{"id":"https://openalex.org/W4391695313","doi":"https://doi.org/10.1109/sii58957.2024.10417171","title":"Visual-Language Decision System Through Integration of Foundation Models for Service Robot Navigation","display_name":"Visual-Language Decision System Through Integration of Foundation Models for Service Robot Navigation","publication_year":2024,"publication_date":"2024-01-08","ids":{"openalex":"https://openalex.org/W4391695313","doi":"https://doi.org/10.1109/sii58957.2024.10417171"},"language":"en","primary_location":{"id":"doi:10.1109/sii58957.2024.10417171","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii58957.2024.10417171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/SICE International Symposium on System Integration (SII)","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/A5039331441","display_name":"Peiyuan Zhu","orcid":"https://orcid.org/0009-0004-4849-5425"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Peiyuan Zhu","raw_affiliation_strings":["Ritsumeikan University,Kusatsu, Shiga,Japan,525-8577"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ritsumeikan University,Kusatsu, Shiga,Japan,525-8577","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017527511","display_name":"Lotfi El Hafi","orcid":"https://orcid.org/0000-0001-9795-6153"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Lotfi El Hafi","raw_affiliation_strings":["Ritsumeikan University,Kusatsu, Shiga,Japan,525-8577"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ritsumeikan University,Kusatsu, Shiga,Japan,525-8577","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023160093","display_name":"Tadahiro Taniguchi","orcid":"https://orcid.org/0000-0002-5682-2076"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tadahiro Taniguchi","raw_affiliation_strings":["Ritsumeikan University,Kusatsu, Shiga,Japan,525-8577"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ritsumeikan University,Kusatsu, Shiga,Japan,525-8577","institution_ids":["https://openalex.org/I135768898"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0936,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.76806246,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1288","last_page":"1295"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9884999990463257,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9854999780654907,"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/computer-science","display_name":"Computer science","score":0.7255352735519409},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6792271137237549},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5940502285957336},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5350647568702698},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4878537654876709},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.4865342676639557},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3911159038543701}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7255352735519409},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6792271137237549},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5940502285957336},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5350647568702698},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4878537654876709},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.4865342676639557},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3911159038543701},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sii58957.2024.10417171","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii58957.2024.10417171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3302257970","display_name":"\u8ab0\u3082\u304c\u81ea\u5728\u306b\u6d3b\u8e8d\u3067\u304d\u308b\u30a2\u30d0\u30bf\u30fc\u5171\u751f\u793e\u4f1a\u306e\u5b9f\u73fe","funder_award_id":"JPMJMS2011","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"}],"funders":[{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2560674852","https://openalex.org/W2963037989","https://openalex.org/W2963800628","https://openalex.org/W3087858202","https://openalex.org/W3164243458","https://openalex.org/W3165881704","https://openalex.org/W4383108296","https://openalex.org/W4385571625","https://openalex.org/W4394828156","https://openalex.org/W6778883912","https://openalex.org/W6791353385","https://openalex.org/W6811433417","https://openalex.org/W6839015040"],"related_works":["https://openalex.org/W1508899372","https://openalex.org/W2012658348","https://openalex.org/W2039460805","https://openalex.org/W4250956039","https://openalex.org/W4240485100","https://openalex.org/W4254970379","https://openalex.org/W2056130799","https://openalex.org/W2045758229","https://openalex.org/W405964254","https://openalex.org/W2297646692"],"abstract_inverted_index":{"This":[0,78],"study":[1],"aims":[2],"to":[3,62,74,91,125,129,155],"build":[4],"a":[5,53,60,111,148,176,181],"system":[6,57,113,162],"that":[7,58,104],"bridges":[8],"the":[9,84,89,131,159],"gap":[10],"between":[11],"robotics":[12],"and":[13,26,38,72,108,137,157,183],"environmental":[14,143],"understanding":[15],"by":[16,134],"integrating":[17,44,105],"various":[18],"foundation":[19],"models.":[20],"While":[21],"current":[22],"visual-language":[23,54],"models":[24,29],"(VLMs)":[25],"large":[27],"language":[28,39],"(LLMs)":[30],"have":[31],"demonstrated":[32],"robust":[33],"capabilities":[34],"in":[35,43,118,163,171],"image":[36],"recognition":[37],"comprehension,":[40],"challenges":[41],"remain":[42],"them":[45],"into":[46,110],"practical":[47],"robotic":[48,112],"applications.":[49],"Therefore,":[50],"we":[51,166],"propose":[52],"decision":[55],"(VLD)":[56],"allows":[59,88],"robot":[61,90,178],"autonomously":[63],"analyze":[64],"its":[65],"surroundings":[66],"using":[67,83,152,175],"three":[68],"VLMs":[69,136],"(CLIP,":[70],"OFA,":[71,107],"PaddleOCR)":[73],"generate":[75,115],"semantic":[76],"information.":[77,144],"information":[79,117],"is":[80,99],"further":[81],"processed":[82],"GPT-3":[85,128],"LLM,":[86],"which":[87],"make":[92,138],"judgments":[93],"during":[94],"autonomous":[95],"navigation.":[96],"The":[97],"contribution":[98],"twofold:":[100],"1)":[101],"We":[102,122,145],"show":[103],"CLIP,":[106],"PaddleOCR":[109],"can":[114],"task-critical":[116],"unexplored":[119,173],"environments;":[120],"2)":[121],"explore":[123],"how":[124],"effectively":[126],"use":[127],"match":[130],"results":[132],"generated":[133],"specific":[135],"navigation":[139,170],"decisions":[140],"based":[141],"on":[142],"also":[146],"implement":[147],"photorealistic":[149],"training":[150],"environment":[151,174],"Isaac":[153],"Sim":[154],"test":[156],"validate":[158],"proposed":[160],"VLD":[161],"simulation.":[164],"Finally,":[165],"demonstrate":[167],"VLD-based":[168],"real-world":[169],"an":[172,184],"TurtleBot3":[177],"equipped":[179],"with":[180],"lidar":[182],"RGB":[185],"camera.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
