{"id":"https://openalex.org/W4389667056","doi":"https://doi.org/10.1109/iros55552.2023.10341776","title":"A Grasp Pose is All You Need: Learning Multi-Fingered Grasping with Deep Reinforcement Learning from Vision and Touch","display_name":"A Grasp Pose is All You Need: Learning Multi-Fingered Grasping with Deep Reinforcement Learning from Vision and Touch","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389667056","doi":"https://doi.org/10.1109/iros55552.2023.10341776"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10341776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031347089","display_name":"Federico Ceola","orcid":"https://orcid.org/0000-0002-2356-0946"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]},{"id":"https://openalex.org/I4210139705","display_name":"Ingegneria dei Sistemi (Italy)","ror":"https://ror.org/03spsm219","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210139705"]},{"id":"https://openalex.org/I83816512","display_name":"University of Genoa","ror":"https://ror.org/0107c5v14","country_code":"IT","type":"education","lineage":["https://openalex.org/I83816512"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Federico Ceola","raw_affiliation_strings":["Istituto Italiano di Tecnologia (IIT),Humanoid Sensing and Perception (HSP),Genoa,Italy","Humanoid Sensing and Perception (HSP), Istituto Italiano di Tecnologia (IIT), Genoa, Italy","Dipartimento di Informatica, Bioingegneria, Robotica e Ingegneria dei Sistemi (DIBRIS), Laboratory for Computational and Statistical Learning (LCSL) and Machine Learning Genoa Center (MaLGa), University of Genoa, Genoa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto Italiano di Tecnologia (IIT),Humanoid Sensing and Perception (HSP),Genoa,Italy","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"Humanoid Sensing and Perception (HSP), Istituto Italiano di Tecnologia (IIT), Genoa, Italy","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"Dipartimento di Informatica, Bioingegneria, Robotica e Ingegneria dei Sistemi (DIBRIS), Laboratory for Computational and Statistical Learning (LCSL) and Machine Learning Genoa Center (MaLGa), University of Genoa, Genoa, Italy","institution_ids":["https://openalex.org/I4210139705","https://openalex.org/I83816512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012621119","display_name":"Elisa Maiettini","orcid":"https://orcid.org/0000-0002-0127-3014"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elisa Maiettini","raw_affiliation_strings":["Istituto Italiano di Tecnologia (IIT),Humanoid Sensing and Perception (HSP),Genoa,Italy","Humanoid Sensing and Perception (HSP), Istituto Italiano di Tecnologia (IIT), Genoa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto Italiano di Tecnologia (IIT),Humanoid Sensing and Perception (HSP),Genoa,Italy","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"Humanoid Sensing and Perception (HSP), Istituto Italiano di Tecnologia (IIT), Genoa, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061220999","display_name":"Lorenzo Rosasco","orcid":"https://orcid.org/0000-0003-3098-383X"},"institutions":[{"id":"https://openalex.org/I4210139705","display_name":"Ingegneria dei Sistemi (Italy)","ror":"https://ror.org/03spsm219","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210139705"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]},{"id":"https://openalex.org/I83816512","display_name":"University of Genoa","ror":"https://ror.org/0107c5v14","country_code":"IT","type":"education","lineage":["https://openalex.org/I83816512"]}],"countries":["IT","US"],"is_corresponding":false,"raw_author_name":"Lorenzo Rosasco","raw_affiliation_strings":["University of Genoa,Laboratory for Computational and Statistical Learning (LCSL) and Machine Learning Genoa Center (MaLGa),Dipartimento di Informatica, Bioingegneria, Robotica e Ingegneria dei Sistemi (DIBRIS),Genoa,Italy","Dipartimento di Informatica, Bioingegneria, Robotica e Ingegneria dei Sistemi (DIBRIS), Laboratory for Computational and Statistical Learning (LCSL) and Machine Learning Genoa Center (MaLGa), University of Genoa, Genoa, Italy","Center for Brains, Minds and Machines (CBMM), Istituto Italiano di Tecnologia (IIT), Massachusetts Institute of Technology (MIT), Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Genoa,Laboratory for Computational and Statistical Learning (LCSL) and Machine Learning Genoa Center (MaLGa),Dipartimento di Informatica, Bioingegneria, Robotica e Ingegneria dei Sistemi (DIBRIS),Genoa,Italy","institution_ids":["https://openalex.org/I4210139705","https://openalex.org/I83816512"]},{"raw_affiliation_string":"Dipartimento di Informatica, Bioingegneria, Robotica e Ingegneria dei Sistemi (DIBRIS), Laboratory for Computational and Statistical Learning (LCSL) and Machine Learning Genoa Center (MaLGa), University of Genoa, Genoa, Italy","institution_ids":["https://openalex.org/I4210139705","https://openalex.org/I83816512"]},{"raw_affiliation_string":"Center for Brains, Minds and Machines (CBMM), Istituto Italiano di Tecnologia (IIT), Massachusetts Institute of Technology (MIT), Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009034971","display_name":"Lorenzo Natale","orcid":"https://orcid.org/0000-0002-8777-5233"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lorenzo Natale","raw_affiliation_strings":["Istituto Italiano di Tecnologia (IIT),Humanoid Sensing and Perception (HSP),Genoa,Italy","Humanoid Sensing and Perception (HSP), Istituto Italiano di Tecnologia (IIT), Genoa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto Italiano di Tecnologia (IIT),Humanoid Sensing and Perception (HSP),Genoa,Italy","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"Humanoid Sensing and Perception (HSP), Istituto Italiano di Tecnologia (IIT), Genoa, Italy","institution_ids":["https://openalex.org/I30771326"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0325,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77473003,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2985","last_page":"2992"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/icub","display_name":"iCub","score":0.9844202995300293},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.8249726891517639},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7727259993553162},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7433174252510071},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.707317054271698},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6410164833068848},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.5942015647888184},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5269965529441833},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4721653163433075},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.453773558139801},{"id":"https://openalex.org/keywords/physics-engine","display_name":"Physics engine","score":0.43342846632003784},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4167676866054535},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.41401106119155884},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.375802218914032},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34358280897140503},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13115766644477844},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.07932737469673157}],"concepts":[{"id":"https://openalex.org/C111151474","wikidata":"https://www.wikidata.org/wiki/Q1653368","display_name":"iCub","level":4,"score":0.9844202995300293},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.8249726891517639},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7727259993553162},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7433174252510071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.707317054271698},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6410164833068848},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.5942015647888184},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5269965529441833},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4721653163433075},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.453773558139801},{"id":"https://openalex.org/C190390380","wikidata":"https://www.wikidata.org/wiki/Q62505","display_name":"Physics engine","level":2,"score":0.43342846632003784},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4167676866054535},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.41401106119155884},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.375802218914032},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34358280897140503},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13115766644477844},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.07932737469673157},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10341776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G7163253977","display_name":null,"funder_award_id":"SLING 819789","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"},{"id":"https://openalex.org/G8338780757","display_name":null,"funder_award_id":"FA9550-18-1-7009,FA9550-17-1-0390,BAA-AFRL-AFOSR-2016-0007","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1963573260","https://openalex.org/W2001737341","https://openalex.org/W2158782408","https://openalex.org/W2161222115","https://openalex.org/W2213758982","https://openalex.org/W2529170537","https://openalex.org/W2600030077","https://openalex.org/W2736601468","https://openalex.org/W2736737714","https://openalex.org/W2741122588","https://openalex.org/W2904246096","https://openalex.org/W2962736495","https://openalex.org/W2962737955","https://openalex.org/W2963099939","https://openalex.org/W2963188159","https://openalex.org/W2963411833","https://openalex.org/W2973229164","https://openalex.org/W2990747716","https://openalex.org/W3081268564","https://openalex.org/W3092037789","https://openalex.org/W3099926824","https://openalex.org/W3203740651","https://openalex.org/W3211444363","https://openalex.org/W3211941939","https://openalex.org/W3216772467","https://openalex.org/W4205295909","https://openalex.org/W4283777363","https://openalex.org/W4287756699","https://openalex.org/W4288021242","https://openalex.org/W4320477822","https://openalex.org/W4383108784","https://openalex.org/W6631190155","https://openalex.org/W6741002519","https://openalex.org/W6742461812","https://openalex.org/W6757592117","https://openalex.org/W6770341929","https://openalex.org/W6770858630","https://openalex.org/W6779656125","https://openalex.org/W6785756301","https://openalex.org/W6788616948","https://openalex.org/W6789211778","https://openalex.org/W6791353385","https://openalex.org/W6802395018","https://openalex.org/W6803178138","https://openalex.org/W6804112224","https://openalex.org/W6804601995","https://openalex.org/W6843220310","https://openalex.org/W6849354660"],"related_works":["https://openalex.org/W2789446524","https://openalex.org/W2963178506","https://openalex.org/W4301244418","https://openalex.org/W2130280438","https://openalex.org/W3123424924","https://openalex.org/W1997666700","https://openalex.org/W1984314158","https://openalex.org/W2915059514","https://openalex.org/W2570508284","https://openalex.org/W2198321481"],"abstract_inverted_index":{"Multi-fingered":[0],"robotic":[1],"hands":[2],"have":[3,63],"potential":[4],"to":[5,8,17,29,44,96,100,147,152,174,190,207,239,244],"enable":[6],"robots":[7],"perform":[9],"sophisticated":[10],"manipulation":[11],"tasks.":[12],"However,":[13,59],"teaching":[14],"a":[15,165,179],"robot":[16],"grasp":[18,166],"objects":[19,212],"with":[20,184,211,237,251,254],"an":[21,25,145,170,255],"anthropomorphic":[22,137],"hand":[23,57,138],"is":[24,73,80,99,109,129,188,248],"arduous":[26],"problem":[27,72],"due":[28],"the":[30,75,78,88,125,136,140,154,157,176,185,194,198,201,214,226,240,246,252],"high":[31],"dimensionality":[32],"of":[33,51,77,91,114,139,156,231],"state":[34],"and":[35,116,192,204,234],"action":[36],"spaces.":[37],"Deep":[38],"Reinforcement":[39],"Learning":[40],"(DRL)":[41],"offers":[42],"techniques":[43,224],"design":[45],"control":[46,180],"policies":[47],"for":[48,66,82,135],"this":[49,98,108],"kind":[50],"problems":[52],"without":[53],"explicit":[54],"environment":[55,79],"or":[56],"modeling.":[58],"state-of-the-art":[60],"model-free":[61],"algorithms":[62],"proven":[64],"inefficient":[65],"learning":[67],"such":[68,83],"policies.":[69],"The":[70,159,242],"main":[71],"that":[74,219],"exploration":[76],"unfeasible":[81],"high-dimensional":[84],"problems,":[85,122],"thus":[86],"hampering":[87],"initial":[89],"phases":[90],"policy":[92,181],"optimization.":[93],"One":[94],"possibility":[95],"address":[97,120],"rely":[101],"on":[102],"off-line":[103],"task":[104,150],"demonstrations,":[105],"but,":[106],"oftentimes,":[107],"too":[110],"demanding":[111],"in":[112,225,229],"terms":[113,230],"time":[115,236],"computational":[117],"resources.":[118],"To":[119],"these":[121],"we":[123],"propose":[124],"A":[126],"Grasp":[127],"Pose":[128],"All":[130],"You":[131],"Need":[132],"(G-PAYN)":[133],"method":[134],"iCub":[141,199],"humanoid.":[142],"We":[143,196],"develop":[144],"approach":[146,210],"automatically":[148],"collect":[149],"demonstrations":[151],"initialize":[153],"training":[155],"policy.":[158],"proposed":[160,186],"grasping":[161],"pipeline":[162],"starts":[163],"from":[164,213],"pose":[167],"generated":[168],"by":[169],"external":[171],"algorithm,":[172],"used":[173,189],"initiate":[175],"movement.":[177],"Then":[178],"(previously":[182],"trained":[183],"G-PAYN)":[187],"reach":[191],"grab":[193],"object.":[195],"deployed":[197],"into":[200],"MuJoCo":[202],"simulator":[203],"use":[205],"it":[206],"test":[208],"our":[209],"YCB-Video":[215],"dataset.":[216],"Results":[217],"show":[218],"G-PAYN":[220],"outperforms":[221],"current":[222],"DRL":[223],"considered":[227],"setting":[228],"success":[232],"rate":[233],"execution":[235],"respect":[238],"baselines.":[241],"code":[243],"reproduce":[245],"experiments":[247],"released":[249],"together":[250],"paper":[253],"open":[256],"source":[257],"license":[258],"<sup":[259,262],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[260,263],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[261,264],"https://github.com/hsp-iit/rl-icub-dexterous-manipulation.":[265]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2023-12-14T00:00:00"}