{"id":"https://openalex.org/W4413917664","doi":"https://doi.org/10.1109/icra55743.2025.11127975","title":"Closed-Loop Open-Vocabulary Mobile Manipulation with GPT-4V","display_name":"Closed-Loop Open-Vocabulary Mobile Manipulation with GPT-4V","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413917664","doi":"https://doi.org/10.1109/icra55743.2025.11127975"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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/A5087547525","display_name":"Peiyuan Zhi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4392738278","display_name":"Beijing Institute for General Artificial Intelligence","ror":"https://ror.org/02kw1ws04","country_code":"CN","type":"government","lineage":["https://openalex.org/I4392738278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiyuan Zhi","raw_affiliation_strings":["Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4392738278"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100403342","display_name":"Zhiyuan Zhang","orcid":"https://orcid.org/0000-0002-2910-1986"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4392738278","display_name":"Beijing Institute for General Artificial Intelligence","ror":"https://ror.org/02kw1ws04","country_code":"CN","type":"government","lineage":["https://openalex.org/I4392738278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Zhang","raw_affiliation_strings":["Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4392738278"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101658897","display_name":"Yu Zhao","orcid":"https://orcid.org/0000-0002-4818-8685"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4392738278","display_name":"Beijing Institute for General Artificial Intelligence","ror":"https://ror.org/02kw1ws04","country_code":"CN","type":"government","lineage":["https://openalex.org/I4392738278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhao","raw_affiliation_strings":["Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4392738278"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070386263","display_name":"Muzhi Han","orcid":"https://orcid.org/0000-0002-2649-4577"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muzhi Han","raw_affiliation_strings":["University of California,Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100358728","display_name":"Zeyu Zhang","orcid":"https://orcid.org/0000-0002-3628-141X"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4392738278","display_name":"Beijing Institute for General Artificial Intelligence","ror":"https://ror.org/02kw1ws04","country_code":"CN","type":"government","lineage":["https://openalex.org/I4392738278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyu Zhang","raw_affiliation_strings":["Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4392738278"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017751636","display_name":"Zhitian Li","orcid":"https://orcid.org/0000-0002-0996-0011"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4392738278","display_name":"Beijing Institute for General Artificial Intelligence","ror":"https://ror.org/02kw1ws04","country_code":"CN","type":"government","lineage":["https://openalex.org/I4392738278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhitian Li","raw_affiliation_strings":["Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4392738278"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084328887","display_name":"Ziyuan Jiao","orcid":"https://orcid.org/0000-0003-3404-3810"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4392738278","display_name":"Beijing Institute for General Artificial Intelligence","ror":"https://ror.org/02kw1ws04","country_code":"CN","type":"government","lineage":["https://openalex.org/I4392738278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyuan Jiao","raw_affiliation_strings":["Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4392738278"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067007325","display_name":"Baoxiong Jia","orcid":"https://orcid.org/0000-0002-4968-3290"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4392738278","display_name":"Beijing Institute for General Artificial Intelligence","ror":"https://ror.org/02kw1ws04","country_code":"CN","type":"government","lineage":["https://openalex.org/I4392738278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoxiong Jia","raw_affiliation_strings":["Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4392738278"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067080265","display_name":"Siyuan Huang","orcid":"https://orcid.org/0000-0003-1524-7148"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4392738278","display_name":"Beijing Institute for General Artificial Intelligence","ror":"https://ror.org/02kw1ws04","country_code":"CN","type":"government","lineage":["https://openalex.org/I4392738278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Huang","raw_affiliation_strings":["Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute for General Artificial Intelligence (BIGAI),State Key Laboratory of General Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4392738278"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.5877,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.99055852,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4761","last_page":"4767"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9767000079154968,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9767000079154968,"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/T12031","display_name":"Speech and dialogue systems","score":0.9746000170707703,"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/T12128","display_name":"AI in Service Interactions","score":0.9667999744415283,"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/open-loop-controller","display_name":"Open-loop controller","score":0.6469846963882446},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6101946830749512},{"id":"https://openalex.org/keywords/closed-loop","display_name":"Closed loop","score":0.6077970862388611},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.45479539036750793},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.43209874629974365},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.16763952374458313},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13512223958969116},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10549205541610718},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0630561113357544}],"concepts":[{"id":"https://openalex.org/C161362739","wikidata":"https://www.wikidata.org/wiki/Q2301555","display_name":"Open-loop controller","level":3,"score":0.6469846963882446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6101946830749512},{"id":"https://openalex.org/C3019251811","wikidata":"https://www.wikidata.org/wiki/Q5135346","display_name":"Closed loop","level":2,"score":0.6077970862388611},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.45479539036750793},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.43209874629974365},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.16763952374458313},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13512223958969116},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10549205541610718},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0630561113357544},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2143936212","https://openalex.org/W3089355520","https://openalex.org/W3189688664","https://openalex.org/W3189699967","https://openalex.org/W4225683910","https://openalex.org/W4383097638","https://openalex.org/W4383108457","https://openalex.org/W4385430679","https://openalex.org/W4386251907","https://openalex.org/W4388936652","https://openalex.org/W4402354102","https://openalex.org/W4402968400","https://openalex.org/W4403277141"],"related_works":["https://openalex.org/W2322335058","https://openalex.org/W2259382430","https://openalex.org/W2397460850","https://openalex.org/W4322484979","https://openalex.org/W2612895087","https://openalex.org/W2757957551","https://openalex.org/W2774292953","https://openalex.org/W2103982267","https://openalex.org/W2065196227","https://openalex.org/W2319944002"],"abstract_inverted_index":{"Autonomous":[0],"robot":[1],"navigation":[2],"and":[3,10,35,52,64,71,74,80,90,109,147],"manipulation":[4,111],"in":[5,38,118],"open":[6],"environments":[7],"require":[8],"reasoning":[9,34,54],"replanning":[11],"with":[12],"closed-loop":[13,23,78],"feedback.":[14],"In":[15],"this":[16],"work,":[17],"we":[18],"present":[19],"COME-robot,":[20],"the":[21,27,61],"first":[22],"robotic":[24],"system":[25],"utilizing":[26],"GPT-4V":[28],"vision-language":[29],"foundation":[30],"model":[31],"for":[32,97],"open-ended":[33],"adaptive":[36],"planning":[37],"real-world":[39,107],"scenarios.":[40],"COME-robot":[41,113],"incorporates":[42],"two":[43],"key":[44],"innovative":[45],"modules:":[46],"(i)":[47],"a":[48,115],"multi-level":[49],"open-vocabulary":[50],"perception":[51],"situated":[53,72],"module":[55],"that":[56,83],"enables":[57],"effective":[58],"exploration":[59],"of":[60],"3D":[62],"environment":[63],"target":[65],"object":[66],"identification":[67],"using":[68],"commonsense":[69],"knowledge":[70],"information,":[73],"(ii)":[75],"an":[76],"iterative":[77],"feedback":[79],"restoration":[81],"mechanism":[82],"verifies":[84],"task":[85,119,149],"feasibility,":[86],"monitors":[87],"execution":[88],"success,":[89],"traces":[91],"failure":[92,99,142],"causes":[93],"across":[94],"different":[95],"modules":[96],"robust":[98],"recovery.":[100],"Through":[101],"comprehensive":[102,134],"experiments":[103],"involving":[104],"8":[105],"challenging":[106],"mobile":[108],"tabletop":[110],"tasks,":[112],"demonstrates":[114],"significant":[116],"improvement":[117],"success":[120],"rate":[121],"(<tex":[122],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[123],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\sim":[124],"35":[125],"\\%$</tex>)":[126],"compared":[127],"to":[128,136],"state-of-the-art":[129],"methods.":[130],"We":[131],"further":[132],"conduct":[133],"analyses":[135],"elucidate":[137],"how":[138],"COME-robot's":[139],"design":[140],"facilitates":[141],"recovery,":[143],"free-form":[144],"instruction":[145],"following,":[146],"long-horizon":[148],"planning.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
