{"id":"https://openalex.org/W2794537597","doi":"https://doi.org/10.1109/iros.2018.8593986","title":"Learning Synergies Between Pushing and Grasping with Self-Supervised Deep Reinforcement Learning","display_name":"Learning Synergies Between Pushing and Grasping with Self-Supervised Deep Reinforcement Learning","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2794537597","doi":"https://doi.org/10.1109/iros.2018.8593986","mag":"2794537597"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2018.8593986","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8593986","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1803.09956","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005577303","display_name":"Andy Zeng","orcid":"https://orcid.org/0000-0002-4319-2159"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andy Zeng","raw_affiliation_strings":["Princeton University"],"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004644695","display_name":"Shuran Song","orcid":"https://orcid.org/0000-0002-8768-7356"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuran Song","raw_affiliation_strings":["Princeton University"],"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090341246","display_name":"Stefan Welker","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefan Welker","raw_affiliation_strings":["Google","Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061866803","display_name":"Johnny Lee","orcid":"https://orcid.org/0000-0003-4993-654X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Johnny Lee","raw_affiliation_strings":["Google","Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100657503","display_name":"Alberto Rodr\u00edguez","orcid":"https://orcid.org/0000-0002-1119-4512"},"institutions":[{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alberto Rodriguez","raw_affiliation_strings":["Massachusetts Institute of Technology","Massachusetts Institute Of Technology#TAB#"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079619886","display_name":"Thomas Funkhouser","orcid":null},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Funkhouser","raw_affiliation_strings":["Princeton University"],"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5005577303"],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":5.4243,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.96190111,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4238","last_page":"4245"},"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/T10868","display_name":"Soft Robotics and Applications","score":0.9916999936103821,"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"}},{"id":"https://openalex.org/T10784","display_name":"Muscle activation and electromyography studies","score":0.9915000200271606,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7727077603340149},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7286577820777893},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.719976007938385},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6882926821708679},{"id":"https://openalex.org/keywords/prehensile-tail","display_name":"Prehensile tail","score":0.4934464991092682},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.490372896194458},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4287009537220001},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32946673035621643}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7727077603340149},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7286577820777893},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.719976007938385},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6882926821708679},{"id":"https://openalex.org/C136380597","wikidata":"https://www.wikidata.org/wiki/Q10508905","display_name":"Prehensile tail","level":2,"score":0.4934464991092682},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.490372896194458},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4287009537220001},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32946673035621643},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/iros.2018.8593986","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8593986","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1803.09956","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.09956","pdf_url":"https://arxiv.org/pdf/1803.09956","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2794537597","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1803.09956","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:dspace.mit.edu:1721.1/130010","is_oa":true,"landing_page_url":"https://dspace.mit.edu/bitstream/1721.1/130010/2/1803.09956.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv","raw_type":"http://purl.org/eprint/type/ConferencePaper"},{"id":"doi:10.48550/arxiv.1803.09956","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1803.09956","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1803.09956","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.09956","pdf_url":"https://arxiv.org/pdf/1803.09956","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W46565623","https://openalex.org/W1608593143","https://openalex.org/W1820657498","https://openalex.org/W1892339738","https://openalex.org/W1903029394","https://openalex.org/W1981667747","https://openalex.org/W1989021449","https://openalex.org/W2029342956","https://openalex.org/W2050708324","https://openalex.org/W2082511574","https://openalex.org/W2088043683","https://openalex.org/W2108598243","https://openalex.org/W2126496149","https://openalex.org/W2132602743","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2173564293","https://openalex.org/W2201912979","https://openalex.org/W2290564286","https://openalex.org/W2405660904","https://openalex.org/W2528489519","https://openalex.org/W2566265240","https://openalex.org/W2600030077","https://openalex.org/W2605916268","https://openalex.org/W2746553466","https://openalex.org/W2949117887","https://openalex.org/W2962746398","https://openalex.org/W2962867039","https://openalex.org/W2963030226","https://openalex.org/W2963411833","https://openalex.org/W2963446712","https://openalex.org/W2963654160","https://openalex.org/W2963678509","https://openalex.org/W2963892386","https://openalex.org/W2964161785","https://openalex.org/W2964335674","https://openalex.org/W4241088297","https://openalex.org/W6637242042","https://openalex.org/W6638667902","https://openalex.org/W6682849425","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6696204902","https://openalex.org/W6730149987","https://openalex.org/W6744542307"],"related_works":["https://openalex.org/W2201912979","https://openalex.org/W2902125520","https://openalex.org/W2810785043","https://openalex.org/W2528489519","https://openalex.org/W3135362564","https://openalex.org/W3004047800","https://openalex.org/W3038199190","https://openalex.org/W3168093159","https://openalex.org/W2964161785","https://openalex.org/W2963678509","https://openalex.org/W2963430173","https://openalex.org/W2963402657","https://openalex.org/W2963149945","https://openalex.org/W2962736495","https://openalex.org/W2194775991","https://openalex.org/W2108598243","https://openalex.org/W3082790508","https://openalex.org/W3208348590","https://openalex.org/W2995986219","https://openalex.org/W2895268904"],"abstract_inverted_index":{"Skilled":[0],"robotic":[1],"manipulation":[2],"benefits":[3],"from":[4,58,75,125],"complex":[5,164],"synergies":[6,57],"between":[7],"non-prehensile":[8],"(e.g.":[9,13],"pushing)":[10],"and":[11,27,41,54,94,113,119,154,174,180,211],"prehensile":[12],"grasping)":[14],"actions:":[15,79],"pushing":[16,37,134],"can":[17,31,144],"help":[18,32],"rearrange":[19],"cluttered":[20],"objects":[21,34],"to":[22,35,52,78,202],"make":[23,36],"space":[24],"for":[25,86,102],"arms":[26],"fingers;":[28],"likewise,":[29],"grasping":[30,177],"displace":[33],"movements":[38],"more":[39],"precise":[40],"collision-free.":[42],"In":[43,128],"this":[44,129],"work,":[45],"we":[46,157],"demonstrate":[47,194],"that":[48,73,136,143,159,195],"it":[49],"is":[50,198],"possible":[51],"discover":[53],"learn":[55],"these":[56],"scratch":[59],"through":[60],"model-free":[61],"deep":[62],"reinforcement":[63],"learning.":[64],"Our":[65],"method":[66,197],"involves":[67],"training":[68],"two":[69],"fully":[70],"convolutional":[71],"networks":[72,105],"map":[74],"visual":[76],"observations":[77],"one":[80],"infers":[81],"the":[82,97,100],"utility":[83],"of":[84,91,170,190,200],"pushes":[85],"a":[87,110,187],"dense":[88],"pixel-wise":[89],"sampling":[90],"end-effector":[92],"orientations":[93],"locations,":[95],"while":[96,140],"other":[98],"does":[99],"same":[101],"grasping.":[103],"Both":[104],"are":[106,114,123,214],"trained":[107],"jointly":[108],"in":[109,151],"Q-learning":[111],"framework":[112],"entirely":[115],"self-supervised":[116],"by":[117],"trial":[118],"error,":[120],"where":[121],"rewards":[122],"provided":[124],"successful":[126],"grasps.":[127],"way,":[130],"our":[131,160,196],"policy":[132],"learns":[133,163],"motions":[135],"enable":[137],"future":[138],"grasps,":[139],"learning":[141],"grasps":[142],"leverage":[145],"past":[146],"pushes.":[147],"During":[148],"picking":[149,181],"experiments":[150],"both":[152],"simulation":[153,212],"real-world":[155],"scenarios,":[156],"find":[158],"system":[161],"quickly":[162],"behaviors":[165],"even":[166],"amid":[167],"challenging":[168],"cases":[169],"tightly":[171],"packed":[172],"clutter,":[173],"achieves":[175],"better":[176],"success":[178],"rates":[179],"efficiencies":[182],"than":[183],"baseline":[184],"alternatives":[185],"after":[186],"few":[188],"hours":[189],"training.":[191],"We":[192],"further":[193],"capable":[199],"generalizing":[201],"novel":[203],"objects.":[204],"Qualitative":[205],"results":[206],"(videos),":[207],"code,":[208],"pre-trained":[209],"models,":[210],"environments":[213],"available":[215],"at":[216],"http://vpg.cs.princeton.edu/":[217]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}