{"id":"https://openalex.org/W4401415664","doi":"https://doi.org/10.1109/icra57147.2024.10610177","title":"An offline learning of behavior correction policy for vision-based robotic manipulation","display_name":"An offline learning of behavior correction policy for vision-based robotic manipulation","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401415664","doi":"https://doi.org/10.1109/icra57147.2024.10610177"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610177","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10610177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5113325618","display_name":"Qingxiuxiong Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Qingxiuxiong Dong","raw_affiliation_strings":["Toshiba Corporation,Media AI Laboratory, Corporate Research and Development Center,Kawasaki,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Corporation,Media AI Laboratory, Corporate Research and Development Center,Kawasaki,Japan","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108669113","display_name":"Toshimitsu Kaneko","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshimitsu Kaneko","raw_affiliation_strings":["Toshiba Corporation,Media AI Laboratory, Corporate Research and Development Center,Kawasaki,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Corporation,Media AI Laboratory, Corporate Research and Development Center,Kawasaki,Japan","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072744508","display_name":"Masashi Sugiyama","orcid":"https://orcid.org/0000-0001-6658-6743"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masashi Sugiyama","raw_affiliation_strings":["RIKEN,Center for Advanced Intelligence Project,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN,Center for Advanced Intelligence Project,Japan","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7753,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.83098637,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5448","last_page":"5454"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9957000017166138,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9745000004768372,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6664639115333557},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5673638582229614},{"id":"https://openalex.org/keywords/robot-vision","display_name":"Robot vision","score":0.4824110269546509},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4492796063423157},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3953840136528015},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37047070264816284},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.3236961364746094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6664639115333557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5673638582229614},{"id":"https://openalex.org/C2983761899","wikidata":"https://www.wikidata.org/wiki/Q604674","display_name":"Robot vision","level":4,"score":0.4824110269546509},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4492796063423157},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3953840136528015},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37047070264816284},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3236961364746094}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610177","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10610177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2936503027","https://openalex.org/W2938269852","https://openalex.org/W3003266338","https://openalex.org/W3007769740","https://openalex.org/W3008273191","https://openalex.org/W3022566517","https://openalex.org/W3033324992","https://openalex.org/W3037440645","https://openalex.org/W3098143573","https://openalex.org/W3172360140","https://openalex.org/W3174849255","https://openalex.org/W3201700917","https://openalex.org/W4225947020","https://openalex.org/W4287209565","https://openalex.org/W4287756699","https://openalex.org/W4289115845","https://openalex.org/W4360584316","https://openalex.org/W4385430679","https://openalex.org/W4385473486","https://openalex.org/W6747473740","https://openalex.org/W6752007561","https://openalex.org/W6753243525","https://openalex.org/W6756848961","https://openalex.org/W6776438516","https://openalex.org/W6779265984","https://openalex.org/W6779656125","https://openalex.org/W6780159193","https://openalex.org/W6787713516","https://openalex.org/W6790920653","https://openalex.org/W6791413555","https://openalex.org/W6793853427","https://openalex.org/W6796589144","https://openalex.org/W6801009634","https://openalex.org/W6839256673","https://openalex.org/W6849204483","https://openalex.org/W6854738657"],"related_works":["https://openalex.org/W8302103","https://openalex.org/W3171631314","https://openalex.org/W2122871747","https://openalex.org/W3114279067","https://openalex.org/W2124872487","https://openalex.org/W2734090492","https://openalex.org/W2913954960","https://openalex.org/W2006288243","https://openalex.org/W2047155493","https://openalex.org/W2005171629"],"abstract_inverted_index":{"Offline":[0],"learning":[1,27,119,133,136],"usually":[2],"requires":[3],"a":[4,29,34,39,44,53,66,113],"large":[5],"dataset":[6],"for":[7],"training.":[8],"In":[9,99,138],"this":[10],"paper,":[11],"we":[12,141],"focus":[13],"on":[14,73],"vision-based":[15],"robotic":[16],"manipulation":[17],"tasks":[18],"and":[19,43,61,134,148],"utilize":[20],"certain":[21],"task":[22,86,152],"properties":[23,87],"to":[24,68,78,88],"achieve":[25],"offline":[26,118,131],"with":[28,93,129],"small":[30],"dataset.":[31],"We":[32,121],"propose":[33],"two-stage":[35,127],"agent":[36,128],"consisting":[37],"of":[38,103,116],"tentative":[40,49,54,70,80],"decision":[41,50],"stage":[42,51,64,84],"correction":[45,63,67,83,159],"stage,":[46],"where":[47],"the":[48,57,62,69,74,79,90,101,104,126,143,151,158],"determines":[52,65],"action":[55,71],"from":[56],"original":[58],"camera":[59],"image,":[60],"based":[72],"cropped":[75,91],"image":[76,92],"according":[77],"action.":[81],"The":[82],"utilizes":[85],"obtain":[89],"task-relevant":[94],"features,":[95],"enabling":[96],"efficient":[97],"correction.":[98],"particular,":[100],"training":[102],"two":[105],"stages":[106],"can":[107],"be":[108],"performed":[109],"individually,":[110],"which":[111],"enables":[112],"straightforward":[114],"application":[115],"general":[117],"algorithms.":[120,137],"conduct":[122],"experiments":[123],"by":[124,157],"combining":[125],"conventional":[130],"reinforcement":[132],"imitation":[135],"both":[139],"cases,":[140],"benchmark":[142],"proposed":[144],"method":[145],"using":[146],"RLBench":[147],"demonstrate":[149],"that":[150],"performance":[153],"is":[154],"significantly":[155],"improved":[156],"stage.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}