Continuous control with deep reinforcement learning – ident: ref79 doi: 10.15607/RSS.2018.XIV.021 – ident: ref207 doi: 10.1109/ICRA40945.2020.9196916 – ident: ref26 doi: 10.1109/CW.2005.39 – start-page: 1602 year: 0 ident: ref94 article-title: Volumetric grasping network: Real-time 6 DoF grasp detection in clutter publication-title: Proc Conf Robot Learn – start-page: 101 year: 2016 ident: ref6 publication-title: From Soft to Adaptive Synergies The Pisa/IIT SoftHand – ident: ref57 doi: 10.1109/LRA.2020.2975706 – start-page: 18661 year: 0 ident: ref185 article-title: Supervised contrastive learning publication-title: Proc 34th Int Conf Neural Inf Process Syst – ident: ref88 doi: 10.1109/ICRA48506.2021.9562046 – ident: ref54 doi: 10.1109/MRA.2020.2976322 – year: 2017 ident: ref115 article-title: Deep reinforcement learning: An overview – ident: ref151 doi: 10.1109/ROBOT.2003.1241860 – ident: ref8 doi: 10.1126/scirobotics.aau4984 – ident: ref137 doi: 10.1109/IROS.2017.8206060 – ident: ref170 doi: 10.1109/ICRA48506.2021.9560844 – year: 2022 ident: ref12 article-title: Interactive language: Talking to robots in real time – ident: ref66 doi: 10.1109/IROS51168.2021.9636876 – ident: ref63 doi: 10.1016/j.robot.2022.104313 – ident: ref93 doi: 10.1109/ICRA40945.2020.9196740 – year: 0 ident: ref33 article-title: Learning to predict grasp reliability for a multifinger robot hand by using visual features publication-title: Proc Int Conf AI Soft Comput – ident: ref111 doi: 10.1109/IROS.2017.8202237 – volume: 34 start-page: 705 year: 2013 ident: ref109 article-title: Deep learning for detecting robotic grasps publication-title: Int J Robot Res doi: 10.1177/0278364914549607 – ident: ref177 doi: 10.1109/ICRA40945.2020.9196677 – ident: ref140 doi: 10.1109/TRO.2020.3033696 – ident: ref173 doi: 10.15607/RSS.2020.XVI.033 – ident: ref121 doi: 10.1038/nature14236 – ident: ref149 doi: 10.1109/IROS.2013.6696808 – ident: ref144 doi: 10.1109/IROS40897.2019.8967816 – start-page: 1 year: 0 ident: ref47 article-title: Grasp planning with incomplete knowledge about the object to be grasped publication-title: Proc IEEE Int Conf Auton Robot Syst Competitions – start-page: 1889 year: 0 ident: ref125 article-title: Trust region policy optimization publication-title: Proc 32nd Int Conf Mach Learn – ident: ref97 doi: 10.1007/s00138-020-01127-9 – ident: ref58 doi: 10.1109/ICRA48506.2021.9561228 – ident: ref67 doi: 10.1109/CCDC52312.2021.9601770 – ident: ref52 doi: 10.1109/ICRA40945.2020.9197413 – volume: 25 start-page: 1097 year: 2012 ident: ref34 article-title: ImageNet classification with deep convolutional neural networks publication-title: Proc Int Conf Neural Inf Process – ident: ref171 doi: 10.1109/RoboSoft51838.2021.9479225 – ident: ref136 doi: 10.3389/frobt.2020.00120 – volume: 38 start-page: 1943 year: 0 ident: ref178 article-title: Very deep convolutional networks for large-scale image recognition publication-title: Proc Int Conf Learn Represent – start-page: 1912 year: 0 ident: ref165 article-title: 3D ShapeNets: A deep representation for volumetric shapes publication-title: Proc IEEE Conf Comput Vis Pattern Recognit – ident: ref38 doi: 10.1109/ICRA.2015.7139793 – ident: ref42 doi: 10.1109/ICRA.2018.8460609 – ident: ref127 doi: 10.1109/LRA.2020.3004787 – ident: ref124 doi: 10.1109/ICRA.2019.8793733 – start-page: 220 year: 0 ident: ref89 article-title: GDN: A coarse-to-fine (C2F) representation for end-to-end 6-DoF grasp detection publication-title: Proc Conf Robot Learn – start-page: 39.1 year: 0 ident: ref73 article-title: Analysis of Thompson sampling for the multi-armed bandit problem publication-title: Proc 25th Ann Conf Learn Theory – ident: ref119 doi: 10.1109/ICRA.2018.8461039 – ident: ref80 doi: 10.1109/HORA52670.2021.9461271 – ident: ref203 doi: 10.1109/CRV55824.2022.00021 – start-page: 53 year: 0 ident: ref87 article-title: S4G: A modal single-view single-shot SE (3) grasp detection in cluttered scenes publication-title: Proc Conf Robot Learn – ident: ref160 doi: 10.1109/ICRA.2014.6906903 – ident: ref96 doi: 10.1109/LRA.2020.2969946 – start-page: 4831 year: 0 ident: ref4 article-title: Lessons from the Amazon picking challenge: Four aspects of building robotic systems publication-title: Proc 26th Int Joint Conf Artif Intell – ident: ref44 doi: 10.1109/ICRA.2019.8794435 – ident: ref86 doi: 10.1109/IROS40897.2019.8968115 – ident: ref83 doi: 10.1109/LRA.2017.2651945 – start-page: 3483 year: 0 ident: ref113 article-title: Learning structured output representation using deep conditional generative models publication-title: Proc Int Conf Neural Inf Process – year: 2022 ident: ref11 article-title: RT-1: Robotics transformer for real-world control at scale – ident: ref61 doi: 10.1109/TASE.2021.3128639 – ident: ref195 doi: 10.1109/IROS.2014.6942539 – ident: ref206 doi: 10.1109/LRA.2018.2799743 – ident: ref155 doi: 10.1109/ICRA.2018.8460902 – ident: ref18 doi: 10.1109/IROS.2006.282367 – ident: ref85 doi: 10.1109/LRA.2018.2810544 – year: 2021 ident: ref65 article-title: Grasping in 6DoF: An orthographic approach to generalized grasp affordance predictions – start-page: 455 year: 2019 ident: ref45 article-title: Planning multi-fingered grasps as probabilistic inference in a learned deep network publication-title: Robotics Research – ident: ref164 doi: 10.1109/SMI.2004.1314504 – start-page: 11516 year: 0 ident: ref50 article-title: Learning continuous 3D reconstructions for geometrically aware grasping publication-title: Proc IEEE Int Conf Robot Autom – volume: 22 start-page: 1395 year: 2021 ident: ref14 article-title: A review of robot learning for manipulation: Challenges, representations, and algorithms publication-title: J Mach Learn Res – ident: ref150 doi: 10.1109/ROMAN.2014.6926343 – ident: ref200 doi: 10.1109/ACCESS.2020.3028740 – year: 2020 ident: ref146 article-title: A brief review of deep multi-task learning and auxiliary task learning – ident: ref10 doi: 10.1177/0278364919868017 – ident: ref13 doi: 10.1007/s43154-020-00021-6 – ident: ref60 doi: 10.1109/LRA.2021.3096239 – ident: ref134 doi: 10.1109/ICRA40945.2020.9197185 – year: 0 ident: ref77 article-title: Auto-encoding variational Bayes publication-title: Proc 2nd Int Conf Learn Represent – ident: ref180 doi: 10.1109/CVPR.2017.243 – ident: ref53 doi: 10.1109/ICRA40945.2020.9196678 – start-page: 3304 year: 0 ident: ref29 article-title: Efficient grasping from RGBD images: Learning using a new rectangle representation publication-title: Proc IEEE Int Conf Robot Autom – ident: ref210 doi: 10.1016/S0003-6870(84)90121-2 – ident: ref112 doi: 10.1007/s10514-020-09907-y – ident: ref76 doi: 10.1177/0278364919865338 – ident: ref36 doi: 10.1109/ICRA.2016.7487342 – ident: ref2 doi: 10.1109/ROBOT.2000.844081 – ident: ref20 doi: 10.1109/ROBOT.1994.351378 – ident: ref31 doi: 10.1177/0278364907087172 – ident: ref191 doi: 10.1177/0278364914559753 – ident: ref193 doi: 10.1007/s10514-013-9365-9 – ident: ref98 doi: 10.1109/ICCV48922.2021.01566 – ident: ref69 doi: 10.1109/ICRA.2018.8460887 – start-page: 1 year: 0 ident: ref48 article-title: Model-free grasp learning framework based on physical simulation publication-title: Proc Int Symp Robot – ident: ref72 doi: 10.1109/ROBOT.1999.770385 – ident: ref90 doi: 10.1109/AIM43001.2020.9158850 – ident: ref9 doi: 10.1177/0278364919887447 – ident: ref129 doi: 10.1109/ICRA48506.2021.9560901 – volume: 3 start-page: 1491 year: 0 ident: ref32 article-title: Learning grasp strategies with partial shape information publication-title: Proc Nat Conf Artif Intell – year: 2017 ident: ref123 article-title: Proximal policy optimization algorithms – ident: ref198 doi: 10.1109/ICRA40945.2020.9197134 – ident: ref39 doi: 10.1109/IROS.2016.7759114 – ident: ref187 doi: 10.1109/MRA.2021.3064754 – ident: ref213 doi: 10.1016/j.smhl.2018.03.002 – ident: ref168 doi: 10.1109/ICRA.2018.8460875 – year: 1999 ident: ref209 article-title: Welding robot – ident: ref131 doi: 10.1109/ICRA48506.2021.9561828 – ident: ref64 doi: 10.1080/01691864.2021.1897674 – ident: ref181 doi: 10.1007/978-3-319-24574-4_28 – start-page: 1540 year: 0 ident: ref56 article-title: Same object, different grasps: Data and semantic knowledge for task-oriented grasping publication-title: Proc Conf Robot Learn – ident: ref84 doi: 10.1109/ICRA.2018.8463204 – ident: ref186 doi: 10.1016/j.compag.2020.105694 – ident: ref202 doi: 10.1109/LRA.2018.2852779 – ident: ref3 doi: 10.1109/TRO.2013.2289018 – ident: ref190 doi: 10.1016/j.robot.2019.103274 – start-page: 477 year: 0 ident: ref120 article-title: Learning 6-DoF grasping and pick-place using attention focus publication-title: Proc Conf Robot Learn – ident: ref107 doi: 10.1109/TPAMI.2016.2577031 – start-page: 70 year: 0 ident: ref132 article-title: Goal-auxiliary actor-critic for 6D robotic grasping with point clouds publication-title: Proc 5th Annu Conf Robot Learn – ident: ref81 doi: 10.1109/LRA.2019.2895878 – ident: ref68 doi: 10.1109/ICRA46639.2022.9811568 – year: 2021 ident: ref130 article-title: Learning 6DoF grasping using reward-consistent demonstration – start-page: 5105 year: 0 ident: ref114 article-title: PointNet: Deep hierarchical feature learning on point sets in a metric space publication-title: Proc 31st Int Conf Neural Inf Process Syst – year: 2020 ident: ref208 article-title: Swoosh! Rattle! Thump!-Actions that sound publication-title: Robotics – ident: ref55 doi: 10.1109/ACIT49673.2020.9208918 – ident: ref197 doi: 10.1109/IROS.2015.7354264 – ident: ref105 doi: 10.1109/CRC52766.2021.9620132 – start-page: 585 year: 2013 ident: ref74 publication-title: Simox A Robotics Toolbox for Simulation Motion and Grasp Planning – ident: ref192 doi: 10.15607/RSS.2012.VIII.023 – ident: ref5 doi: 10.1177/0278364915592961 – ident: ref141 doi: 10.1561/2200000056 – ident: ref106 doi: 10.1109/CVPR.2016.91 – ident: ref152 doi: 10.1109/COASE.2018.8560417 – ident: ref205 doi: 10.1109/LRA.2021.3063074 – ident: ref175 doi: 10.1109/CVPR.2017.16 – year: 1979 ident: ref1 article-title: Studies on prehension and handling by robot hands with elastic fingers – ident: ref91 doi: 10.1109/CVPR42600.2020.01146 – ident: ref51 doi: 10.1109/ICRA40945.2020.9197320 – volume: 33 start-page: 13174 year: 0 ident: ref92 article-title: Grasp proposal networks: An end-to-end solution for visual learning of robotic grasps publication-title: Proc Conf Neural Inf Process Syst – ident: ref46 doi: 10.1109/Humanoids43949.2019.9035002 – ident: ref19 doi: 10.1109/ROBOT.1987.1088014 – ident: ref30 doi: 10.1007/978-3-540-77457-0_4 – ident: ref28 doi: 10.1109/ROBOT.1996.506534 – ident: ref49 doi: 10.1109/ICRA40945.2020.9197318 – ident: ref166 doi: 10.1007/978-3-319-46484-8_10 – ident: ref201 doi: 10.1109/TRO.2011.2132870 – ident: ref100 doi: 10.1109/ICRA48506.2021.9561920 – volume: 36 start-page: 1455 year: 2017 ident: ref40 article-title: Grasp pose detection in point clouds publication-title: Int J Robot Res doi: 10.1177/0278364917735594 – ident: ref75 doi: 10.1177/0278364909105606 – start-page: 1050 year: 0 ident: ref145 article-title: Dropout as a Bayesian approximation: Representing model uncertainty in deep learning publication-title: Proc Int Conf Mach Learn – ident: ref122 doi: 10.1109/IROS40897.2019.8968263 – ident: ref117 doi: 10.1177/0278364917710318 – ident: ref43 doi: 10.1109/ICCV.2019.00299 – ident: ref25 doi: 10.1109/IROS.2007.4399052 – ident: ref22 doi: 10.1007/978-3-319-32552-1_38 – ident: ref24 doi: 10.1109/MRA.2004.1371616 – ident: ref182 doi: 10.1109/IROS.2015.7353481 – ident: ref212 doi: 10.1088/1748-3190/abe345 – ident: ref21 doi: 10.1109/70.246063 – ident: ref35 doi: 10.1142/S0219843622500116 – volume: 2 start-page: 6 year: 0 ident: ref41 article-title: 6DoF grasp planning by optimizing a deep learning scoring function publication-title: Proc Robot Sci Syst Workshop Revisiting Contact-Turning Probl Solution – ident: ref188 doi: 10.1016/j.compag.2022.106716 – ident: ref135 doi: 10.1109/CVPR.2019.00891 – ident: ref142 doi: 10.1109/IROS47612.2022.9981955 – ident: ref110 doi: 10.1109/LRA.2018.2852777 – ident: ref82 doi: 10.1109/ROBOT.1992.219918 – ident: ref169 doi: 10.1109/COASE.2019.8843059 – ident: ref174 doi: 10.1007/978-3-030-58548-8_34 – ident: ref15 doi: 10.3389/fnbot.2021.658280 – start-page: 67 year: 1977 ident: ref16 article-title: The theory of affordances publication-title: Perceiving Acting and Knowing Toward and Ecological Psychology – year: 1994 ident: ref23 publication-title: A Mathematical Introduction to Robotic Manipulation – ident: ref27 doi: 10.1109/ISIE.2006.296116 – ident: ref194 doi: 10.1109/ICRA.2012.6225101 – ident: ref184 doi: 10.1109/CVPR.2019.01291 – ident: ref62 doi: 10.15607/RSS.2021.XVII.024 – year: 0 ident: ref118 article-title: QT-Opt: Scalable deep reinforcement learning for vision-based robotic manipulation publication-title: Proc Conf Robot Learn – ident: ref148 doi: 10.15607/RSS.2017.XIII.058 – ident: ref161 doi: 10.1177/0278364912445831 – ident: ref101 doi: 10.1109/ICRA48506.2021.9561409 – ident: ref70 doi: 10.1109/IROS45743.2020.9340783
SSID	ssj0024903
Score	2.698252
Snippet	Grasping is the process of picking up an object by applying forces and torques at a set of contacts. Recent advances in deep learning methods have allowed...
SourceID	swepub proquest crossref ieee
SourceType	Open Access Repository Aggregation Database Enrichment Source Index Database Publisher
StartPage	1
SubjectTerms	Deep learning deep learning in robotics and automation Dexterous manipulation End effectors Force Grasping Grasping (robotics) Grippers perception for grasping and manipulation Shape Systematics Task analysis
Title	Deep Learning Approaches to Grasp Synthesis: A Review
URI	https://ieeexplore.ieee.org/document/10149823 https://www.proquest.com/docview/2872465160 https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-349565
Volume	39
WOSCitedRecordID	wos001019463600001&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: 1941-0468 databaseCode: RIE dateStart: 20040101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFH4R4kEP_sSIounBmHgYdLSjqzciogeDRtFwa7a2U6IBwoaJ_71tNxAOmnjasrRL871u77Wv7_sAzmLmy8DmDIOWZh41vz8v8qXyfKrDJCImRKWuUPiO9XrhYMAfimJ1VwujtXaHz3Td3rpcvhrLmd0qa1hdWR42SQlKjLG8WOuHWI87GWRLKeYRzMN5ThLzRv_xvm5lwuukGZpwgq34ICeqshpfLnOGOj_T3f7nCHdgqwgoUTufAbuwpkd7sLlEM7gPQUfrCSqYVF9Ru6AR1ynKxuhmGqUT9PQ1MpFgOkwvURvl-YIKPHev-1e3XiGX4ElCcOZFzJYDtQiNOVGJiaxiShWNksBy4kvi-4rxGIcSE0qSiCUYSwOKNI-oYs2IkQMoj8YjfQiIcYlpHHLjyxUNaBTz0FxxoFRs3D1JqtCYAyhkwSVuJS0-hFtTYC4M5MJCLgrIq3Cx6DHJeTT-aFuxyC61y0GtQm1uJFF8aakwK76m1XNv4Sqc54ZbdLTU2Z3hS1sYG4n37E0QuxwMjn55_zFs2GHkR_VqUM6mM30C6_IzG6bTUzfbvgE8UM5W
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwFD54A_XB68R5zYMIPnRLm3RpfBvecU7RKb6FNkl1KNtYq-C_N0k7nQ8KPrWUJITvpD0nPTnfB7CXMF-GNmcYNjTzqPn8ebEvledTHaUxMSEqdYXCLdZuR4-P_KYsVne1MFprd_hM1-yty-Wrvnyzv8rqVleWRwGZhGkzfuAX5Vrf1HrcCSFbUjGPYB6NspKY1zu31zUrFF4jQWQCCvbDCzlZlZ8R5jhrqPM0p4v_nOMSLJQhJWoWa2AZJnRvBebHiAZXITzWeoBKLtUn1CyJxHWG8j46G8bZAN199EwsmHWzQ9RERcagAvenJ52jc68UTPAkITj3YmYLghqEJpyo1MRWCaWKxmloWfEl8X3FeIIjiQklacxSjKUBRZpHVLEgZmQNpnr9nl4HxLjENIm48eaKhjROeGSuOFQqMQ6fpFWojwAUsmQTt6IWr8LtKjAXBnJhIRcl5FU4-OoxKJg0_mhbsciOtStArcLWyEiifNcyYfZ8gVV0b-Aq7BeG--poybOPuw9NYWwkXvJnQeyGMNz4ZfxdmD3vXLVE66J9uQlzdkrFwb0tmMqHb3obZuR73s2GO27lfQIk_dGd
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=Deep+Learning+Approaches+to+Grasp+Synthesis%3A+A+Review&rft.jtitle=IEEE+transactions+on+robotics&rft.au=Newbury%2C+Rhys&rft.au=Gu%2C+Morris&rft.au=Chumbley%2C+Lachlan&rft.au=Mousavian%2C+Arsalan&rft.date=2023-10-01&rft.pub=IEEE&rft.issn=1552-3098&rft.spage=1&rft.epage=22&rft_id=info:doi/10.1109%2FTRO.2023.3280597&rft.externalDocID=10149823
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