{"id":"https://openalex.org/W4413917574","doi":"https://doi.org/10.1109/icra55743.2025.11128444","title":"BUMBLE: Unifying Reasoning and Acting with Vision-Language Models for Building-wide Mobile Manipulation","display_name":"BUMBLE: Unifying Reasoning and Acting with Vision-Language Models for Building-wide Mobile Manipulation","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413917574","doi":"https://doi.org/10.1109/icra55743.2025.11128444"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128444","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":"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/A5047602471","display_name":"Rutav Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rutav Shah","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052967534","display_name":"Albert R. Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Albert Yu","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101638642","display_name":"Yifeng Zhu","orcid":"https://orcid.org/0000-0003-2580-5748"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifeng Zhu","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030826237","display_name":"Yuke Zhu","orcid":"https://orcid.org/0000-0002-9198-2227"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuke Zhu","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065655761","display_name":"Roberto Mart\u00edn-Mart\u00edn","orcid":"https://orcid.org/0000-0002-9586-2759"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roberto Mart\u00edn-Mart\u00edn","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":16.9371,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.99306221,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"13337","last_page":"13345"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9666000008583069,"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":0.9666000008583069,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9577000141143799,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T13382","display_name":"Robotics and Automated Systems","score":0.9422000050544739,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7087276577949524},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4210509955883026},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4088127613067627},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.32417795062065125},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08474692702293396}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7087276577949524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4210509955883026},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4088127613067627},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.32417795062065125},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08474692702293396}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128444","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":[{"id":"https://openalex.org/G7488983277","display_name":null,"funder_award_id":"FRR2145283,EFRI-2318065","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7528812362","display_name":null,"funder_award_id":"N00014-22-1-2204,N00014-24-1-2550","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1503861282","https://openalex.org/W1964695965","https://openalex.org/W1992653875","https://openalex.org/W2004094485","https://openalex.org/W2036288719","https://openalex.org/W2043822938","https://openalex.org/W2046365304","https://openalex.org/W2051155494","https://openalex.org/W2071470832","https://openalex.org/W2073924944","https://openalex.org/W2103332960","https://openalex.org/W2118897212","https://openalex.org/W2119955255","https://openalex.org/W2122287758","https://openalex.org/W2131622683","https://openalex.org/W2135639338","https://openalex.org/W2141841102","https://openalex.org/W2143936212","https://openalex.org/W2153000379","https://openalex.org/W2162434188","https://openalex.org/W2499457802","https://openalex.org/W2964055695","https://openalex.org/W2998903229","https://openalex.org/W3042275200","https://openalex.org/W3128894241","https://openalex.org/W3132058511","https://openalex.org/W3134972302","https://openalex.org/W3184282957","https://openalex.org/W3205400264","https://openalex.org/W3207057769","https://openalex.org/W4210613326","https://openalex.org/W4240202985","https://openalex.org/W4248415029","https://openalex.org/W4383097638","https://openalex.org/W4383108296","https://openalex.org/W4383108457","https://openalex.org/W4385430556","https://openalex.org/W4386251907","https://openalex.org/W4388660746","https://openalex.org/W4390874575","https://openalex.org/W4391407102","https://openalex.org/W4391559307","https://openalex.org/W4392866655","https://openalex.org/W4404612908","https://openalex.org/W4405785256","https://openalex.org/W4405786269","https://openalex.org/W4405786528"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"To":[0,42],"operate":[1],"at":[2],"a":[3,25,51,61],"building":[4],"scale,":[5],"service":[6],"robots":[7],"must":[8],"perform":[9],"long-horizon":[10,46,83],"mobile":[11,133],"manipulation":[12,134],"tasks":[13,37,85],"by":[14],"navigating":[15],"to":[16,35,90,130,147],"different":[17,108],"rooms,":[18],"accessing":[19],"multiple":[20],"floors,":[21],"and":[22,27,68,111],"interacting":[23],"with":[24],"wide":[26,62],"unseen":[28],"range":[29],"of":[30,64,141],"everyday":[31],"objects.":[32],"We":[33],"refer":[34],"these":[36,44],"as":[38],"Building-wide":[39],"Mobile":[40],"Manipulation.":[41],"tackle":[43],"inherently":[45],"tasks,":[47,110],"we":[48,137],"introduce":[49],"BUMBLE,":[50],"unified":[52],"Vision-Language":[53],"Model":[54],"(VLM)-based":[55],"framework":[56,128],"integrating":[57],"open-world":[58],"RGB-D":[59],"perception,":[60],"spectrum":[63],"gross-to-fine":[65],"motor":[66],"skills,":[67,92],"dual-layered":[69],"memory.":[70],"Our":[71,118],"extensive":[72],"evaluation":[73],"(90+":[74],"hours)":[75],"indicates":[76],"that":[77,86],"BUMBLE":[78,98],"outperforms":[79],"competitive":[80],"baselines":[81],"in":[82,107],"building-wide":[84],"require":[87],"sequencing":[88],"up":[89],"12":[91],"spanning":[93],"15":[94],"minutes":[95],"per":[96],"trial.":[97],"achieves":[99],"47.1%":[100],"success":[101],"rate":[102],"averaged":[103],"over":[104],"70":[105],"trials":[106],"buildings,":[109],"scene":[112],"layouts":[113],"from":[114],"various":[115],"starting":[116],"locations.":[117],"user":[119],"study":[120],"shows":[121],"22%":[122],"higher":[123],"task":[124],"satisfaction":[125],"using":[126,142],"our":[127],"compared":[129],"state-of-the-art":[131],"VLM-based":[132],"methods.":[135],"Finally,":[136],"show":[138],"the":[139,149],"potential":[140],"increasingly":[143],"capable":[144],"foundation":[145],"models":[146],"improve":[148],"system":[150],"performance":[151],"further.":[152],"For":[153],"more":[154],"information,":[155],"see":[156],"https://robin-lab.cs.utexas.edu/BUMBLE/":[157]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}