{"id":"https://openalex.org/W4415387995","doi":"https://doi.org/10.3389/frobt.2025.1693988","title":"Real-time open-vocabulary perception for mobile robots on edge devices: a systematic analysis of the accuracy-latency trade-off","display_name":"Real-time open-vocabulary perception for mobile robots on edge devices: a systematic analysis of the accuracy-latency trade-off","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415387995","doi":"https://doi.org/10.3389/frobt.2025.1693988","pmid":"https://pubmed.ncbi.nlm.nih.gov/41194942"},"language":"en","primary_location":{"id":"doi:10.3389/frobt.2025.1693988","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frobt.2025.1693988","pdf_url":"https://www.frontiersin.org/journals/robotics-and-ai/articles/10.3389/frobt.2025.1693988/pdf","source":{"id":"https://openalex.org/S2595095599","display_name":"Frontiers in Robotics and AI","issn_l":"2296-9144","issn":["2296-9144"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Robotics and AI","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/journals/robotics-and-ai/articles/10.3389/frobt.2025.1693988/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101056812","display_name":"Jongyoon Park","orcid":null},"institutions":[{"id":"https://openalex.org/I24456540","display_name":"Korea Aerospace University","ror":"https://ror.org/05jmm0651","country_code":"KR","type":"education","lineage":["https://openalex.org/I24456540"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jongyoon Park","raw_affiliation_strings":["Intelligence Robotics and Autonomous Mobility, Department of Artificial Intelligent, Korea Aerospace University, Goyang-si, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligence Robotics and Autonomous Mobility, Department of Artificial Intelligent, Korea Aerospace University, Goyang-si, Republic of Korea","institution_ids":["https://openalex.org/I24456540"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068419623","display_name":"Pileun Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I24456540","display_name":"Korea Aerospace University","ror":"https://ror.org/05jmm0651","country_code":"KR","type":"education","lineage":["https://openalex.org/I24456540"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Pileun Kim","raw_affiliation_strings":["Intelligence Robotics and Autonomous Mobility, Department of Autonomous Vehicle Engineering, Korea Aerospace University, Goyang-si, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligence Robotics and Autonomous Mobility, Department of Autonomous Vehicle Engineering, Korea Aerospace University, Goyang-si, Republic of Korea","institution_ids":["https://openalex.org/I24456540"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084930054","display_name":"Daijin Ko","orcid":"https://orcid.org/0000-0002-1281-1076"},"institutions":[{"id":"https://openalex.org/I24456540","display_name":"Korea Aerospace University","ror":"https://ror.org/05jmm0651","country_code":"KR","type":"education","lineage":["https://openalex.org/I24456540"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Daeil Ko","raw_affiliation_strings":["Intelligence Robotics and Autonomous Mobility, Department of Artificial Intelligent, Korea Aerospace University, Goyang-si, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligence Robotics and Autonomous Mobility, Department of Artificial Intelligent, Korea Aerospace University, Goyang-si, Republic of Korea","institution_ids":["https://openalex.org/I24456540"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5068419623"],"corresponding_institution_ids":["https://openalex.org/I24456540"],"apc_list":{"value":1900,"currency":"USD","value_usd":1900},"apc_paid":{"value":1900,"currency":"USD","value_usd":1900},"fwci":2.2966,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.89845988,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"12","issue":null,"first_page":"1693988","last_page":"1693988"},"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":0.9976999759674072,"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/T13382","display_name":"Robotics and Automated Systems","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/pipeline","display_name":"Pipeline (software)","score":0.6640999913215637},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.5666000247001648},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5638999938964844},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.5275999903678894},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5199000239372253},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5170000195503235},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5023999810218811},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4796999990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8622000217437744},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6640999913215637},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.5666000247001648},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5638999938964844},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.5275999903678894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5227000117301941},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5199000239372253},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5170000195503235},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5023999810218811},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4796999990940094},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.475600004196167},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.44359999895095825},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.40959998965263367},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.37450000643730164},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.3463999927043915},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.34290000796318054},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3125999867916107},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2793999910354614},{"id":"https://openalex.org/C2776061582","wikidata":"https://www.wikidata.org/wiki/Q25325231","display_name":"Mobile edge computing","level":3,"score":0.2750999927520752},{"id":"https://openalex.org/C144543869","wikidata":"https://www.wikidata.org/wiki/Q2738570","display_name":"Mobile computing","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2680000066757202},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26589998602867126},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2549000084400177}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/frobt.2025.1693988","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frobt.2025.1693988","pdf_url":"https://www.frontiersin.org/journals/robotics-and-ai/articles/10.3389/frobt.2025.1693988/pdf","source":{"id":"https://openalex.org/S2595095599","display_name":"Frontiers in Robotics and AI","issn_l":"2296-9144","issn":["2296-9144"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Robotics and AI","raw_type":"journal-article"},{"id":"pmid:41194942","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41194942","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in robotics and AI","raw_type":null},{"id":"pmh:oai:doaj.org/article:ba4feb244c254ceca11620531d83d068","is_oa":true,"landing_page_url":"https://doaj.org/article/ba4feb244c254ceca11620531d83d068","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Robotics and AI, Vol 12 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11392231","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12583037","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3389/frobt.2025.1693988","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frobt.2025.1693988","pdf_url":"https://www.frontiersin.org/journals/robotics-and-ai/articles/10.3389/frobt.2025.1693988/pdf","source":{"id":"https://openalex.org/S2595095599","display_name":"Frontiers in Robotics and AI","issn_l":"2296-9144","issn":["2296-9144"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Robotics and AI","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415387995.pdf","grobid_xml":"https://content.openalex.org/works/W4415387995.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2489434015","https://openalex.org/W2560674852","https://openalex.org/W3023742835","https://openalex.org/W4313026212","https://openalex.org/W4382322597","https://openalex.org/W4390874575","https://openalex.org/W4399695552","https://openalex.org/W4402706078","https://openalex.org/W4402716047"],"related_works":[],"abstract_inverted_index":{"The":[0],"integration":[1],"of":[2,10,89,119,149],"Vision-Language":[3],"Models":[4],"(VLMs)":[5],"into":[6],"autonomous":[7],"systems":[8],"is":[9,57,131],"growing":[11],"importance":[12],"for":[13,76,158,166],"improving":[14],"Human-Robot":[15],"Interaction":[16],"(HRI),":[17],"enabling":[18],"robots":[19,34],"to":[20,35,50],"operate":[21],"within":[22],"complex":[23],"and":[24,27,52,114,124,139,156,164,168],"unstructured":[25],"environments":[26],"collaborate":[28],"with":[29],"non-expert":[30],"users.":[31],"For":[32],"mobile":[33],"be":[36],"effectively":[37],"deployed":[38],"in":[39,93],"dynamic":[40],"settings":[41],"such":[42],"as":[43],"domestic":[44],"or":[45],"industrial":[46],"areas,":[47],"the":[48,90,101,110,150],"ability":[49],"interpret":[51],"execute":[53],"natural":[54],"language":[55],"commands":[56],"crucial.":[58],"However,":[59],"while":[60],"VLMs":[61],"offer":[62],"powerful":[63],"zero-shot,":[64],"open-vocabulary":[65,121],"recognition":[66],"capabilities,":[67],"their":[68],"high":[69],"computational":[70],"cost":[71],"presents":[72],"a":[73,86,95,146],"significant":[74],"challenge":[75],"real-time":[77,96],"performance":[78],"on":[79,100,174],"resource-constrained":[80],"edge":[81],"devices.":[82],"This":[83],"study":[84],"provides":[85],"systematic":[87],"analysis":[88],"trade-offs":[91],"involved":[92],"optimizing":[94],"robotic":[97],"perception":[98],"pipeline":[99,130],"NVIDIA":[102,142],"Jetson":[103],"AGX":[104],"Orin":[105],"64GB":[106],"platform.":[107],"We":[108,144],"investigate":[109],"relationship":[111],"between":[112],"accuracy":[113],"latency":[115,157],"by":[116],"evaluating":[117],"combinations":[118],"two":[120,125],"detection":[122],"models":[123,173],"prompt-based":[126],"segmentation":[127],"models.":[128],"Each":[129],"optimized":[132],"using":[133],"various":[134],"precision":[135],"levels":[136],"(FP32,":[137],"FP16,":[138],"Best)":[140],"via":[141],"TensorRT.":[143],"present":[145],"quantitative":[147],"comparison":[148],"mean":[151],"Intersection":[152],"over":[153],"Union":[154],"(mIoU)":[155],"each":[159],"configuration,":[160],"offering":[161],"practical":[162],"insights":[163],"benchmarks":[165],"researchers":[167],"developers":[169],"deploying":[170],"these":[171],"advanced":[172],"embedded":[175],"systems.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-22T00:00:00"}