{"id":"https://openalex.org/W4414359457","doi":"https://doi.org/10.24963/ijcai.2025/976","title":"Language-Conditioned Open-Vocabulary Mobile Manipulation with Pretrained Models","display_name":"Language-Conditioned Open-Vocabulary Mobile Manipulation with Pretrained Models","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359457","doi":"https://doi.org/10.24963/ijcai.2025/976"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/976","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/976","pdf_url":"https://www.ijcai.org/proceedings/2025/0976.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2025/0976.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103830131","display_name":"Shen Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shen Tan","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008623529","display_name":"Dong Zhou","orcid":"https://orcid.org/0000-0003-0855-8327"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Zhou","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102860748","display_name":"Xiangyu Shao","orcid":"https://orcid.org/0000-0002-7779-2267"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Shao","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102863521","display_name":"Junqiao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junqiao Wang","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101430467","display_name":"Guanghui Sun","orcid":"https://orcid.org/0000-0002-9072-1236"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanghui Sun","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":1.6571,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85095283,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"8778","last_page":"8786"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9955000281333923,"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":0.9955000281333923,"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":0.994700014591217,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9569000005722046,"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/desk","display_name":"Desk","score":0.6699000000953674},{"id":"https://openalex.org/keywords/workspace","display_name":"Workspace","score":0.6629999876022339},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.609000027179718},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.5620999932289124},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.3783000111579895},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.37790000438690186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7652999758720398},{"id":"https://openalex.org/C2776545233","wikidata":"https://www.wikidata.org/wiki/Q1064858","display_name":"Desk","level":2,"score":0.6699000000953674},{"id":"https://openalex.org/C58581272","wikidata":"https://www.wikidata.org/wiki/Q12741163","display_name":"Workspace","level":3,"score":0.6629999876022339},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.609000027179718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5960999727249146},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.5620999932289124},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5547999739646912},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3783000111579895},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C2988145974","wikidata":"https://www.wikidata.org/wiki/Q620615","display_name":"Mobile apps","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.3330000042915344},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.31049999594688416},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2775000035762787},{"id":"https://openalex.org/C156273044","wikidata":"https://www.wikidata.org/wiki/Q4913766","display_name":"Bin","level":2,"score":0.27320000529289246}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/976","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/976","pdf_url":"https://www.ijcai.org/proceedings/2025/0976.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2025/976","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/976","pdf_url":"https://www.ijcai.org/proceedings/2025/0976.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2641237906","display_name":null,"funder_award_id":"62403162","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414359457.pdf","grobid_xml":"https://content.openalex.org/works/W4414359457.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Open-vocabulary":[0],"mobile":[1,51],"manipulation":[2,52,127],"(OVMM)":[3],"that":[4],"involves":[5],"the":[6,39,73,77,82,86,90,93,96,99],"handling":[7],"of":[8,61,116],"novel":[9,30],"and":[10,44,88,112,129],"unseen":[11],"objects":[12],"across":[13],"different":[14],"workspaces":[15],"remains":[16],"a":[17,29],"significant":[18],"challenge":[19],"for":[20],"real-world":[21],"robotic":[22],"applications.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27],"propose":[28],"Language-conditioned":[31],"Open-Vocabulary":[32],"Mobile":[33],"Manipulation":[34],"framework,":[35],"named":[36],"LOVMM,":[37],"incorporating":[38],"large":[40],"language":[41,69],"model":[42,46],"(LLM)":[43],"vision-language":[45],"(VLM)":[47],"to":[48,81,95,124,135],"tackle":[49],"various":[50,63],"tasks":[53,65,128],"in":[54,85,98,104],"household":[55,106],"environments.":[56],"Our":[57],"approach":[58,120],"is":[59],"capable":[60],"solving":[62],"OVMM":[64],"with":[66],"free-form":[67],"natural":[68],"instructions":[70],"(e.g.":[71],"\"toss":[72],"food":[74],"boxes":[75],"on":[76],"office":[78],"room":[79],"desk":[80],"trash":[83],"bin":[84],"corner\",":[87],"\"pack":[89],"bottles":[91],"from":[92],"bed":[94],"box":[97],"guestroom\").":[100],"Extensive":[101],"experiments":[102],"simulated":[103],"complex":[105],"environments":[107],"show":[108],"strong":[109],"zero-shot":[110],"generalization":[111],"multi-task":[113],"learning":[114],"abilities":[115],"LOVMM.":[117],"Moreover,":[118],"our":[119],"can":[121],"also":[122],"generalize":[123],"multiple":[125],"tabletop":[126],"achieve":[130],"better":[131],"success":[132],"rates":[133],"compared":[134],"other":[136],"state-of-the-art":[137],"methods.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}
