{"id":"https://openalex.org/W4416342072","doi":"https://doi.org/10.3389/frai.2025.1681277","title":"Resource-efficient fine-tuning of large vision-language models for multimodal perception in autonomous excavators","display_name":"Resource-efficient fine-tuning of large vision-language models for multimodal perception in autonomous excavators","publication_year":2025,"publication_date":"2025-11-18","ids":{"openalex":"https://openalex.org/W4416342072","doi":"https://doi.org/10.3389/frai.2025.1681277","pmid":"https://pubmed.ncbi.nlm.nih.gov/41341806"},"language":"en","primary_location":{"id":"doi:10.3389/frai.2025.1681277","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2025.1681277","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1681277/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"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 Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://public-pages-files-2025.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1681277/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084971994","display_name":"Hung Viet Nguyen","orcid":"https://orcid.org/0000-0002-6981-0891"},"institutions":[{"id":"https://openalex.org/I104338594","display_name":"Inje University","ror":"https://ror.org/04xqwq985","country_code":"KR","type":"education","lineage":["https://openalex.org/I104338594"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hung Viet Nguyen","raw_affiliation_strings":["Department of Digital Anti-aging Healthcare, INJE University, Kimhae, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Digital Anti-aging Healthcare, INJE University, Kimhae, Republic of Korea","institution_ids":["https://openalex.org/I104338594"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020627604","display_name":"H. Park","orcid":"https://orcid.org/0000-0001-5021-4240"},"institutions":[{"id":"https://openalex.org/I71007489","display_name":"Kyungnam University","ror":"https://ror.org/037pkxm09","country_code":"KR","type":"education","lineage":["https://openalex.org/I71007489"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyojin Park","raw_affiliation_strings":["Gyeongnam Intelligence Innovation Center (GIIC), Kyungnam University, Changwon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gyeongnam Intelligence Innovation Center (GIIC), Kyungnam University, Changwon, Republic of Korea","institution_ids":["https://openalex.org/I71007489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016249429","display_name":"Nam\u2010Hyun Yoo","orcid":"https://orcid.org/0000-0003-2161-9251"},"institutions":[{"id":"https://openalex.org/I71007489","display_name":"Kyungnam University","ror":"https://ror.org/037pkxm09","country_code":"KR","type":"education","lineage":["https://openalex.org/I71007489"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Namhyun Yoo","raw_affiliation_strings":["Department of Computer Engineering, Kyungnam University, Changwon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Kyungnam University, Changwon, Republic of Korea","institution_ids":["https://openalex.org/I71007489"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114860745","display_name":"Jinhong Yang","orcid":"https://orcid.org/0000-0002-7756-0263"},"institutions":[{"id":"https://openalex.org/I104338594","display_name":"Inje University","ror":"https://ror.org/04xqwq985","country_code":"KR","type":"education","lineage":["https://openalex.org/I104338594"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jinhong Yang","raw_affiliation_strings":["Department of Digital Anti-aging Healthcare, INJE University, Kimhae, Republic of Korea","Department of Medical IT, INJE University, Kimhae, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Digital Anti-aging Healthcare, INJE University, Kimhae, Republic of Korea","institution_ids":["https://openalex.org/I104338594"]},{"raw_affiliation_string":"Department of Medical IT, INJE University, Kimhae, Republic of Korea","institution_ids":["https://openalex.org/I104338594"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5114860745"],"corresponding_institution_ids":["https://openalex.org/I104338594"],"apc_list":{"value":1150,"currency":"USD","value_usd":1150},"apc_paid":{"value":1150,"currency":"USD","value_usd":1150},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33135736,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":null,"first_page":"1681277","last_page":"1681277"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.46970000863075256,"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":0.46970000863075256,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.1574999988079071,"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/T11606","display_name":"Infrastructure Maintenance and Monitoring","score":0.0625,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural 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/excavator","display_name":"Excavator","score":0.6173999905586243},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5325000286102295},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.43389999866485596},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4300999939441681},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4090999960899353},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4007999897003174},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3716000020503998},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.3652999997138977},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3598000109195709},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.34150001406669617}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.666700005531311},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6662999987602234},{"id":"https://openalex.org/C141392084","wikidata":"https://www.wikidata.org/wiki/Q182661","display_name":"Excavator","level":2,"score":0.6173999905586243},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5325000286102295},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4404999911785126},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.43389999866485596},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4300999939441681},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4090999960899353},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4007999897003174},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34150001406669617},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3368000090122223},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3100999891757965},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.29760000109672546},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28139999508857727},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2750999927520752},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.262800008058548},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2574000060558319},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C87833898","wikidata":"https://www.wikidata.org/wiki/Q1060280","display_name":"Advanced driver assistance systems","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3389/frai.2025.1681277","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2025.1681277","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1681277/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"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 Artificial Intelligence","raw_type":"journal-article"},{"id":"pmid:41341806","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41341806","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 artificial intelligence","raw_type":null},{"id":"pmh:oai:doaj.org/article:9a45ea7e160f4703b769e2629c631c27","is_oa":true,"landing_page_url":"https://doaj.org/article/9a45ea7e160f4703b769e2629c631c27","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 Artificial Intelligence, Vol 8 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/frai.2025.1681277","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2025.1681277","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1681277/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"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 Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1027354739","display_name":null,"funder_award_id":"IITP-2025-RS-2024-00436773","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G2117989831","display_name":null,"funder_award_id":"IITP-2025-RS-2024-00436773","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G5293985778","display_name":null,"funder_award_id":"SG20240201","funder_id":"https://openalex.org/F4320321681","funder_display_name":"Ministry of Trade, Industry and Energy"}],"funders":[{"id":"https://openalex.org/F4320321681","display_name":"Ministry of Trade, Industry and Energy","ror":"https://ror.org/008nkqk13"},{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"},{"id":"https://openalex.org/F4320337407","display_name":"Division of Human Resource Development","ror":"https://ror.org/03mamvh39"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416342072.pdf","grobid_xml":"https://content.openalex.org/works/W4416342072.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W2037364857","https://openalex.org/W3001083904","https://openalex.org/W3038935994","https://openalex.org/W3201064488","https://openalex.org/W4283392904","https://openalex.org/W4310230601","https://openalex.org/W4313272453","https://openalex.org/W4386051124","https://openalex.org/W4386276891","https://openalex.org/W4388242041","https://openalex.org/W4391463078","https://openalex.org/W4393079208","https://openalex.org/W4396895114","https://openalex.org/W4397012455","https://openalex.org/W4399153128","https://openalex.org/W4399507014","https://openalex.org/W4399547912","https://openalex.org/W4399990687","https://openalex.org/W4400146581","https://openalex.org/W4401023130","https://openalex.org/W4401306886","https://openalex.org/W4401770219","https://openalex.org/W4403391478","https://openalex.org/W4403682793","https://openalex.org/W4403853618","https://openalex.org/W4404532814","https://openalex.org/W4404570750","https://openalex.org/W4404575436","https://openalex.org/W4404625362","https://openalex.org/W4404909438","https://openalex.org/W4405006707","https://openalex.org/W4406069943","https://openalex.org/W4406077510","https://openalex.org/W4406915597","https://openalex.org/W4407092802","https://openalex.org/W4407189925","https://openalex.org/W4407622810","https://openalex.org/W4407794264","https://openalex.org/W4408253686","https://openalex.org/W4416042718","https://openalex.org/W6929349271","https://openalex.org/W6947991961"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,42,90,147,209],"large":[3],"vision-language":[4],"models":[5],"(LVLMs)":[6],"have":[7],"transformed":[8],"visual":[9,31,40],"recognition":[10,41],"research":[11],"by":[12],"enabling":[13],"multimodal":[14,196],"integration":[15],"of":[16,30,36,70,78,159,162,165,170,193],"images,":[17],"text,":[18],"and":[19,26,72,102,126,137,151,167,180,206],"videos.":[20],"This":[21],"fusion":[22],"supports":[23],"a":[24,53,65,112],"deeper":[25],"more":[27],"context-aware":[28],"understanding":[29],"environments.":[32],"However,":[33],"the":[34,93,191],"application":[35],"LVLMs":[37,58],"to":[38,60],"multitask":[39],"real-world":[43],"construction":[44],"scenarios":[45],"remains":[46],"underexplored.":[47],"In":[48],"this":[49],"study,":[50],"we":[51],"present":[52],"resource-efficient":[54],"framework":[55],"for":[56,199],"fine-tuning":[57,104],"tailored":[59],"autonomous":[61,210],"excavator":[62,211],"operations,":[63],"with":[64,92,106,154],"focus":[66],"on":[67,81,133,139],"robust":[68],"detection":[69,150],"humans":[71,179],"obstacles,":[73],"as":[74,76],"well":[75],"classification":[77],"weather":[79,152,186],"conditions":[80],"consumer-grade":[82],"hardware.":[83],"By":[84],"leveraging":[85],"Quantized":[86],"Low-Rank":[87],"Adaptation":[88],"(QLoRA)":[89],"conjunction":[91],"Unsloth":[94],"framework,":[95],"our":[96],"method":[97],"substantially":[98],"reduces":[99],"memory":[100],"consumption":[101],"accelerates":[103],"compared":[105],"conventional":[107],"approaches.":[108],"We":[109],"comprehensively":[110],"evaluate":[111],"domain-specific":[113],"excavator-vision":[114],"dataset":[115],"using":[116],"five":[117],"open-source":[118],"LVLMs.":[119],"These":[120,188],"include":[121],"Llama-3.2-Vision,":[122],"Qwen2-VL,":[123],"Qwen2.5-VL,":[124],"LLaVA-1.6,":[125],"Gemma":[127],"3.":[128],"Each":[129],"model":[130,175],"is":[131],"fine-tuned":[132,173],"1,000":[134],"annotated":[135],"frames":[136],"tested":[138],"2000":[140],"images.":[141],"Experimental":[142],"results":[143,189],"demonstrate":[144],"significant":[145],"improvements":[146],"both":[148],"object":[149],"classification,":[153],"Qwen2-VL-7B":[155,174],"achieving":[156],"an":[157],"mAP@50":[158],"88.03%,":[160],"mAP@[0.50:0.95]":[161],"74.20%,":[163],"accuracy":[164],"84.54%,":[166],"F1":[168],"score":[169],"78.83%.":[171],"Our":[172],"not":[176],"only":[177],"detects":[178],"obstacles":[181],"robustly":[182],"but":[183],"also":[184],"classifies":[185],"accurately.":[187],"illustrate":[190],"feasibility":[192],"deploying":[194],"LVLM-based":[195],"AI":[197],"agents":[198],"safety":[200],"monitoring,":[201],"pose":[202],"estimation,":[203],"activity":[204],"tracking,":[205],"strategic":[207],"planning":[208],"operations.":[212]},"counts_by_year":[],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-11-18T00:00:00"}