{"id":"https://openalex.org/W7134833748","doi":"https://doi.org/10.1109/tase.2026.3671848","title":"A Robot System for Indoor Environment Question Answering With Cognitive Map Leveraging Vision-Language Models","display_name":"A Robot System for Indoor Environment Question Answering With Cognitive Map Leveraging Vision-Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7134833748","doi":"https://doi.org/10.1109/tase.2026.3671848"},"language":null,"primary_location":{"id":"doi:10.1109/tase.2026.3671848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3671848","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automation Science and Engineering","raw_type":"journal-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/A5087150523","display_name":"Chih-Hung Tu","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chih-Hung Tu","raw_affiliation_strings":["Department of Electrical Engineering, National Taiwan University (NTU), Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Taiwan University (NTU), Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101801635","display_name":"Fu-Hao Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Fu-Hao Chang","raw_affiliation_strings":["Department of Electrical Engineering, National Taiwan University (NTU), Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Taiwan University (NTU), Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128655082","display_name":"Chih-Hsiang Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chih-Hsiang Cheng","raw_affiliation_strings":["Department of Electrical Engineering, National Taiwan University (NTU), Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Taiwan University (NTU), Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128654176","display_name":"Li-Chen Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Li-Chen Fu","raw_affiliation_strings":["NTU Center for Artificial Intelligence and Advanced Robotics, National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"NTU Center for Artificial Intelligence and Advanced Robotics, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5087150523"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.78894447,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":null,"first_page":"6090","last_page":"6101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8482999801635742,"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":0.8482999801635742,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.06679999828338623,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0357000008225441,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.8260999917984009},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6243000030517578},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5625},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5519999861717224},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.5216000080108643},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.47049999237060547},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.46709999442100525},{"id":"https://openalex.org/keywords/cognitive-map","display_name":"Cognitive map","score":0.4431000053882599},{"id":"https://openalex.org/keywords/cognitive-systems","display_name":"Cognitive systems","score":0.44020000100135803}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8260999917984009},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7560999989509583},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6243000030517578},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5594000220298767},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5523999929428101},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5519999861717224},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5216000080108643},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.47049999237060547},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.46709999442100525},{"id":"https://openalex.org/C170494330","wikidata":"https://www.wikidata.org/wiki/Q1778434","display_name":"Cognitive map","level":3,"score":0.4431000053882599},{"id":"https://openalex.org/C2986342778","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Cognitive systems","level":3,"score":0.44020000100135803},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.38190001249313354},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3797999918460846},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.36899998784065247},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3070000112056732},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.3068999946117401},{"id":"https://openalex.org/C61641136","wikidata":"https://www.wikidata.org/wiki/Q1107019","display_name":"Cognitive load","level":3,"score":0.30219998955726624},{"id":"https://openalex.org/C2777371692","wikidata":"https://www.wikidata.org/wiki/Q2178611","display_name":"Spatial cognition","level":3,"score":0.28459998965263367},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.257999986410141},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.2572000026702881},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2026.3671848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3671848","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W1969483458","https://openalex.org/W1973876344","https://openalex.org/W2011835662","https://openalex.org/W2106673546","https://openalex.org/W2130763585","https://openalex.org/W2152536965","https://openalex.org/W2593841437","https://openalex.org/W2745461083","https://openalex.org/W2854445389","https://openalex.org/W2930283066","https://openalex.org/W2950697717","https://openalex.org/W2963800628","https://openalex.org/W2964339842","https://openalex.org/W2970499014","https://openalex.org/W3009928773","https://openalex.org/W3044538580","https://openalex.org/W3173736705","https://openalex.org/W4200184564","https://openalex.org/W4207072548","https://openalex.org/W4296890702","https://openalex.org/W4297243437","https://openalex.org/W4312336574","https://openalex.org/W4319300119","https://openalex.org/W4324125087","https://openalex.org/W4385245566","https://openalex.org/W4386076522","https://openalex.org/W4389819300","https://openalex.org/W7133220561"],"related_works":[],"abstract_inverted_index":{"The":[0,50],"paper":[1,78],"introduces":[2],"\u201dEnvironment":[3],"Question":[4,13],"Answering":[5,14],"(EnvQA),\u201d":[6],"an":[7],"advanced":[8],"task":[9],"derived":[10],"from":[11],"Embodied":[12],"(EQA),":[15],"aiming":[16],"to":[17,46,55,92,130,135],"enhance":[18,131],"the":[19,77,102,111,132,142],"practicality":[20],"of":[21,33,72,113],"robotic":[22],"systems":[23],"in":[24,96,118],"real-world":[25],"scenarios.":[26],"Unlike":[27],"EQA,":[28],"which":[29,87],"involves":[30],"repeated":[31],"exploration":[32],"familiar":[34],"environments":[35],"for":[36],"answering":[37],"questions,":[38],"EnvQA":[39,51],"integrates":[40],"spatial":[41],"memory":[42],"and":[43,60,116,121,137],"user":[44],"feedback":[45],"address":[47],"these":[48],"limitations.":[49],"system":[52],"is":[53],"designed":[54],"autonomously":[56],"navigate,":[57],"answer":[58],"queries,":[59],"store":[61],"environmental":[62],"information":[63],"using":[64],"a":[65,80],"cognition-inspired":[66],"cognitive":[67],"map":[68],"with":[69,141],"intermediate":[70],"features":[71],"Vision-language":[73],"models":[74],"(VLMs).":[75],"Additionally,":[76],"presents":[79],"new":[81],"zero-shot":[82],"image-image":[83],"matching":[84],"method,":[85],"ViTPR,":[86],"utilizes":[88],"large-scale":[89],"vision":[90],"transformers":[91],"achieve":[93],"state-of-the-art":[94],"performance":[95],"Visual":[97],"Place":[98],"Recognition":[99],"(VPR)":[100],"on":[101],"highly":[103],"challenging":[104],"Nordland":[105],"dataset.":[106],"Experimental":[107],"results":[108],"also":[109],"demonstrate":[110],"effectiveness":[112],"global":[114],"localization":[115],"question-answering":[117],"both":[119],"simulated":[120],"physical":[122],"environments.":[123],"In":[124],"summary,":[125],"we":[126],"successfully":[127],"use":[128],"VLMs":[129],"robot\u2019s":[133],"ability":[134],"understand":[136],"associate":[138],"human":[139],"questions":[140],"environment.":[143]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-11T00:00:00"}
