{"id":"https://openalex.org/W4407403389","doi":"https://doi.org/10.1109/sii59315.2025.10871009","title":"A VLM-Drone System for Indoor Navigation Assistance with Semantic Reasoning for the Visually Impaired","display_name":"A VLM-Drone System for Indoor Navigation Assistance with Semantic Reasoning for the Visually Impaired","publication_year":2025,"publication_date":"2025-01-21","ids":{"openalex":"https://openalex.org/W4407403389","doi":"https://doi.org/10.1109/sii59315.2025.10871009"},"language":"en","primary_location":{"id":"doi:10.1109/sii59315.2025.10871009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii59315.2025.10871009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5070315330","display_name":"Zezhong Zhang","orcid":"https://orcid.org/0000-0002-8060-5784"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Zezhong Zhang","raw_affiliation_strings":["Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore,639798"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore,639798","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038650064","display_name":"Chenyu Hu","orcid":"https://orcid.org/0000-0001-7084-3343"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chenyu Hu","raw_affiliation_strings":["Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore,639798"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore,639798","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110261606","display_name":"Sun\u2010Woh Lye","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Sunwoh Lye","raw_affiliation_strings":["Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore,639798"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore,639798","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072073374","display_name":"Chen Lv","orcid":"https://orcid.org/0000-0001-6897-4512"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chen Lv","raw_affiliation_strings":["Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore,639798"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore,639798","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5070315330"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02789285,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1260","last_page":"1265"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.9764999747276306,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.9764999747276306,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9490000009536743,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.90420001745224,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.7995407581329346},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7060932517051697},{"id":"https://openalex.org/keywords/visually-impaired","display_name":"Visually impaired","score":0.5716112852096558},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4920918345451355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4920470416545868},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4245002865791321}],"concepts":[{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.7995407581329346},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7060932517051697},{"id":"https://openalex.org/C3020106864","wikidata":"https://www.wikidata.org/wiki/Q737460","display_name":"Visually impaired","level":2,"score":0.5716112852096558},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4920918345451355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4920470416545868},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4245002865791321},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sii59315.2025.10871009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii59315.2025.10871009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311687","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2044146786","https://openalex.org/W2534652725","https://openalex.org/W2568039188","https://openalex.org/W2594255081","https://openalex.org/W2749554940","https://openalex.org/W2765252989","https://openalex.org/W2940779895","https://openalex.org/W2981380018","https://openalex.org/W3011451419","https://openalex.org/W3157852503","https://openalex.org/W3206532678","https://openalex.org/W3207432148","https://openalex.org/W4321428710","https://openalex.org/W4366605974","https://openalex.org/W4383108997","https://openalex.org/W4390023570","https://openalex.org/W4390582457","https://openalex.org/W4399300452","https://openalex.org/W6764045775","https://openalex.org/W6811013733","https://openalex.org/W6849177959"],"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":{"Reduced":[0],"vision":[1],"significantly":[2],"impacts":[3],"the":[4,23,60,86,96,116,119,134,183,192],"daily":[5],"lives":[6],"of":[7,27,89,99,126,173],"people":[8],"with":[9,42,167,180],"visual":[10],"impairments":[11],"(PVI),":[12],"often":[13],"posing":[14],"challenges":[15],"in":[16,51,163,206],"navigation":[17],"and":[18,77,102,114,141,153,194],"spatial":[19],"awareness.":[20],"To":[21,185],"enhance":[22],"semantic":[24,56,90],"reasoning":[25,87],"capabilities":[26],"assistive":[28,208],"technologies,":[29],"we":[30,63,189],"have":[31,190],"developed":[32,111],"a":[33,43,65,145],"guidance":[34],"system":[35,47],"that":[36,71],"integrates":[37],"large":[38],"vision-language":[39],"models":[40],"(VLMs)":[41],"collision-avoidance":[44],"drone.":[45],"This":[46,83],"provides":[48],"navigational":[49],"assistance":[50,181],"indoor":[52],"environments":[53],"by":[54],"interpreting":[55],"wayfinding":[57,91,107],"signs.":[58,143],"At":[59,118],"software":[61],"level,":[62,121],"propose":[64],"hierarchical":[66],"cross-prompt":[67],"VLM":[68],"(HCP-VLM)":[69],"structure":[70,84],"leverages":[72],"both":[73,172],"Claude":[74,100],"3.5":[75],"Sonnet":[76],"ChatGPT":[78,103],"4o":[79],"<sup":[80,199],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[81,200],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[82],"improves":[85],"accuracy":[88],"signs":[92],"to":[93,112,136,150,156,203],"76.73%,":[94],"outperforming":[95],"standalone":[97],"accuracies":[98],"(74.73%)":[101],"(66.35%).":[104],"A":[105],"specialized":[106],"sign":[108],"dataset":[109,193],"was":[110,131,148,161],"fine-tune":[113],"evaluate":[115],"VLM.":[117],"hardware":[120],"an":[122],"ultralight":[123],"dual-modal":[124],"Time":[125],"Flight":[127],"(TOF)":[128],"Laser-Camera":[129],"module":[130,147],"integrated":[132],"into":[133],"drone":[135],"detect":[137],"obstacles,":[138],"track":[139],"users,":[140],"identify":[142],"Additionally,":[144],"vibration":[146],"designed":[149],"communicate":[151],"orientation":[152],"mobility":[154],"information":[155],"users.":[157],"The":[158],"system\u2019s":[159],"performance":[160],"evaluated":[162],"unfamiliar":[164],"office":[165],"buildings":[166],"two":[168],"blindfolded":[169],"sighted":[170],"subjects,":[171],"whom":[174],"successfully":[175],"located":[176],"their":[177],"target":[178],"rooms":[179],"from":[182],"system.":[184],"further":[186],"drive":[187],"innovation,":[188],"released":[191],"code":[195],"for":[196],"public":[197],"access":[198],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>,":[201],"aiming":[202],"inspire":[204],"advancements":[205],"intelligent":[207],"technologies.":[209]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}
