{"id":"https://openalex.org/W7166707837","doi":"https://doi.org/10.7148/2026-0151","title":"Vision\u2013language\u2013action models for hri/hrc/hrt: a taxonomy, simulation-centric gaps, and research directions","display_name":"Vision\u2013language\u2013action models for hri/hrc/hrt: a taxonomy, simulation-centric gaps, and research directions","publication_year":2026,"publication_date":"2026-06-23","ids":{"openalex":"https://openalex.org/W7166707837","doi":"https://doi.org/10.7148/2026-0151"},"language":null,"primary_location":{"id":"doi:10.7148/2026-0151","is_oa":true,"landing_page_url":"https://doi.org/10.7148/2026-0151","pdf_url":"https://doi.org/10.7148/2026-0151","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ECMS 2026 Proceedings edited by Filippo Sanfilippo, Florenc Demrozi, Fabio Sgarbossa, Mohammad Poursina","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.7148/2026-0151","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139678059","display_name":"Jiri Konecny","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiri Konecny","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139675593","display_name":"Filippo Sanfilippo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Filippo Sanfilippo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139697822","display_name":"Michal Prauzek","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michal Prauzek","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"151","last_page":"160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.3587000072002411,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.3587000072002411,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3156000077724457,"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/T10525","display_name":"Human-Automation Interaction and Safety","score":0.04800000041723251,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.6561999917030334},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5619000196456909},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5266000032424927},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4927999973297119},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49140000343322754},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.38029998540878296},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.3781999945640564}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6597999930381775},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.6561999917030334},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5619000196456909},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5266000032424927},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4927999973297119},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49140000343322754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.446399986743927},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4226999878883362},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.32580000162124634},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.325300008058548},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3174999952316284},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.29249998927116394},{"id":"https://openalex.org/C65414064","wikidata":"https://www.wikidata.org/wiki/Q484105","display_name":"Autonomy","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2854999899864197},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.26080000400543213}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.7148/2026-0151","is_oa":true,"landing_page_url":"https://doi.org/10.7148/2026-0151","pdf_url":"https://doi.org/10.7148/2026-0151","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ECMS 2026 Proceedings edited by Filippo Sanfilippo, Florenc Demrozi, Fabio Sgarbossa, Mohammad Poursina","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.7148/2026-0151","is_oa":true,"landing_page_url":"https://doi.org/10.7148/2026-0151","pdf_url":"https://doi.org/10.7148/2026-0151","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ECMS 2026 Proceedings edited by Filippo Sanfilippo, Florenc Demrozi, Fabio Sgarbossa, Mohammad Poursina","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166707837.pdf","grobid_xml":"https://content.openalex.org/works/W7166707837.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Robotics":[0],"driven":[1],"by":[2,66,86],"foundation":[3],"models,":[4],"such":[5,83],"as":[6],"Vision--Language--Action":[7],"(VLA)":[8],"systems,":[9],"already":[10],"represents":[11],"a":[12,112,156],"major":[13],"step":[14],"forward":[15],"in":[16,167],"autonomy":[17],"and":[18,42,56,70,78,85,96,106,120,128,150,154,160],"natural-language":[19],"interaction.":[20],"Yet,":[21],"many":[22],"obstacles":[23],"remain":[24,57],"on":[25],"the":[26,136],"path":[27],"toward":[28],"Human--Robot":[29],"Teaming":[30],"(HRT):":[31],"most":[32],"current":[33],"models":[34],"improve":[35],"\\emph{task":[36],"autonomy}":[37],"faster":[38],"than":[39],"\\emph{teaming":[40],"autonomy},":[41],"therefore":[43],"lack":[44],"key":[45],"properties":[46],"required":[47],"for":[48,82,163],"human-centred":[49],"deployments":[50],"where":[51],"robots":[52],"must":[53],"coordinate,":[54],"clarify,":[55],"safe":[58],"under":[59],"contact-rich":[60],"uncertainty.":[61],"This":[62],"gap":[63],"is":[64],"compounded":[65],"limited":[67],"multimodality":[68],"(tactile":[69],"audio":[71],"channels":[72],"are":[73],"often":[74],"missing),":[75],"scarce":[76],"datasets":[77],"unified":[79],"input":[80],"formats":[81],"signals,":[84],"simulation":[87],"limits---digital":[88],"twins":[89],"typically":[90],"under-represent":[91],"real-world":[92,183],"noise,":[93],"disturbances,":[94],"imperfections,":[95],"unpredictable":[97],"events":[98],"across":[99],"modalities.":[100],"To":[101],"make":[102,175],"HRT":[103,137,176],"readiness":[104,177],"explicit":[105],"testable,":[107],"this":[108],"paper":[109],"provides":[110],"(i)":[111],"taxonomy":[113],"of":[114,135],"contemporary":[115],"VLA":[116],"architectures":[117],"(monolithic,":[118],"hierarchical,":[119],"agentic/world-model)":[121],"together":[122],"with":[123],"axes":[124],"that":[125],"separate":[126],"task":[127],"teaming":[129],"autonomy,":[130],"(ii)":[131],"an":[132],"operational":[133],"decomposition":[134],"barrier":[138],"into":[139],"four":[140],"capability":[141],"blocks":[142],"spanning":[143],"human-state":[144],"alignment,":[145],"interaction":[146],"policies,":[147],"contact":[148],"robustness,":[149],"shared":[151],"team":[152],"state,":[153],"(iii)":[155],"simulation-centric":[157],"evaluation":[158],"protocol":[159],"metric":[161],"suite":[162],"reproducible":[164],"stress":[165],"testing":[166],"digital":[168],"twins.":[169],"The":[170],"proposed":[171],"framework":[172],"aims":[173],"to":[174],"measurable":[178],"before":[179],"costly":[180],"or":[181],"risky":[182],"trials.":[184]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-07-01T00:00:00"}
