{"id":"https://openalex.org/W4405786269","doi":"https://doi.org/10.1109/iros58592.2024.10802716","title":"CoNVOI: Context-aware Navigation using Vision Language Models in Outdoor and Indoor Environments","display_name":"CoNVOI: Context-aware Navigation using Vision Language Models in Outdoor and Indoor Environments","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405786269","doi":"https://doi.org/10.1109/iros58592.2024.10802716"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802716","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/A5013408106","display_name":"Adarsh Jagan Sathyamoorthy","orcid":"https://orcid.org/0000-0002-9678-4748"},"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":true,"raw_author_name":"Adarsh Jagan Sathyamoorthy","raw_affiliation_strings":["University of Maryland,College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080472165","display_name":"Kasun Weerakoon","orcid":null},"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":"Kasun Weerakoon","raw_affiliation_strings":["University of Maryland,College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092506235","display_name":"Mohamed Elnoor","orcid":"https://orcid.org/0009-0000-2326-6184"},"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":"Mohamed Elnoor","raw_affiliation_strings":["University of Maryland,College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078906241","display_name":"Anuj Zore","orcid":null},"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":"Anuj Zore","raw_affiliation_strings":["University of Maryland,College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018507768","display_name":"Brian Ichter","orcid":"https://orcid.org/0000-0002-6955-6432"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Brian Ichter","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676786","display_name":"Fei Xia","orcid":"https://orcid.org/0009-0002-4609-9950"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Fei Xia","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103241086","display_name":"Jie Tan","orcid":"https://orcid.org/0000-0002-7947-0333"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Jie Tan","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114860703","display_name":"Wenhao Yu","orcid":"https://orcid.org/0000-0002-9671-8652"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Wenhao Yu","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5013408106"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":2.7912,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.92072621,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"13837","last_page":"13844"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9822999835014343,"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":0.9822999835014343,"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/T10757","display_name":"Geographic Information Systems Studies","score":0.9610000252723694,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9287999868392944,"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":0.7648254036903381},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.622093677520752},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4122558534145355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36486175656318665},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3455325961112976},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3371971547603607},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.11101463437080383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7648254036903381},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.622093677520752},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4122558534145355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36486175656318665},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3455325961112976},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3371971547603607},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.11101463437080383},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10802716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802716","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/F4320332447","display_name":"U.S. Army","ror":"https://ror.org/00afsp483"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2040121219","https://openalex.org/W2059993653","https://openalex.org/W2065943880","https://openalex.org/W2117211893","https://openalex.org/W2124299914","https://openalex.org/W2133552987","https://openalex.org/W2167052694","https://openalex.org/W2560023338","https://openalex.org/W2565402511","https://openalex.org/W2604216058","https://openalex.org/W2750929583","https://openalex.org/W2772638427","https://openalex.org/W2913921102","https://openalex.org/W2962954724","https://openalex.org/W3026389972","https://openalex.org/W3196185526","https://openalex.org/W3199502123","https://openalex.org/W3214557258","https://openalex.org/W4232280717","https://openalex.org/W4250315003","https://openalex.org/W4250696540","https://openalex.org/W4285304415","https://openalex.org/W4312726754","https://openalex.org/W4381802186","https://openalex.org/W4383066545","https://openalex.org/W4383097638","https://openalex.org/W4383108296","https://openalex.org/W4384918448","https://openalex.org/W4385430678","https://openalex.org/W4389667035","https://openalex.org/W4390041933","https://openalex.org/W4391695313","https://openalex.org/W4402727764","https://openalex.org/W4402890475","https://openalex.org/W6744156861","https://openalex.org/W6778883912","https://openalex.org/W6791353385","https://openalex.org/W6839459284","https://openalex.org/W6841082114","https://openalex.org/W6846479934","https://openalex.org/W6851592950","https://openalex.org/W6854692045","https://openalex.org/W6858299849","https://openalex.org/W6860803839","https://openalex.org/W6861319346"],"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":[0,21,209,245],"present":[1],"CoNVOI,":[2],"a":[3,79,91,118,179,189,216,231],"novel":[4,92],"method":[5,190],"for":[6],"autonomous":[7],"robot":[8],"navigation":[9,55,250],"in":[10,24,102,131,152,238,265],"real-world":[11,240],"indoor":[12,42,241],"and":[13,52,73,142,149,177,219,242,249,252,279],"outdoor":[14,44,243],"environments":[15],"using":[16,182,235],"Vision":[17],"Language":[18],"Models":[19],"(VLMs).":[20],"employ":[22],"VLMs":[23],"two":[25],"ways:":[26],"first,":[27],"we":[28,67,89,159,187],"leverage":[29],"their":[30,69],"zero-shot":[31],"image":[32,105,129,154,169],"classification":[33],"capability":[34],"to":[35,77,97,109,139,155,163,191,204,214,224,260,276,281],"identify":[36],"the":[37,49,64,83,99,103,110,123,132,135,144,153,156,161,167,172,183,193,197,211],"context":[38,200],"or":[39],"scenario":[40],"(e.g.,":[41],"corridor,":[43],"terrain,":[45],"crosswalk,":[46],"etc)":[47],"of":[48,122,233,267,285],"robot\u2019s":[50,198],"surroundings,":[51],"formulate":[53],"context-based":[54,173],"behaviors":[56,226],"as":[57,107],"simple":[58],"text":[59,175],"prompts":[60],"(e.g.":[61,227],"\"stay":[62],"on":[63,166],"pavement\").":[65],"Second,":[66],"utilize":[68],"state-of-the-art":[70],"semantic":[71],"understanding":[72],"logical":[74],"reasoning":[75],"capabilities":[76],"compute":[78],"suitable":[80],"trajectory":[81,195,213],"given":[82],"identified":[84],"context.":[85],"To":[86],"this":[87],"end,":[88],"propose":[90,188],"multi-modal":[93],"visual":[94],"marking":[95],"approach":[96],"annotate":[98],"obstacle-free":[100],"regions":[101],"RGB":[104],"used":[106],"input":[108],"VLM":[111,162,207],"with":[112,117],"numbers,":[113],"by":[114],"correlating":[115],"it":[116,222],"local":[119],"occupancy":[120],"map":[121],"environment.":[124],"The":[125],"marked":[126,168],"numbers":[127,165],"ground":[128,263],"locations":[130],"real-world,":[133],"direct":[134],"VLM\u2019s":[136],"attention":[137],"solely":[138],"navigable":[140],"locations,":[141],"elucidate":[143],"spatial":[145],"relationships":[146],"between":[147],"them":[148],"terrains":[150],"depicted":[151],"VLM.":[157],"Next,":[158],"query":[160],"select":[164],"that":[170,221,254],"satisfy":[171],"behavior":[174],"prompt,":[176],"construct":[178],"reference":[180,194,212],"path":[181,273],"selected":[184],"numbers.":[185],"Finally,":[186],"extrapolate":[192],"when":[196],"environmental":[199],"has":[201],"not":[202,228],"changed":[203],"prevent":[205],"unnecessary":[206],"queries.":[208],"use":[210],"guide":[215],"motion":[217],"planner,":[218],"demonstrate":[220,253],"leads":[223],"human-like":[225],"cutting":[229],"through":[230],"group":[232],"people,":[234],"crosswalks,":[236],"etc.)":[237],"various":[239],"scenarios.":[244],"perform":[246],"several":[247],"ablations":[248],"comparisons":[251],"CoNVOI\u2019s":[255],"trajectories":[256],"are":[257],"most":[258],"similar":[259],"human":[261],"teleoperated":[262],"truth":[264],"terms":[266],"Fr\u00e9chet":[268],"distance":[269],"(9.7-58.2%":[270],"closer),":[271],"lowest":[272],"errors":[274],"(up":[275],"88.13%":[277],"lower),":[278],"up":[280],"86.09%":[282],"lower":[283],"%":[284],"unacceptable":[286],"paths.":[287]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}