{"id":"https://openalex.org/W7135098435","doi":"https://doi.org/10.1145/3776734.3794528","title":"HumanoidVLM: Vision-Language-Guided Impedance Control for Contact-Rich Humanoid Manipulation","display_name":"HumanoidVLM: Vision-Language-Guided Impedance Control for Contact-Rich Humanoid Manipulation","publication_year":2026,"publication_date":"2026-03-12","ids":{"openalex":"https://openalex.org/W7135098435","doi":"https://doi.org/10.1145/3776734.3794528"},"language":null,"primary_location":{"id":"doi:10.1145/3776734.3794528","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3776734.3794528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"type":"article","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/A5123560143","display_name":"Yara Mahmoud","orcid":null},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Yara Mahmoud","raw_affiliation_strings":["Skolkovo Institute of Science and Technology, Moscow, Russian Federation"],"raw_orcid":"https://orcid.org/0009-0009-5104-682X","affiliations":[{"raw_affiliation_string":"Skolkovo Institute of Science and Technology, Moscow, Russian Federation","institution_ids":["https://openalex.org/I125989756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104621266","display_name":"Yasheerah Yaqoot","orcid":null},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Yasheerah Yaqoot","raw_affiliation_strings":["Skolkovo Institute of Science and Technology, Moscow, Russian Federation"],"raw_orcid":"https://orcid.org/0009-0004-3610-2452","affiliations":[{"raw_affiliation_string":"Skolkovo Institute of Science and Technology, Moscow, Russian Federation","institution_ids":["https://openalex.org/I125989756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128903282","display_name":"Miguel Altamirano Cabrera","orcid":null},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Miguel Altamirano Cabrera","raw_affiliation_strings":["Skolkovo Institute of Science and Technology, Moscow, Russian Federation"],"raw_orcid":"https://orcid.org/0000-0002-5974-9257","affiliations":[{"raw_affiliation_string":"Skolkovo Institute of Science and Technology, Moscow, Russian Federation","institution_ids":["https://openalex.org/I125989756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128841721","display_name":"Dzmitry Tsetserukou","orcid":null},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Dzmitry Tsetserukou","raw_affiliation_strings":["Skolkovo Institute of Science and Technology, Moscow, Russian Federation"],"raw_orcid":"https://orcid.org/0000-0001-8055-5345","affiliations":[{"raw_affiliation_string":"Skolkovo Institute of Science and Technology, Moscow, Russian Federation","institution_ids":["https://openalex.org/I125989756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5123560143"],"corresponding_institution_ids":["https://openalex.org/I125989756"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.54661191,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"918","last_page":"922"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.7317000031471252,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.7317000031471252,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.10260000079870224,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.05130000039935112,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/humanoid-robot","display_name":"Humanoid robot","score":0.6819000244140625},{"id":"https://openalex.org/keywords/impedance-control","display_name":"Impedance control","score":0.6363000273704529},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.6168000102043152},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5462999939918518},{"id":"https://openalex.org/keywords/electrical-impedance","display_name":"Electrical impedance","score":0.5230000019073486},{"id":"https://openalex.org/keywords/cartesian-coordinate-system","display_name":"Cartesian coordinate system","score":0.4180999994277954},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.415800005197525},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.39739999175071716},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3549000024795532}],"concepts":[{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.6819000244140625},{"id":"https://openalex.org/C2777984285","wikidata":"https://www.wikidata.org/wiki/Q17098134","display_name":"Impedance control","level":3,"score":0.6363000273704529},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.619700014591217},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.6168000102043152},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5691999793052673},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5462999939918518},{"id":"https://openalex.org/C17829176","wikidata":"https://www.wikidata.org/wiki/Q179043","display_name":"Electrical impedance","level":2,"score":0.5230000019073486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49050000309944153},{"id":"https://openalex.org/C16038011","wikidata":"https://www.wikidata.org/wiki/Q62912","display_name":"Cartesian coordinate system","level":2,"score":0.4180999994277954},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.415800005197525},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.39739999175071716},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.34209999442100525},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.33309999108314514},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C161759796","wikidata":"https://www.wikidata.org/wiki/Q3982902","display_name":"Teleoperation","level":3,"score":0.31709998846054077},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C108811297","wikidata":"https://www.wikidata.org/wiki/Q214518","display_name":"Admittance","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C2775960376","wikidata":"https://www.wikidata.org/wiki/Q1435859","display_name":"Grippers","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.28760001063346863},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C113805353","wikidata":"https://www.wikidata.org/wiki/Q13424600","display_name":"Impedance parameters","level":3,"score":0.28209999203681946},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2782000005245209}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3776734.3794528","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3776734.3794528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2841149998","display_name":null,"funder_award_id":"24-41-02039","funder_id":"https://openalex.org/F4320324099","funder_display_name":"Russian Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320324099","display_name":"Russian Science Foundation","ror":"https://ror.org/03y2gwe85"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1820657498","https://openalex.org/W1967377907","https://openalex.org/W2110454168","https://openalex.org/W2765218414","https://openalex.org/W3115157241","https://openalex.org/W4385430679","https://openalex.org/W4401417048","https://openalex.org/W4403074774","https://openalex.org/W4403656976","https://openalex.org/W4406613045","https://openalex.org/W4416245575","https://openalex.org/W4416422407","https://openalex.org/W4416750732","https://openalex.org/W7131086494","https://openalex.org/W7133196460"],"related_works":[],"abstract_inverted_index":{"Humanoid":[0],"robots":[1],"must":[2],"adapt":[3],"their":[4],"contact":[5],"behavior":[6],"to":[7,38,124],"diverse":[8],"objects":[9],"and":[10,21,44,76,84,102,127],"tasks,":[11],"yet":[12],"most":[13],"controllers":[14],"rely":[15],"on":[16,98],"fixed,":[17],"hand-tuned":[18],"impedance":[19,42,90,133],"gains":[20],"gripper":[22,45],"settings.":[23,134],"This":[24],"paper":[25],"introduces":[26],"HumanoidVLM,":[27],"a":[28,56,64,88,104],"vision\u2013language-driven":[29],"retrieval":[30,105],"framework":[31],"that":[32,70],"enables":[33],"the":[34,138],"Unitree":[35],"G1":[36],"humanoid":[37,153],"select":[39],"task-appropriate":[40],"cartesian":[41],"parameters":[43],"configurations":[46],"directly":[47],"from":[48,80],"an":[49,148],"egocentric":[50],"RGB":[51],"image.":[52],"The":[53],"system":[54],"couples":[55],"vision\u2013language":[57],"model":[58],"for":[59,92],"semantic":[60,142],"task":[61],"inference":[62],"with":[63,116,131,144],"FAISS-based":[65],"Retrieval-Augmented":[66],"Generation":[67],"(RAG)":[68],"module":[69],"retrieves":[71],"experimentally":[72],"validated":[73],"stiffness\u2013damping":[74],"pairs":[75],"object-specific":[77],"grasp":[78],"angles":[79],"two":[81],"custom":[82],"databases":[83],"executes":[85],"them":[86],"through":[87],"task-space":[89],"controller":[91],"compliant":[93],"manipulation.":[94,154],"We":[95],"evaluate":[96],"HumanoidVLM":[97],"14":[99],"visual":[100],"scenarios":[101],"achieve":[103],"accuracy":[106],"of":[107,140],"93":[108],"%.":[109],"Real-world":[110],"experiments":[111],"show":[112],"stable":[113],"interaction":[114],"dynamics,":[115],"z-axis":[117],"tracking":[118],"errors":[119],"typically":[120],"within":[121],"1":[122],"cm":[123,126],"3.5":[125],"virtual":[128],"forces":[129],"consistent":[130],"task-dependent":[132],"These":[135],"results":[136],"demonstrate":[137],"feasibility":[139],"linking":[141],"perception":[143],"retrieval-based":[145],"control":[146],"as":[147],"interpretable":[149],"path":[150],"toward":[151],"adaptive":[152]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-03-13T00:00:00"}
