{"id":"https://openalex.org/W4401414621","doi":"https://doi.org/10.1109/icra57147.2024.10610751","title":"Interactive Navigation in Environments with Traversable Obstacles Using Large Language and Vision-Language Models","display_name":"Interactive Navigation in Environments with Traversable Obstacles Using Large Language and Vision-Language Models","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401414621","doi":"https://doi.org/10.1109/icra57147.2024.10610751"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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/A5115595967","display_name":"Zhen Zhang","orcid":"https://orcid.org/0000-0002-0647-4253"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhen Zhang","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035407538","display_name":"Anran Lin","orcid":"https://orcid.org/0009-0006-2550-598X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anran Lin","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Computer Science and Engineering"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101903605","display_name":"Chun Wai Wong","orcid":"https://orcid.org/0000-0001-8732-1891"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Wai Wong","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054031435","display_name":"Xiangyu Chu","orcid":"https://orcid.org/0000-0002-7677-2600"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Chu","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090516040","display_name":"Qi Dou","orcid":"https://orcid.org/0000-0002-3416-9950"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Dou","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Computer Science and Engineering"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038766171","display_name":"Kwok Wai Samuel Au","orcid":"https://orcid.org/0000-0002-0114-7499"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"K. W. Samuel Au","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5115595967"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":3.4211,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.93765726,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7867","last_page":"7873"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9851999878883362,"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":0.9819999933242798,"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":0.7112879753112793},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.46012139320373535},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45350930094718933},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37882035970687866}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7112879753112793},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.46012139320373535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45350930094718933},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37882035970687866}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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":42,"referenced_works":["https://openalex.org/W1507667015","https://openalex.org/W1969483458","https://openalex.org/W2018369130","https://openalex.org/W2021096542","https://openalex.org/W2028047862","https://openalex.org/W2033819227","https://openalex.org/W2034801091","https://openalex.org/W2045134164","https://openalex.org/W2145313322","https://openalex.org/W2167340365","https://openalex.org/W2411093439","https://openalex.org/W2555443888","https://openalex.org/W2924641327","https://openalex.org/W2963800628","https://openalex.org/W2964287316","https://openalex.org/W2966611292","https://openalex.org/W3000916453","https://openalex.org/W3103759224","https://openalex.org/W3186132599","https://openalex.org/W3199245537","https://openalex.org/W4221143046","https://openalex.org/W4225591000","https://openalex.org/W4285304415","https://openalex.org/W4287888303","https://openalex.org/W4292779060","https://openalex.org/W4312747482","https://openalex.org/W4312956471","https://openalex.org/W4315488806","https://openalex.org/W4320005767","https://openalex.org/W4382334278","https://openalex.org/W4383108296","https://openalex.org/W4387123376","https://openalex.org/W4390874575","https://openalex.org/W4404612908","https://openalex.org/W6778883912","https://openalex.org/W6801512601","https://openalex.org/W6809646742","https://openalex.org/W6810220367","https://openalex.org/W6839459284","https://openalex.org/W6849941170","https://openalex.org/W6850787431","https://openalex.org/W6853468020"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","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":{"This":[0],"paper":[1],"proposes":[2],"an":[3,39,56,100],"interactive":[4,132],"navigation":[5,133],"framework":[6],"by":[7,149],"using":[8],"large":[9,26,51,112],"language":[10,27],"and":[11,30,95,98,118,145,173],"vision-language":[12],"models,":[13,52],"allowing":[14,127],"robots":[15],"to":[16,37,42,69,72,74,86,137,153,175],"navigate":[17],"in":[18,130,159],"environments":[19],"with":[20,79],"traversable":[21,94,140],"obstacles.":[22],"We":[23,135],"utilize":[24],"the":[25,31,50,67,131,151,169],"model":[28],"(GPT-3.5)":[29],"open-set":[32],"Vision-language":[33],"Model":[34],"(Grounding":[35],"DINO)":[36],"create":[38],"action-aware":[40,80,101],"costmap":[41,102],"perform":[43],"effective":[44],"path":[45],"planning":[46],"without":[47],"fine-tuning.":[48],"With":[49],"we":[53],"can":[54,83],"achieve":[55],"end-to-end":[57],"system":[58],"from":[59],"textual":[60],"instructions":[61],"like":[62],"\"Can":[63],"you":[64],"pass":[65],"through":[66],"curtains":[68,144,158],"deliver":[70],"medicines":[71],"me?\",":[73],"bounding":[75],"boxes":[76],"(e.g.,":[77],"curtains)":[78],"attributes.":[81],"They":[82],"be":[84],"used":[85],"segment":[87],"LiDAR":[88],"point":[89],"clouds":[90],"into":[91],"two":[92],"parts:":[93],"untraversable":[96],"parts,":[97],"then":[99],"is":[103],"constructed":[104],"for":[105,125,147],"generating":[106],"a":[107,160],"feasible":[108],"path.":[109],"The":[110],"pre-trained":[111],"models":[113],"have":[114],"great":[115],"generalization":[116],"ability":[117],"do":[119],"not":[120],"require":[121],"additional":[122],"annotated":[123],"data":[124],"training,":[126],"fast":[128],"deployment":[129],"tasks.":[134],"choose":[136],"use":[138],"multiple":[139],"objects":[141],"such":[142],"as":[143],"grasses":[146],"verification":[148],"instructing":[150],"robot":[152],"traverse":[154],"them.":[155],"Besides,":[156],"traversing":[157],"medical":[161],"scenario":[162],"was":[163],"tested.":[164],"All":[165],"experimental":[166],"results":[167],"demonstrated":[168],"proposed":[170],"framework\u2019s":[171],"effectiveness":[172],"adaptability":[174],"diverse":[176],"environments.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}