{"id":"https://openalex.org/W4416750750","doi":"https://doi.org/10.1109/iros60139.2025.11247714","title":"RoboDexVLM: Visual Language Model-Enabled Task Planning and Motion Control for Dexterous Robot Manipulation","display_name":"RoboDexVLM: Visual Language Model-Enabled Task Planning and Motion Control for Dexterous Robot Manipulation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750750","doi":"https://doi.org/10.1109/iros60139.2025.11247714"},"language":"en","primary_location":{"id":"doi:10.1109/iros60139.2025.11247714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5104203665","display_name":"Haichao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Haichao Liu","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou),Robotics and Autonomous Systems Thrust,Guangzhou,China,511453"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou),Robotics and Autonomous Systems Thrust,Guangzhou,China,511453","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111350345","display_name":"Sikai Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sikai Guo","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou),Robotics and Autonomous Systems Thrust,Guangzhou,China,511453"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou),Robotics and Autonomous Systems Thrust,Guangzhou,China,511453","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pengfei Mai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengfei Mai","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou),Robotics and Autonomous Systems Thrust,Guangzhou,China,511453"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou),Robotics and Autonomous Systems Thrust,Guangzhou,China,511453","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015422529","display_name":"Jiahang Cao","orcid":"https://orcid.org/0000-0003-4338-4414"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiahang Cao","raw_affiliation_strings":["The Hong Kong University of Science and Technology,The Division of Emerging Interdisciplinary Areas,Hong Kong SAR,China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology,The Division of Emerging Interdisciplinary Areas,Hong Kong SAR,China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040338788","display_name":"Haoang Li","orcid":"https://orcid.org/0000-0002-1576-9408"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Haoang Li","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou),Microelectronics Thrust,Guangzhou,China,511453"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou),Microelectronics Thrust,Guangzhou,China,511453","institution_ids":["https://openalex.org/I90610280","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100357282","display_name":"Jun Ma","orcid":"https://orcid.org/0000-0002-6127-000X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Ma","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou),Robotics and Autonomous Systems Thrust,Guangzhou,China,511453"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou),Robotics and Autonomous Systems Thrust,Guangzhou,China,511453","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5104203665"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2326,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90041653,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1381","last_page":"1388"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8295999765396118,"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":0.8295999765396118,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.09700000286102295,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.009800000116229057,"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/grasp","display_name":"GRASP","score":0.7287999987602234},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6065999865531921},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.5497000217437744},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5329999923706055},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5307999849319458},{"id":"https://openalex.org/keywords/grippers","display_name":"Grippers","score":0.44449999928474426},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.42809998989105225},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.4221000075340271},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.376800000667572},{"id":"https://openalex.org/keywords/robotic-hand","display_name":"Robotic hand","score":0.3589000105857849}],"concepts":[{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.7287999987602234},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6366000175476074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6072999835014343},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6065999865531921},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.5497000217437744},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5329999923706055},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5307999849319458},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5181000232696533},{"id":"https://openalex.org/C2775960376","wikidata":"https://www.wikidata.org/wiki/Q1435859","display_name":"Grippers","level":2,"score":0.44449999928474426},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44179999828338623},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.42809998989105225},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.4221000075340271},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.376800000667572},{"id":"https://openalex.org/C2988191880","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic hand","level":3,"score":0.3589000105857849},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.35600000619888306},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.33329999446868896},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.325300008058548},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.32519999146461487},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.30640000104904175},{"id":"https://openalex.org/C10912380","wikidata":"https://www.wikidata.org/wiki/Q527952","display_name":"Visual servoing","level":3,"score":0.29649999737739563},{"id":"https://openalex.org/C8652668","wikidata":"https://www.wikidata.org/wiki/Q1340324","display_name":"Robot end effector","level":3,"score":0.29589998722076416},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2881999909877777},{"id":"https://openalex.org/C17511633","wikidata":"https://www.wikidata.org/wiki/Q830694","display_name":"SMT placement equipment","level":3,"score":0.28600001335144043},{"id":"https://openalex.org/C2985527887","wikidata":"https://www.wikidata.org/wiki/Q1587588","display_name":"Robot manipulator","level":3,"score":0.28060001134872437},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.267300009727478},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C58581272","wikidata":"https://www.wikidata.org/wiki/Q12741163","display_name":"Workspace","level":3,"score":0.26339998841285706},{"id":"https://openalex.org/C2776010242","wikidata":"https://www.wikidata.org/wiki/Q4677575","display_name":"Active perception","level":3,"score":0.26030001044273376},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.25540000200271606}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros60139.2025.11247714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-169101","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-169101","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1984237968","https://openalex.org/W2128082316","https://openalex.org/W2953669419","https://openalex.org/W3207187156","https://openalex.org/W3213320157","https://openalex.org/W4200213509","https://openalex.org/W4382366145","https://openalex.org/W4387623807","https://openalex.org/W4388823657","https://openalex.org/W4389352485","https://openalex.org/W4390874575","https://openalex.org/W4391128534","https://openalex.org/W4401417048","https://openalex.org/W4401634211","https://openalex.org/W4402354112","https://openalex.org/W4402890475","https://openalex.org/W4404612908","https://openalex.org/W4413146350"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"RoboDexVLM,":[3],"an":[4],"innovative":[5],"framework":[6,54],"for":[7,15,111,132,174],"robot":[8,126],"task":[9,87],"planning":[10],"and":[11,29,66,107,128,139,148,156],"grasp":[12,119],"detection":[13],"tailored":[14,131],"a":[16,21,41,47,56,85,90,116],"collaborative":[17],"manipulator":[18],"equipped":[19],"with":[20,39,89,136],"dexterous":[22,57,118,134,158,176],"hand.":[23],"Previous":[24],"methods":[25],"focus":[26],"on":[27,72,125],"simplified":[28],"limited":[30],"manipulation":[31,135],"tasks,":[32],"which":[33,101],"often":[34],"neglect":[35],"the":[36,80,103,145,163],"complexities":[37],"associated":[38],"grasping":[40,61],"diverse":[42,137],"array":[43],"of":[44,60,63,150],"objects":[45,62,138],"in":[46,152,168],"long-horizon":[48,154],"manner.":[49],"In":[50],"contrast,":[51],"our":[52],"proposed":[53,77],"utilizes":[55],"hand":[58],"capable":[59],"varying":[64],"shapes":[65],"sizes":[67],"while":[68],"executing":[69],"tasks":[70],"based":[71,124],"natural":[73],"language":[74],"commands.":[75,140],"The":[76],"approach":[78],"has":[79],"following":[81],"core":[82],"components:":[83],"First,":[84],"robust":[86],"planner":[88],"task-level":[91],"recovery":[92],"mechanism":[93],"that":[94],"leverages":[95],"vision-language":[96],"models":[97],"(VLMs)":[98],"is":[99,122],"designed,":[100],"enables":[102],"system":[104],"to":[105,166],"interpret":[106],"execute":[108],"open-vocabulary":[109,175],"commands":[110],"long":[112],"sequence":[113],"tasks.":[114],"Second,":[115],"language-guided":[117],"perception":[120],"algorithm":[121],"presented":[123],"kinematics":[127],"formal":[129],"methods,":[130],"zero-shot":[133],"Comprehensive":[141],"experimental":[142],"results":[143,161],"validate":[144],"effectiveness,":[146],"adaptability,":[147],"robustness":[149],"RoboDexVLM":[151],"handling":[153],"scenarios":[155],"performing":[157],"grasping.":[159],"These":[160],"highlight":[162],"framework\u2019s":[164],"ability":[165],"operate":[167],"complex":[169],"environments,":[170],"showcasing":[171],"its":[172],"potential":[173],"manipulation.":[177],"Our":[178],"open-source":[179],"project":[180],"page":[181],"can":[182],"be":[183],"found":[184],"at":[185],"https://henryhcliu.github.io/robodexvlm.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-11-28T00:00:00"}
