{"id":"https://openalex.org/W4416749524","doi":"https://doi.org/10.1109/iros60139.2025.11247258","title":"VLIN-RL: A Unified Vision-Language Interpreter and Reinforcement Learning Motion Planner Framework for Robot Dynamic Tasks","display_name":"VLIN-RL: A Unified Vision-Language Interpreter and Reinforcement Learning Motion Planner Framework for Robot Dynamic Tasks","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749524","doi":"https://doi.org/10.1109/iros60139.2025.11247258"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247258","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/A5018783984","display_name":"Zewu Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zewu Jiang","raw_affiliation_strings":["Tianjin University,School of Electrical and Information Engineering,Tianjin,China,300072"],"affiliations":[{"raw_affiliation_string":"Tianjin University,School of Electrical and Information Engineering,Tianjin,China,300072","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101756653","display_name":"Junnan Zhang","orcid":"https://orcid.org/0000-0001-8830-222X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junnan Zhang","raw_affiliation_strings":["Tianjin University,School of Electrical and Information Engineering,Tianjin,China,300072"],"affiliations":[{"raw_affiliation_string":"Tianjin University,School of Electrical and Information Engineering,Tianjin,China,300072","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693413","display_name":"Ke Wang","orcid":"https://orcid.org/0000-0002-5615-0847"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Wang","raw_affiliation_strings":["Tianjin University,School of Electrical and Information Engineering,Tianjin,China,300072"],"affiliations":[{"raw_affiliation_string":"Tianjin University,School of Electrical and Information Engineering,Tianjin,China,300072","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020096491","display_name":"Chenyi Si","orcid":"https://orcid.org/0000-0002-0006-8967"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyi Si","raw_affiliation_strings":["Tianjin University,School of Electrical and Information Engineering,Tianjin,China,300072"],"affiliations":[{"raw_affiliation_string":"Tianjin University,School of Electrical and Information Engineering,Tianjin,China,300072","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5018783984"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37009577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21040","last_page":"21047"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9185000061988831,"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":0.9185000061988831,"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":0.02669999934732914,"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":0.006599999964237213,"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/robot","display_name":"Robot","score":0.6396999955177307},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5943999886512756},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.5914000272750854},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5777000188827515},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.557699978351593},{"id":"https://openalex.org/keywords/interpreter","display_name":"Interpreter","score":0.5037999749183655},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4941999912261963},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4449000060558319},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43799999356269836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7544999718666077},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6396999955177307},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5943999886512756},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.5914000272750854},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5777000188827515},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.557699978351593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5357999801635742},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5065000057220459},{"id":"https://openalex.org/C122783720","wikidata":"https://www.wikidata.org/wiki/Q183065","display_name":"Interpreter","level":2,"score":0.5037999749183655},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4941999912261963},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4449000060558319},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43799999356269836},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.4244000017642975},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4230000078678131},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4228000044822693},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.3549000024795532},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3255999982357025},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.2856000065803528},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.27320000529289246},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.2578999996185303},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247258","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334111","display_name":"Innovation Fund","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1974795838","https://openalex.org/W2005354226","https://openalex.org/W2028945152","https://openalex.org/W2064675550","https://openalex.org/W2077758943","https://openalex.org/W2103120971","https://openalex.org/W2119709400","https://openalex.org/W2128990851","https://openalex.org/W2141664020","https://openalex.org/W2142431032","https://openalex.org/W2144293566","https://openalex.org/W2161414194","https://openalex.org/W2618530766","https://openalex.org/W2950069298","https://openalex.org/W2980400095","https://openalex.org/W3001865277","https://openalex.org/W3004407706","https://openalex.org/W3210288250","https://openalex.org/W4385430679","https://openalex.org/W4390874280","https://openalex.org/W4401413802","https://openalex.org/W4404612908"],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"with":[1,50,61,120],"the":[2,23,51,62,98,127,134,146,155,159,186],"development":[3],"of":[4,97],"Large":[5],"Language":[6],"Models":[7,14],"(LLMs),":[8],"Embodied":[9],"AI":[10],"represented":[11],"by":[12,164,185],"Vision-Language-Action":[13],"(VLAs)":[15],"has":[16],"played":[17],"a":[18,92],"significant":[19],"role":[20],"in":[21,79,138],"realizing":[22],"natural":[24],"language":[25,41,56,106],"interaction":[26],"between":[27],"humans":[28],"and":[29,36,40,64,71,74,83,109,114,123,178,189],"robots.":[30],"Current":[31],"VLA":[32],"models":[33],"can":[34,171],"process":[35],"understand":[37],"visual":[38,151],"information":[39,107],"instructions,":[42,82],"while":[43],"guiding":[44],"robots":[45],"to":[46,153],"complete":[47,172],"interactive":[48],"tasks":[49,175,188],"environment":[52],"based":[53,149],"on":[54,150],"human":[55],"instructions.":[57],"However,":[58],"when":[59],"tackling":[60],"real-time":[63,72],"dynamic":[65,143],"tasks,":[66],"VLAs":[67],"have":[68],"poor":[69],"robustness":[70],"planning":[73,112,136],"adjustment":[75],"ability":[76],"against":[77],"changes":[78,130],"target":[80],"objects,":[81],"environments.":[84],"To":[85],"handle":[86],"these":[87],"limitations,":[88],"we":[89],"propose":[90],"VLIN-RL,":[91],"unified":[93],"framework":[94],"that":[95,102,168],"consists":[96],"Vision-Language":[99],"Interpreter":[100],"(VLIN)":[101],"owns":[103],"excellent":[104],"vision":[105],"understanding":[108],"advanced":[110],"task":[111,132,156],"abilities":[113],"reinforcement":[115],"learning":[116],"(RL)-based":[117],"motion":[118],"planner":[119],"enhanced":[121],"flexibility":[122],"broader":[124],"applicability.":[125],"If":[126],"environmental":[128],"state":[129],"during":[131],"execution,":[133],"RL":[135],"module":[137],"VLIN-RL":[139],"will":[140],"directly":[141],"make":[142],"adjustments":[144],"at":[145,198],"subtask":[147],"level":[148],"feedback":[152],"achieve":[154],"goals,":[157],"without":[158],"need":[160],"for":[161],"time-consuming":[162],"reprocessing":[163],"VLIN.":[165],"Experiments":[166],"demonstrate":[167],"our":[169,181],"model":[170],"multi-robot":[173],"manipulation":[174],"more":[176],"efficiently":[177],"stably.":[179],"Finally,":[180],"work":[182],"is":[183,196],"verified":[184],"pick-grasp":[187],"real":[190],"manipulators":[191],"experiments.":[192],"The":[193],"test":[194],"video":[195],"available":[197],"https://github.com/jzwsoulferryman/VLIN-RL.git.":[199]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}