{"id":"https://openalex.org/W7130575746","doi":"https://doi.org/10.1109/ictc66702.2025.11388300","title":"Perception to Action with Vision-Language-Action Models for Fast and Reliable Decision Making in Dynamic Environments","display_name":"Perception to Action with Vision-Language-Action Models for Fast and Reliable Decision Making in Dynamic Environments","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W7130575746","doi":"https://doi.org/10.1109/ictc66702.2025.11388300"},"language":null,"primary_location":{"id":"doi:10.1109/ictc66702.2025.11388300","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11388300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5121825351","display_name":"Yeryeong Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yeryeong Cho","raw_affiliation_strings":["Korea University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030921798","display_name":"JW Choe","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaeyoung Choe","raw_affiliation_strings":["Korea University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126424237","display_name":"Joongheon Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joongheon Kim","raw_affiliation_strings":["Korea University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"810","last_page":"812"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9315999746322632,"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":0.9315999746322632,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.009999999776482582,"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"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.007400000002235174,"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/task","display_name":"Task (project management)","score":0.6748999953269958},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6743000149726868},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.64410001039505},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.520799994468689},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.45829999446868896},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4440000057220459},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4359999895095825},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.38519999384880066},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.3779999911785126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7684999704360962},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6748999953269958},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6743000149726868},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.64410001039505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5529000163078308},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.520799994468689},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4869000017642975},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.45829999446868896},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4440000057220459},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4359999895095825},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.3779999911785126},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.35519999265670776},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3425999879837036},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.3125},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3061000108718872},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2957000136375427},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29010000824928284},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc66702.2025.11388300","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11388300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6961560845375061}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2082991751","https://openalex.org/W2604698059","https://openalex.org/W2963525569","https://openalex.org/W3211462570","https://openalex.org/W4312427786","https://openalex.org/W4383093244","https://openalex.org/W4385430679","https://openalex.org/W4389326543","https://openalex.org/W4389510174","https://openalex.org/W4390843813","https://openalex.org/W4391021503","https://openalex.org/W4392172801","https://openalex.org/W4401417184","https://openalex.org/W4403852428","https://openalex.org/W4405022833","https://openalex.org/W4413156213"],"related_works":[],"abstract_inverted_index":{"Executing":[0],"natural-language":[1],"instructions":[2,51],"in":[3,107],"dynamic":[4,109],"environments":[5],"requires":[6],"robust":[7],"integration":[8],"of":[9],"perception,":[10],"planning,":[11],"and":[12,27,50,57,100,126],"control.":[13,59],"Conventional":[14],"vision\u2013language":[15,67],"models":[16],"(VLMs)":[17],"provide":[18],"open-vocabulary":[19],"recognition":[20],"but":[21],"often":[22],"leave":[23],"a":[24,40,79,108],"perception\u2013action":[25,95],"gap":[26],"fail":[28],"to":[29,52,69,131],"ensure":[30],"safety":[31,76],"under":[32],"uncertainty.":[33],"To":[34],"address":[35],"this":[36],"challenge,":[37],"we":[38],"propose":[39],"Vision-Language":[41],"Action":[42],"Model":[43],"(VLAM)":[44],"that":[45,118],"directly":[46],"maps":[47],"visual":[48],"observations":[49],"actions":[53,72],"through":[54],"adaptive":[55],"perception":[56],"uncertainty-aware":[58],"The":[60],"algorithm":[61],"leverages":[62],"contrastive":[63],"language-image":[64],"pretraining":[65],"(CLIP)-based":[66],"similarity":[68],"score":[70],"candidate":[71],"while":[73],"incorporating":[74],"rule-based":[75],"priors":[77],"as":[78],"fallback":[80],"mechanism":[81],"when":[82],"confidence":[83],"is":[84,89],"low":[85],"or":[86],"collision":[87],"risk":[88],"detected.":[90],"This":[91],"design":[92],"narrows":[93],"the":[94,119],"gap,":[96],"maintains":[97],"semantic":[98],"grounding,":[99],"guarantees":[101],"stable":[102],"behavior.":[103],"We":[104],"evaluate":[105],"VLAM":[106],"multi-agent":[110],"environment":[111],"with":[112],"moving":[113],"obstacles.":[114],"Experimental":[115],"results":[116],"demonstrate":[117],"proposed":[120],"method":[121],"achieves":[122],"higher":[123],"task":[124],"success":[125],"reduced":[127],"inter-agent":[128],"conflicts":[129],"compared":[130],"baseline":[132],"strategies.":[133]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-20T00:00:00"}