{"id":"https://openalex.org/W2894988833","doi":"https://doi.org/10.1109/icra.2019.8794074","title":"A Practical Approach to Insertion with Variable Socket Position Using Deep Reinforcement Learning","display_name":"A Practical Approach to Insertion with Variable Socket Position Using Deep Reinforcement Learning","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2894988833","doi":"https://doi.org/10.1109/icra.2019.8794074","mag":"2894988833"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2019.8794074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8794074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","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/1810.01531","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032877928","display_name":"Mel Vecer\u00edk","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mel Vecerik","raw_affiliation_strings":["DeepMind, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061512729","display_name":"Oleg Sushkov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oleg Sushkov","raw_affiliation_strings":["DeepMind, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108639255","display_name":"David Barker","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David Barker","raw_affiliation_strings":["DeepMind, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015856388","display_name":"Thomas Roth\u00f6rl","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Rothorl","raw_affiliation_strings":["DeepMind, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048229171","display_name":"Todd Hester","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Todd Hester","raw_affiliation_strings":["DeepMind, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014848474","display_name":"Jon Scholz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jon Scholz","raw_affiliation_strings":["DeepMind, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8431,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.72663764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"754","last_page":"760"},"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":0.9980000257492065,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/computer-science","display_name":"Computer science","score":0.6964980363845825},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6891714334487915},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.682628870010376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6665661334991455},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.6185963749885559},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5773180723190308},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4907156229019165},{"id":"https://openalex.org/keywords/orientation","display_name":"Orientation (vector space)","score":0.46523207426071167},{"id":"https://openalex.org/keywords/haptic-technology","display_name":"Haptic technology","score":0.4411925971508026},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4401059150695801},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.43204349279403687},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.34378719329833984},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13785994052886963},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08518514037132263}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6964980363845825},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6891714334487915},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.682628870010376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6665661334991455},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6185963749885559},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5773180723190308},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4907156229019165},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.46523207426071167},{"id":"https://openalex.org/C152086174","wikidata":"https://www.wikidata.org/wiki/Q3030571","display_name":"Haptic technology","level":2,"score":0.4411925971508026},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4401059150695801},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.43204349279403687},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.34378719329833984},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13785994052886963},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08518514037132263},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra.2019.8794074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8794074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1810.01531","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.01531","pdf_url":"https://arxiv.org/pdf/1810.01531","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:2894988833","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1810.01531","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":"doi:10.48550/arxiv.1810.01531","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1810.01531","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:1810.01531","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.01531","pdf_url":"https://arxiv.org/pdf/1810.01531","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2894988833.pdf","grobid_xml":"https://content.openalex.org/works/W2894988833.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W101508493","https://openalex.org/W2113486533","https://openalex.org/W2131119817","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2173248099","https://openalex.org/W2584009249","https://openalex.org/W2610395436","https://openalex.org/W2619484182","https://openalex.org/W2732547613","https://openalex.org/W2741122588","https://openalex.org/W2748919602","https://openalex.org/W2750745447","https://openalex.org/W2756826236","https://openalex.org/W2788862220","https://openalex.org/W2792036039","https://openalex.org/W2803158784","https://openalex.org/W2808844346","https://openalex.org/W2952629144","https://openalex.org/W2962792802","https://openalex.org/W2963634205","https://openalex.org/W2963940579","https://openalex.org/W2964161785","https://openalex.org/W2964227158","https://openalex.org/W6682849425","https://openalex.org/W6683300800","https://openalex.org/W6684921986","https://openalex.org/W6728925229","https://openalex.org/W6738746681","https://openalex.org/W6742461812","https://openalex.org/W6744564315","https://openalex.org/W6748645729","https://openalex.org/W6751438039","https://openalex.org/W6752818329"],"related_works":["https://openalex.org/W2967355195","https://openalex.org/W3159735414","https://openalex.org/W3032216251","https://openalex.org/W2774559822","https://openalex.org/W3174740958","https://openalex.org/W3095065393","https://openalex.org/W3120428840","https://openalex.org/W3089337217","https://openalex.org/W2521863123","https://openalex.org/W2982252571","https://openalex.org/W3207601508","https://openalex.org/W3037691451","https://openalex.org/W2771549791","https://openalex.org/W2725320964","https://openalex.org/W3091857413","https://openalex.org/W3132708124","https://openalex.org/W3003177163","https://openalex.org/W2186735349","https://openalex.org/W2999343182","https://openalex.org/W1969104618"],"abstract_inverted_index":{"Insertion":[0],"is":[1,29,55],"a":[2,47,56,101,149,154],"challenging":[3],"haptic":[4],"and":[5,34,38,118,140,153,189,202],"visual":[6],"control":[7],"problem":[8,45],"with":[9,100],"significant":[10],"practical":[11],"value":[12],"for":[13],"manufacturing.":[14],"Existing":[15],"approaches":[16,64],"in":[17,163,181,198],"the":[18,51,108,164,178,191,199],"model-based":[19],"robotics":[20],"community":[21,53],"can":[22,173],"be":[23,40,174],"highly":[24],"effective":[25],"when":[26],"task":[27,152],"geometry":[28],"known,":[30],"but":[31,62],"are":[32,65,194],"complex":[33],"cumbersome":[35],"to":[36,42,69,77,93,110,113,196],"implement,":[37],"must":[39],"tailored":[41],"each":[43],"individual":[44],"by":[46],"qualified":[48],"engineer.":[49],"Within":[50],"learning":[52],"there":[54],"long":[57],"history":[58],"of":[59,104,159,186],"insertion":[60],"research,":[61],"existing":[63],"either":[66],"too":[67],"sample-inefficient":[68],"run":[70],"on":[71,148,177],"real":[72,179],"robots,":[73],"or":[74,125,130],"assume":[75],"access":[76],"high-level":[78],"object":[79],"features,":[80],"e.g.":[81],"socket":[82,165,200],"pose.":[83],"In":[84],"this":[85],"paper":[86],"we":[87],"show":[88,169],"that":[89,170,190],"relatively":[90],"minor":[91],"modifications":[92],"an":[94],"off-the-shelf":[95],"Deep-RL":[96],"algorithm":[97],"(DDPG),":[98],"combined":[99],"small":[102],"number":[103],"human":[105],"demonstrations,":[106],"allows":[107],"robot":[109,180],"quickly":[111],"learn":[112],"solve":[114],"these":[115,171],"tasks":[116,172],"efficiently":[117],"robustly.":[119],"Our":[120,167],"approach":[121,147],"requires":[122],"no":[123,127,133,141],"modeling":[124],"simulation,":[126],"parameterized":[128],"search":[129],"alignment":[131],"behaviors,":[132],"vision":[134],"system":[135],"aside":[136],"from":[137],"raw":[138],"images,":[139],"reward":[142],"shaping.":[143],"We":[144],"evaluate":[145],"our":[146],"narrow-clearance":[150],"peg-insertion":[151],"deformable":[155],"clip-insertion":[156],"task,":[157],"both":[158],"which":[160],"include":[161],"variability":[162],"position.":[166],"results":[168],"solved":[175],"reliably":[176],"less":[182],"than":[183],"10":[184],"minutes":[185],"interaction":[187],"time,":[188],"resulting":[192],"policies":[193],"robust":[195],"variance":[197],"position":[201],"orientation.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}