{"id":"https://openalex.org/W7130576297","doi":"https://doi.org/10.1109/fllm67465.2025.11390966","title":"GestOS: Advanced Hand Gesture Interpretation via Large Language Models to control Any Type of Robot","display_name":"GestOS: Advanced Hand Gesture Interpretation via Large Language Models to control Any Type of Robot","publication_year":2025,"publication_date":"2025-11-25","ids":{"openalex":"https://openalex.org/W7130576297","doi":"https://doi.org/10.1109/fllm67465.2025.11390966"},"language":null,"primary_location":{"id":"doi:10.1109/fllm67465.2025.11390966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm67465.2025.11390966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 3rd International Conference on Foundation and Large Language Models (FLLM)","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/A5059197603","display_name":"Artem Lykov","orcid":"https://orcid.org/0000-0001-6119-2366"},"institutions":[{"id":"https://openalex.org/I9115533","display_name":"Moscow Polytechnic University","ror":"https://ror.org/03paz2a60","country_code":"RU","type":"education","lineage":["https://openalex.org/I9115533"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Artem Lykov","raw_affiliation_strings":["Skoltech,ISR Lab,Moscow,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Skoltech,ISR Lab,Moscow,Russia","institution_ids":["https://openalex.org/I9115533"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126443180","display_name":"Oleg Kobzarev","orcid":null},"institutions":[{"id":"https://openalex.org/I9115533","display_name":"Moscow Polytechnic University","ror":"https://ror.org/03paz2a60","country_code":"RU","type":"education","lineage":["https://openalex.org/I9115533"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Oleg Kobzarev","raw_affiliation_strings":["Skoltech,ISR Lab,Moscow,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Skoltech,ISR Lab,Moscow,Russia","institution_ids":["https://openalex.org/I9115533"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056458774","display_name":"Dzmitry Tsetserukou","orcid":"https://orcid.org/0000-0001-8055-5345"},"institutions":[{"id":"https://openalex.org/I9115533","display_name":"Moscow Polytechnic University","ror":"https://ror.org/03paz2a60","country_code":"RU","type":"education","lineage":["https://openalex.org/I9115533"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Dzmitry Tsetserukou","raw_affiliation_strings":["Skoltech,ISR Lab,Moscow,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Skoltech,ISR Lab,Moscow,Russia","institution_ids":["https://openalex.org/I9115533"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9115533"],"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":"976","last_page":"981"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2919999957084656,"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":0.2919999957084656,"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":0.1761000007390976,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.15800000727176666,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/gesture","display_name":"Gesture","score":0.8192999958992004},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6208000183105469},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5418999791145325},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.4586000144481659},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4526999890804291},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4244000017642975},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.4185999929904938},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.4146000146865845}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8192999958992004},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.705299973487854},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6208000183105469},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.595300018787384},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5418999791145325},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5095999836921692},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.4586000144481659},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4526999890804291},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4244000017642975},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.4185999929904938},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.4146000146865845},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4115000069141388},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.30959999561309814},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.2824000120162964},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27630001306533813},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.26649999618530273},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2603999972343445}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fllm67465.2025.11390966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm67465.2025.11390966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 3rd International Conference on Foundation and Large Language Models (FLLM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2007730520","https://openalex.org/W2022214202","https://openalex.org/W2125838338","https://openalex.org/W2137448229","https://openalex.org/W2144380653","https://openalex.org/W2154543878","https://openalex.org/W2592523922","https://openalex.org/W2963488642","https://openalex.org/W3034758614","https://openalex.org/W4200554356","https://openalex.org/W4318953217","https://openalex.org/W4383108320","https://openalex.org/W4387421577","https://openalex.org/W4388692601","https://openalex.org/W4391572558","https://openalex.org/W4392646028","https://openalex.org/W4401415888","https://openalex.org/W4402716288","https://openalex.org/W4402727730","https://openalex.org/W4403717124","https://openalex.org/W4404915039","https://openalex.org/W4405786333","https://openalex.org/W4413147465","https://openalex.org/W4413925337"],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"GestOS,":[2],"a":[3,8],"gesture-based":[4],"Operating":[5],"System":[6],"for":[7],"high-level":[9],"control":[10,104],"of":[11,110],"heterogeneous":[12],"robot":[13,81],"teams.":[14],"Unlike":[15],"prior":[16],"systems":[17,132],"that":[18,85],"map":[19],"gestures":[20,30],"to":[21,73,91,120],"fixed":[22],"commands":[23],"or":[24,112],"single-agent":[25],"actions,":[26],"GestOS":[27,123],"interprets":[28],"hand":[29,61],"semantically":[31],"and":[32,45,76,127],"dynamically":[33],"distributes":[34],"tasks":[35],"across":[36],"multiple":[37],"robots":[38],"based":[39],"on":[40],"their":[41],"capabilities,":[42],"current":[43],"state,":[44],"supported":[46],"instruction":[47],"sets.":[48],"The":[49],"system":[50],"combines":[51],"lightweight":[52],"visual":[53],"perception":[54],"with":[55,130],"Large":[56],"Language":[57],"Model":[58],"(LLM)":[59],"reasoning:":[60],"poses":[62],"are":[63],"converted":[64],"into":[65],"the":[66,92],"structured":[67],"textual":[68],"descriptions,":[69],"which":[70],"LLM":[71],"uses":[72],"infer":[74],"intent":[75],"generate":[77],"robot-specific":[78],"commands.":[79,113],"A":[80],"selection":[82],"module":[83],"ensures":[84],"each":[86],"gesture-triggered":[87],"task":[88],"is":[89],"matched":[90],"most":[93],"suitable":[94],"agent":[95],"in":[96,133],"real":[97],"time.":[98],"This":[99],"architecture":[100],"enables":[101],"context-aware,":[102],"adaptive":[103],"without":[105],"requiring":[106],"explicit":[107],"user":[108],"specification":[109],"targets":[111],"By":[114],"advancing":[115],"gesture":[116],"interaction":[117],"from":[118],"recognition":[119],"intelligent":[121],"orchestration,":[122],"supports":[124],"scalable,":[125],"flexible,":[126],"user-friendly":[128],"collaboration":[129],"robotic":[131],"dynamic":[134],"environments.":[135]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-20T00:00:00"}
