{"id":"https://openalex.org/W4416749785","doi":"https://doi.org/10.1109/iros60139.2025.11246581","title":"TagGuideBot: Enhancing Robot Intelligence with Object Tags and VLMs","display_name":"TagGuideBot: Enhancing Robot Intelligence with Object Tags and VLMs","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749785","doi":"https://doi.org/10.1109/iros60139.2025.11246581"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":null,"display_name":"Jiayi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jiayi Chen","raw_affiliation_strings":["Shenzhen University,Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University,Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),P.R. China","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693513","display_name":"Ying He","orcid":"https://orcid.org/0000-0002-7079-8682"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying He","raw_affiliation_strings":["Shenzhen University,College of Computer Science and Software Engineering,P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University,College of Computer Science and Software Engineering,P.R. China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103085687","display_name":"Fuxun Yu","orcid":"https://orcid.org/0000-0002-4880-6658"},"institutions":[{"id":"https://openalex.org/I67031392","display_name":"Carleton University","ror":"https://ror.org/02qtvee93","country_code":"CA","type":"education","lineage":["https://openalex.org/I67031392"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"F. Richard Yu","raw_affiliation_strings":["Carleton University,School of Information Technology,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carleton University,School of Information Technology,Canada","institution_ids":["https://openalex.org/I67031392"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42568667,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"842","last_page":"849"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.919700026512146,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.919700026512146,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.01810000091791153,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.010300000198185444,"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/robot","display_name":"Robot","score":0.6437000036239624},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6431000232696533},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.5799000263214111},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4970000088214874},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.47130000591278076},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4535999894142151},{"id":"https://openalex.org/keywords/semantic-mapping","display_name":"Semantic mapping","score":0.39079999923706055},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3790999948978424},{"id":"https://openalex.org/keywords/smt-placement-equipment","display_name":"SMT placement equipment","score":0.3650999963283539}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7888000011444092},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6437000036239624},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6431000232696533},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6398000121116638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6004999876022339},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5799000263214111},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4970000088214874},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.47130000591278076},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4535999894142151},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40610000491142273},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.39079999923706055},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C17511633","wikidata":"https://www.wikidata.org/wiki/Q830694","display_name":"SMT placement equipment","level":3,"score":0.3650999963283539},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.32019999623298645},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.2985999882221222},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2752000093460083},{"id":"https://openalex.org/C2781411174","wikidata":"https://www.wikidata.org/wiki/Q8034662","display_name":"Workcell","level":3,"score":0.27459999918937683},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.271699994802475},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26339998841285706},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2082511574","https://openalex.org/W2760103357","https://openalex.org/W3007769740","https://openalex.org/W4312396403","https://openalex.org/W4383097638","https://openalex.org/W4383108457","https://openalex.org/W4385403811","https://openalex.org/W4385430679","https://openalex.org/W4388660746","https://openalex.org/W4389665575","https://openalex.org/W4390873481","https://openalex.org/W4390873795","https://openalex.org/W4390874280","https://openalex.org/W4390874575","https://openalex.org/W4392866655","https://openalex.org/W4402354045","https://openalex.org/W4402354093","https://openalex.org/W4402716166","https://openalex.org/W4402727764","https://openalex.org/W4405785541"],"related_works":[],"abstract_inverted_index":{"This":[0],"research":[1],"aims":[2],"to":[3,27,57,82],"enhance":[4],"the":[5,64,72,95,108,127],"interaction":[6],"between":[7],"humans":[8],"and":[9,53,60,88,97,114],"robots,":[10],"especially":[11],"in":[12,63],"environments":[13],"with":[14,75],"multiple":[15],"similar":[16],"objects":[17,62,74],"or":[18],"semantic":[19],"ambiguities.":[20],"Traditional":[21],"command-based":[22],"interactions":[23],"typically":[24],"require":[25],"users":[26],"provide":[28],"precise":[29],"descriptions,":[30],"which":[31,47],"often":[32],"poses":[33],"a":[34,43,84],"significant":[35],"challenge.":[36],"To":[37],"address":[38],"this":[39],"issue,":[40],"we":[41,80],"propose":[42],"framework":[44],"named":[45],"Tag-GuideBot,":[46],"leverages":[48],"Visual":[49],"Language":[50],"Models":[51],"(VLMs)":[52],"utilizes":[54],"object":[55],"markers":[56],"help":[58],"locate":[59],"identify":[61],"environment.":[65],"By":[66],"integrating":[67],"positional":[68],"point":[69],"prompts":[70],"of":[71,90,99,120,136],"target":[73],"robot":[76],"motion":[77],"planning":[78],"models,":[79],"aim":[81],"achieve":[83],"more":[85],"accurate":[86],"understanding":[87],"execution":[89],"complex":[91,112],"commands,":[92],"thus":[93],"improving":[94],"efficiency":[96],"naturalness":[98],"interactions.":[100],"Experimental":[101],"results":[102],"demonstrate":[103],"that":[104],"TagGuideBot":[105],"effectively":[106],"addresses":[107],"challenges":[109],"posed":[110],"by":[111],"commands":[113],"environmental":[115],"complexities,":[116],"achieving":[117],"an":[118],"accuracy":[119],"66.3%":[121],"on":[122],"user":[123],"instructions":[124],"extended":[125],"beyond":[126],"training":[128],"set,":[129],"providing":[130],"solid":[131],"support":[132],"for":[133],"further":[134],"optimization":[135],"human-robot":[137],"interaction.":[138]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-28T00:00:00"}