{"id":"https://openalex.org/W4416750593","doi":"https://doi.org/10.1109/iros60139.2025.11247072","title":"Observation-Graph Interaction and Key-Detail Guidance for Vision and Language Navigation","display_name":"Observation-Graph Interaction and Key-Detail Guidance for Vision and Language Navigation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750593","doi":"https://doi.org/10.1109/iros60139.2025.11247072"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247072","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":"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/A5101729450","display_name":"Yifan Xie","orcid":"https://orcid.org/0000-0002-7158-1514"},"institutions":[{"id":"https://openalex.org/I32820368","display_name":"Guangdong Polytechnic of Science and Technology","ror":"https://ror.org/01wq2p249","country_code":"CN","type":"education","lineage":["https://openalex.org/I32820368"]},{"id":"https://openalex.org/I4210142539","display_name":"Guangdong Institute of Intelligent Manufacturing","ror":"https://ror.org/049jpjz09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210142539"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yifan Xie","raw_affiliation_strings":["Guangdong Institute of Intelligence Science and Technology,Guangdong,China,519031"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Institute of Intelligence Science and Technology,Guangdong,China,519031","institution_ids":["https://openalex.org/I4210142539","https://openalex.org/I32820368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083251111","display_name":"Binkai Ou","orcid":null},"institutions":[{"id":"https://openalex.org/I29236304","display_name":"Advisory Board Company (United States)","ror":"https://ror.org/02q248z41","country_code":"US","type":"company","lineage":["https://openalex.org/I29236304"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Binkai Ou","raw_affiliation_strings":["BoardWare Information System Company Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BoardWare Information System Company Ltd","institution_ids":["https://openalex.org/I29236304"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062318925","display_name":"Fei Ma","orcid":"https://orcid.org/0000-0001-6099-480X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Ma","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100674174","display_name":"Yaohua Liu","orcid":"https://orcid.org/0000-0003-2016-1605"},"institutions":[{"id":"https://openalex.org/I32820368","display_name":"Guangdong Polytechnic of Science and Technology","ror":"https://ror.org/01wq2p249","country_code":"CN","type":"education","lineage":["https://openalex.org/I32820368"]},{"id":"https://openalex.org/I4210142539","display_name":"Guangdong Institute of Intelligent Manufacturing","ror":"https://ror.org/049jpjz09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210142539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaohua Liu","raw_affiliation_strings":["Guangdong Institute of Intelligence Science and Technology,Guangdong,China,519031"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Institute of Intelligence Science and Technology,Guangdong,China,519031","institution_ids":["https://openalex.org/I4210142539","https://openalex.org/I32820368"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101729450"],"corresponding_institution_ids":["https://openalex.org/I32820368","https://openalex.org/I4210142539"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35237392,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15306","last_page":"15313"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9866999983787537,"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":0.9866999983787537,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0032999999821186066,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0015999999595806003,"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/key","display_name":"Key (lock)","score":0.6007999777793884},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5099999904632568},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.506600022315979},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4878999888896942},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.4147000014781952},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4027000069618225},{"id":"https://openalex.org/keywords/navigation-system","display_name":"Navigation system","score":0.396699994802475},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.3714999854564667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7674999833106995},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6079999804496765},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6007999777793884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5397999882698059},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5220000147819519},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5099999904632568},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.506600022315979},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4878999888896942},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.4147000014781952},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4027000069618225},{"id":"https://openalex.org/C2777891301","wikidata":"https://www.wikidata.org/wiki/Q3475123","display_name":"Navigation system","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.3714999854564667},{"id":"https://openalex.org/C26990112","wikidata":"https://www.wikidata.org/wiki/Q6887224","display_name":"Mobile robot navigation","level":5,"score":0.3499000072479248},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3418000042438507},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C128644962","wikidata":"https://www.wikidata.org/wiki/Q683111","display_name":"Visual programming language","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247072","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1979266466","https://openalex.org/W2142661557","https://openalex.org/W2798483995","https://openalex.org/W2926977875","https://openalex.org/W2962744691","https://openalex.org/W2963800628","https://openalex.org/W2964339842","https://openalex.org/W2964935470","https://openalex.org/W3034500398","https://openalex.org/W3034728521","https://openalex.org/W3035390927","https://openalex.org/W3100923070","https://openalex.org/W3165915253","https://openalex.org/W3172675210","https://openalex.org/W3174887918","https://openalex.org/W3176974620","https://openalex.org/W3206064582","https://openalex.org/W4221167437","https://openalex.org/W4226052928","https://openalex.org/W4312295286","https://openalex.org/W4312434279","https://openalex.org/W4312501707","https://openalex.org/W4386065347","https://openalex.org/W4386072289","https://openalex.org/W4388543778","https://openalex.org/W4389524290","https://openalex.org/W4390871755","https://openalex.org/W4392173854","https://openalex.org/W4394627367","https://openalex.org/W4400111956","https://openalex.org/W4404792748","https://openalex.org/W4409366558"],"related_works":[],"abstract_inverted_index":{"Vision":[0],"and":[1,26,36,48,70,81,90,94,105,126],"Language":[2],"Navigation":[3],"(VLN)":[4],"requires":[5],"an":[6,63],"agent":[7],"to":[8,32,116],"navigate":[9],"through":[10,58,149],"environments":[11],"following":[12],"natural":[13],"language":[14],"instructions.":[15,98,120],"However,":[16],"existing":[17],"methods":[18],"often":[19],"struggle":[20],"with":[21],"effectively":[22],"integrating":[23],"visual":[24,71],"observations":[25],"instruction":[27,107],"details":[28],"during":[29],"navigation,":[30],"leading":[31],"suboptimal":[33],"path":[34],"planning":[35],"limited":[37],"success":[38],"rates.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43],"propose":[44],"OIKG":[45,131],"(Observation-graph":[46],"Interaction":[47],"Key-detail":[49],"Guidance),":[50],"a":[51,83],"novel":[52],"framework":[53],"that":[54,67,87,130],"addresses":[55],"these":[56],"limitations":[57],"two":[59],"key":[60],"components:":[61],"(1)":[62],"observation-graph":[64],"interaction":[65],"module":[66,86],"decouples":[68],"angular":[69],"information":[72,96],"while":[73],"strengthening":[74],"edge":[75],"representations":[76],"in":[77,145],"the":[78,113,124,140],"navigation":[79,119,147],"space,":[80],"(2)":[82],"key-detail":[84],"guidance":[85],"dynamically":[88],"extracts":[89],"utilizes":[91],"fine-grained":[92],"location":[93],"object":[95],"from":[97],"By":[99],"enabling":[100],"more":[101],"precise":[102],"cross-modal":[103],"alignment":[104],"dynamic":[106],"interpretation,":[108],"our":[109,143],"approach":[110],"significantly":[111],"improves":[112],"agent\u2019s":[114],"ability":[115],"follow":[117],"complex":[118],"Extensive":[121],"experiments":[122],"on":[123],"R2R":[125],"RxR":[127],"datasets":[128],"demonstrate":[129],"achieves":[132],"state-of-the-art":[133],"performance":[134],"across":[135],"multiple":[136],"evaluation":[137],"metrics,":[138],"validating":[139],"effectiveness":[141],"of":[142],"method":[144],"enhancing":[146],"precision":[148],"better":[150],"observation-instruction":[151],"alignment.":[152]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-11-28T00:00:00"}