{"id":"https://openalex.org/W7135085282","doi":"https://doi.org/10.1145/3776734.3794572","title":"DroneVLA: VLA-Based Aerial Manipulation","display_name":"DroneVLA: VLA-Based Aerial Manipulation","publication_year":2026,"publication_date":"2026-03-12","ids":{"openalex":"https://openalex.org/W7135085282","doi":"https://doi.org/10.1145/3776734.3794572"},"language":null,"primary_location":{"id":"doi:10.1145/3776734.3794572","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3776734.3794572","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/A5123637687","display_name":"Fawad Mehboob","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":"Fawad Mehboob","raw_affiliation_strings":["Skolkovo Institute of Science and Technology, Moscow, Russian Federation"],"raw_orcid":"https://orcid.org/0009-0002-0850-6519","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/A5128853032","display_name":"MoniJesu Wonders James","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":"MoniJesu Wonders James","raw_affiliation_strings":["Skolkovo Institute of Science and Technology, Moscow, Russian Federation"],"raw_orcid":"https://orcid.org/0009-0002-7524-0108","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/A5128822309","display_name":"Amir Atef Habel","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":"Amir Atef Habel","raw_affiliation_strings":["Skolkovo Institute of Science and Technology, Moscow, Russian Federation"],"raw_orcid":"https://orcid.org/0009-0009-4239-219X","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/A5123453619","display_name":"Jeffrin Sam","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":"Jeffrin Sam","raw_affiliation_strings":["Skolkovo Institute of Science and Technology, Moscow, Russian Federation"],"raw_orcid":"https://orcid.org/0009-0000-8635-5379","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":1,"corresponding_author_ids":[],"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":0.43521014,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1135","last_page":"1139"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.3183000087738037,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.3183000087738037,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T11133","display_name":"UAV Applications and Optimization","score":0.06629999727010727,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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":0.05730000138282776,"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/visual-servoing","display_name":"Visual servoing","score":0.6992999911308289},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6647999882698059},{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.5224999785423279},{"id":"https://openalex.org/keywords/handover","display_name":"Handover","score":0.5048999786376953},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4571000039577484},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4496999979019165},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.44699999690055847},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4442000091075897},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.40049999952316284}],"concepts":[{"id":"https://openalex.org/C10912380","wikidata":"https://www.wikidata.org/wiki/Q527952","display_name":"Visual servoing","level":3,"score":0.6992999911308289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6898999810218811},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6647999882698059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6065999865531921},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5679000020027161},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.5224999785423279},{"id":"https://openalex.org/C111852164","wikidata":"https://www.wikidata.org/wiki/Q1414679","display_name":"Handover","level":2,"score":0.5048999786376953},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4496999979019165},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.44699999690055847},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4442000091075897},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C2775960376","wikidata":"https://www.wikidata.org/wiki/Q1435859","display_name":"Grippers","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3467999994754791},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.29829999804496765},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2924000024795532},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.28839999437332153},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2597000002861023},{"id":"https://openalex.org/C2780527621","wikidata":"https://www.wikidata.org/wiki/Q7936593","display_name":"Visual control","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3776734.3794572","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3776734.3794572","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":13,"referenced_works":["https://openalex.org/W1591981541","https://openalex.org/W1999657641","https://openalex.org/W2792083172","https://openalex.org/W2809971797","https://openalex.org/W2909187758","https://openalex.org/W2967235442","https://openalex.org/W3005101058","https://openalex.org/W4213424679","https://openalex.org/W4391547874","https://openalex.org/W4403721801","https://openalex.org/W4407874080","https://openalex.org/W4410297957","https://openalex.org/W4414360275"],"related_works":[],"abstract_inverted_index":{"This":[0,120],"work":[1],"introduces":[2],"a":[3,26,35,40,45,50,68,73,114,136,147,165],"novel":[4],"concept":[5],"of":[6,13,67,143,173,185],"an":[7,54],"autonomous":[8],"aerial":[9,188],"manipulation":[10,189],"system":[11,30,112],"capable":[12],"interpreting":[14],"high-level":[15],"natural":[16,105],"language":[17],"commands":[18],"to":[19,25,33,63,94,130,134],"retrieve":[20],"objects":[21,80],"and":[22,39,53,71,86,96,104,160,170,177],"deliver":[23],"them":[24],"human":[27,124],"user.":[28],"The":[29],"is":[31],"intended":[32],"integrate":[34],"MediaPipe-based":[36],"Grounding":[37,84],"DINO":[38,85],"Vision-Language-Action":[41],"(VLA)":[42],"model":[43],"with":[44,49],"custom-built":[46],"drone":[47,129],"equipped":[48],"1-DOF":[51],"gripper":[52],"Intel":[55],"RealSense":[56],"RGB-D":[57],"camera.":[58],"VLA":[59,186],"performs":[60],"semantic":[61],"reasoning":[62],"interpret":[64],"the":[65,82,87,99,108,111,128,144,152,183],"intent":[66],"user":[69],"prompt":[70],"generates":[72],"prioritized":[74],"task":[75],"queue":[76],"for":[77,158,187],"grasping":[78],"relevant":[79],"in":[81,141,164],"scene.":[83],"dynamic":[88],"A*":[89],"planning":[90],"algorithm":[91],"are":[92],"used":[93],"navigate":[95],"safely":[97],"relocate":[98],"object.":[100],"To":[101],"ensure":[102],"safe":[103],"interaction":[106],"during":[107],"handover":[109],"phase,":[110],"employs":[113],"human-centric":[115],"controller":[116],"driven":[117],"by":[118],"MediaPipe.":[119],"module":[121],"provides":[122],"real-time":[123],"pose":[125],"estimation,":[126],"allowing":[127],"employ":[131],"visual":[132],"servoing":[133],"maintain":[135],"stable,":[137],"distinct":[138],"position":[139],"directly":[140],"front":[142],"user,":[145],"facilitating":[146],"comfortable":[148],"handover.":[149],"We":[150],"demonstrate":[151],"system's":[153],"efficacy":[154],"through":[155],"real-world":[156],"experiments":[157],"localization":[159],"navigation,":[161],"which":[162],"resulted":[163],"16.4":[166],"cm,":[167,169],"7.0":[168],"8.4":[171],"cm":[172],"max,":[174],"mean":[175],"euclidean,":[176],"root-mean":[178],"squared":[179],"errors,":[180],"respectively,":[181],"highlighting":[182],"feasibility":[184],"operations.":[190]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2026-03-13T00:00:00"}
