{"id":"https://openalex.org/W7131189345","doi":"https://doi.org/10.1109/robio66223.2025.11377394","title":"VLC: A Human-Robot-Collaboration Framework with Vision-Language-Model","display_name":"VLC: A Human-Robot-Collaboration Framework with Vision-Language-Model","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7131189345","doi":"https://doi.org/10.1109/robio66223.2025.11377394"},"language":null,"primary_location":{"id":"doi:10.1109/robio66223.2025.11377394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio66223.2025.11377394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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/A5126583030","display_name":"Zilong Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zilong Chen","raw_affiliation_strings":["Southern University of Science and Technology,Shenzhen,China,518055"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,Shenzhen,China,518055","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111042722","display_name":"Lebin Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lebin Liang","raw_affiliation_strings":["Guangdong Provincial Key Lab of Robotics and Intelligent System, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China,518055"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Lab of Robotics and Intelligent System, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China,518055","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126584416","display_name":"Haonian Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haonian Dong","raw_affiliation_strings":["Guangdong Provincial Key Lab of Robotics and Intelligent System, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China,518055"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Lab of Robotics and Intelligent System, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China,518055","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126609854","display_name":"Dehao Kong","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dehao Kong","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications,Nanjing,China,210023"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications,Nanjing,China,210023","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Can Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Can Wang","raw_affiliation_strings":["Guangdong Provincial Key Lab of Robotics and Intelligent System, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China,518055"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Lab of Robotics and Intelligent System, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China,518055","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063786172","display_name":"Xinyu Wu","orcid":"https://orcid.org/0000-0001-6130-7821"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Wu","raw_affiliation_strings":["Guangdong Provincial Key Lab of Robotics and Intelligent System, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China,518055"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Lab of Robotics and Intelligent System, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China,518055","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"2099","last_page":"2104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3734000027179718,"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":0.3734000027179718,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.07240000367164612,"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/T10851","display_name":"Optical Wireless Communication Technologies","score":0.05000000074505806,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/task","display_name":"Task (project management)","score":0.5999000072479248},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5073999762535095},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.45730000734329224},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.4399000108242035},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4372999966144562},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.42750000953674316},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.37940001487731934},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.37529999017715454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7023000121116638},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6514000296592712},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5999000072479248},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5073999762535095},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.45730000734329224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44369998574256897},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.4399000108242035},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4372999966144562},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.42750000953674316},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3312000036239624},{"id":"https://openalex.org/C152086174","wikidata":"https://www.wikidata.org/wiki/Q3030571","display_name":"Haptic technology","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.2529999911785126},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio66223.2025.11377394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio66223.2025.11377394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2934724902","display_name":null,"funder_award_id":"62373344","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":16,"referenced_works":["https://openalex.org/W1487858791","https://openalex.org/W2103738037","https://openalex.org/W2103831616","https://openalex.org/W2122139236","https://openalex.org/W2568343704","https://openalex.org/W2765218414","https://openalex.org/W2771354076","https://openalex.org/W2953773709","https://openalex.org/W3059965140","https://openalex.org/W4383097638","https://openalex.org/W4383108753","https://openalex.org/W4388720459","https://openalex.org/W4389666038","https://openalex.org/W4405786324","https://openalex.org/W4406711794","https://openalex.org/W4414079054"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,11,20,139],"Vision-Language-Action":[3],"(VLA)":[4],"models":[5],"have":[6],"significantly":[7],"enhanced":[8],"robots'":[9],"capabilities":[10],"instruction":[12],"following":[13],"and":[14,39,46,64,88,92,114,135,150],"multimodal":[15],"reasoning.":[16],"However,":[17],"their":[18,137],"effectiveness":[19],"close-proximity":[21],"physical":[22,34,102],"human-robot":[23,69,152],"collaboration":[24],"remains":[25],"limited,":[26],"primarily":[27],"due":[28],"to":[29,129],"the":[30,107],"neglect":[31],"of":[32,100],"non-verbal":[33],"cues\u2014such":[35],"as":[36],"force,":[37],"contact,":[38],"motion":[40],"intent\u2014that":[41],"are":[42],"essential":[43],"for":[44,67,79,86,97,146],"fluent":[45],"safe":[47],"interaction.":[48],"To":[49],"address":[50],"this":[51],"limitation,":[52],"we":[53],"introduce":[54],"Vision-Language-Collaboration":[55],"(VLC),":[56],"a":[57,75,83,93,111,144],"novel":[58],"framework":[59,73],"that":[60,125],"unifies":[61],"multi-modal":[62],"perception":[63],"bidirectional":[65],"interaction":[66],"physically-aware":[68],"teaming.":[70],"The":[71],"proposed":[72],"inte-grates":[74],"Vision-Language":[76],"Model":[77],"(VLM)":[78],"high-level":[80],"task":[81],"reasoning,":[82],"vision":[84],"module":[85,96],"environment":[87],"human-object":[89],"state":[90],"perception,":[91],"haptic":[94],"sensing":[95],"real-time":[98],"inference":[99],"human":[101,133],"intent.":[103],"We":[104],"formally":[105],"define":[106],"VLC":[108,126],"paradigm,":[109],"implement":[110],"prototype":[112],"system,":[113],"validate":[115],"its":[116],"feasibility":[117],"through":[118],"collaborative":[119],"manipulation":[120],"experiments.":[121],"Experimental":[122],"results":[123],"demonstrate":[124],"enables":[127],"robots":[128],"more":[130,147],"accurately":[131],"infer":[132],"intent":[134],"adapt":[136],"actions":[138],"real":[140],"time,":[141],"thereby":[142],"establishing":[143],"foundation":[145],"intuitive,":[148],"responsive,":[149],"harmonious":[151],"collaboration.":[153]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-24T00:00:00"}
