{"id":"https://openalex.org/W4405778661","doi":"https://doi.org/10.1109/iros58592.2024.10802008","title":"VLPG-Nav: Object Navigation Using Visual Language Pose Graph and Object Localization Probability Maps","display_name":"VLPG-Nav: Object Navigation Using Visual Language Pose Graph and Object Localization Probability Maps","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405778661","doi":"https://doi.org/10.1109/iros58592.2024.10802008"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5029729390","display_name":"Senthil Hariharan Arul","orcid":"https://orcid.org/0000-0002-3852-0998"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Senthil Hariharan Arul","raw_affiliation_strings":["Amazon Lab126,Sunnyvale,CA,USA,94098"],"affiliations":[{"raw_affiliation_string":"Amazon Lab126,Sunnyvale,CA,USA,94098","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112942731","display_name":"Dhruva Kumar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dhruva Kumar","raw_affiliation_strings":["Amazon Lab126,Sunnyvale,CA,USA,94098"],"affiliations":[{"raw_affiliation_string":"Amazon Lab126,Sunnyvale,CA,USA,94098","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115645765","display_name":"Vivek Sugirtharaj","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vivek Sugirtharaj","raw_affiliation_strings":["Amazon Lab126,Sunnyvale,CA,USA,94098"],"affiliations":[{"raw_affiliation_string":"Amazon Lab126,Sunnyvale,CA,USA,94098","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104094020","display_name":"Richard Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Richard Kim","raw_affiliation_strings":["Amazon Lab126,Sunnyvale,CA,USA,94098"],"affiliations":[{"raw_affiliation_string":"Amazon Lab126,Sunnyvale,CA,USA,94098","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101906245","display_name":"Xuewei Qi","orcid":"https://orcid.org/0000-0003-3890-135X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuewei Tony Qi","raw_affiliation_strings":["Amazon Lab126,Sunnyvale,CA,USA,94098"],"affiliations":[{"raw_affiliation_string":"Amazon Lab126,Sunnyvale,CA,USA,94098","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056472890","display_name":"Rajasimman Madhivanan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajasimman Madhivanan","raw_affiliation_strings":["Amazon Lab126,Sunnyvale,CA,USA,94098"],"affiliations":[{"raw_affiliation_string":"Amazon Lab126,Sunnyvale,CA,USA,94098","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053890173","display_name":"Arnie Sen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arnie Sen","raw_affiliation_strings":["Amazon Lab126,Sunnyvale,CA,USA,94098"],"affiliations":[{"raw_affiliation_string":"Amazon Lab126,Sunnyvale,CA,USA,94098","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004194238","display_name":"Dinesh Manocha","orcid":"https://orcid.org/0000-0001-7047-9801"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinesh Manocha","raw_affiliation_strings":["University of Maryland,College Park,MD,USA,20740"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,MD,USA,20740","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5029729390"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5263,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68568297,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7625","last_page":"7632"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"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":0.9991999864578247,"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/T12031","display_name":"Speech and dialogue systems","score":0.9843999743461609,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9713000059127808,"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/computer-science","display_name":"Computer science","score":0.7278760671615601},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7189899682998657},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6958951354026794},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6469376087188721},{"id":"https://openalex.org/keywords/deep-sky-object","display_name":"Deep-sky object","score":0.5509966611862183},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5211874842643738},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.13329750299453735},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.057353079319000244}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7278760671615601},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7189899682998657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6958951354026794},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6469376087188721},{"id":"https://openalex.org/C201276399","wikidata":"https://www.wikidata.org/wiki/Q249389","display_name":"Deep-sky object","level":3,"score":0.5509966611862183},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5211874842643738},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.13329750299453735},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.057353079319000244}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10802008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/F4320316514","display_name":"Arm","ror":"https://ror.org/04mmhzs81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W192919555","https://openalex.org/W1539282749","https://openalex.org/W1935926926","https://openalex.org/W2066955564","https://openalex.org/W2107667896","https://openalex.org/W2117211893","https://openalex.org/W2167501464","https://openalex.org/W2962858109","https://openalex.org/W2963545832","https://openalex.org/W2963854535","https://openalex.org/W2964339842","https://openalex.org/W2999746904","https://openalex.org/W3158711590","https://openalex.org/W3201221410","https://openalex.org/W3211462570","https://openalex.org/W4285053689","https://openalex.org/W4312910992","https://openalex.org/W4312956471","https://openalex.org/W4383108296","https://openalex.org/W4383108519","https://openalex.org/W4386071636","https://openalex.org/W6778883912","https://openalex.org/W6790124654","https://openalex.org/W6791353385","https://openalex.org/W6802257716","https://openalex.org/W6811013733","https://openalex.org/W6811433417","https://openalex.org/W6839459284","https://openalex.org/W6846479934","https://openalex.org/W6849177959","https://openalex.org/W6849793301"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"We":[0,96,150],"present":[1],"VLPG-Nav,":[2],"a":[3,46,55,68],"visual":[4,47],"language":[5,48],"navigation":[6,72],"method":[7,44],"for":[8,70],"guiding":[9],"robots":[10],"to":[11,78,142,165],"specified":[12],"objects":[13],"within":[14,38,172,193],"household":[15],"scenes.":[16],"Unlike":[17],"existing":[18],"methods":[19],"primarily":[20],"focused":[21],"on":[22],"navigating":[23,77,186],"the":[24,31,36,39,74,79,89,105,113,118,139,144,147,152,170,173,184,191,194,202],"robot":[25],"toward":[26],"objects,":[27],"our":[28,155],"approach":[29,156],"considers":[30],"additional":[32],"challenge":[33],"of":[34,58,154,176],"centering":[35,190],"object":[37,64,71,85,99,114,145,171,192],"robot\u2019s":[40,90,106,140,195],"camera":[41,148,196],"view.":[42,149,177],"Our":[43],"builds":[45],"pose":[49,141],"graph":[50],"(VLPG)":[51],"that":[52,103,136],"functions":[53],"as":[54,84],"spatial":[56],"map":[57,102,120],"VL":[59],"embeddings.":[60],"Given":[61],"an":[62,98,124,133],"open-vocabulary":[63],"query,":[65],"we":[66,131],"plan":[67],"viewpoint":[69,126],"using":[73],"VLPG.":[75,111],"Despite":[76],"viewpoint,":[80],"real-world":[81,160],"challenges":[82],"such":[83],"occlusion,":[86],"displacement,":[87],"and":[88,109,123,159,168,189],"localization":[91,100],"errors":[92],"can":[93],"prevent":[94],"visibility.":[95],"build":[97],"probability":[101,119],"leverages":[104],"current":[107],"observations":[108],"prior":[110],"When":[112],"is":[115,121,127],"not":[116],"visible,":[117],"updated,":[122],"alternate":[125],"computed.":[128],"In":[129],"addition,":[130],"propose":[132],"object-centering":[134],"formulation":[135],"locally":[137],"adjusts":[138],"center":[143,169],"in":[146,182,201],"evaluate":[151],"effectiveness":[153],"through":[157],"simulations":[158],"experiments,":[161],"evaluating":[162],"its":[163],"ability":[164],"successfully":[166],"view":[167],"camera\u2019s":[174],"field":[175],"VLPG-Nav":[178],"demonstrates":[179],"improved":[180],"performance":[181],"locating":[183],"object,":[185],"around":[187],"occlusions,":[188],"view,":[197],"outperforming":[198],"selected":[199],"baselines":[200],"evaluation":[203],"settings.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
