{"id":"https://openalex.org/W4415970868","doi":"https://doi.org/10.1109/lra.2025.3629984","title":"A Hierarchical Vision-Language and Reinforcement Learning Framework for Robotic Task and Motion Planning in Collaborative Manipulation","display_name":"A Hierarchical Vision-Language and Reinforcement Learning Framework for Robotic Task and Motion Planning in Collaborative Manipulation","publication_year":2025,"publication_date":"2025-11-06","ids":{"openalex":"https://openalex.org/W4415970868","doi":"https://doi.org/10.1109/lra.2025.3629984"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2025.3629984","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3629984","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5003736415","display_name":"Jiadong Zhang","orcid":"https://orcid.org/0009-0004-1042-5421"},"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":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0004-1042-5421","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057898837","display_name":"Chaoxu Mu","orcid":"https://orcid.org/0000-0003-1055-9513"},"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":"Chaoxu Mu","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-1055-9513","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053112608","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-3238-745X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xu","raw_affiliation_strings":["School of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-3238-745X","affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028426177","display_name":"Lei Ren","orcid":"https://orcid.org/0000-0001-6346-6930"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Ren","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6346-6930","affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7779,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77311211,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"11","issue":"1","first_page":"65","last_page":"72"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8442000150680542,"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":0.8442000150680542,"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":0.06109999865293503,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.02410000003874302,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8112000226974487},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.7789000272750854},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6816999912261963},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6711000204086304},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.6312999725341797},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.619700014591217},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5156000256538391},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.486299991607666}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8112000226974487},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.7789000272750854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.708299994468689},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6816999912261963},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6711000204086304},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.6312999725341797},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.619700014591217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5726000070571899},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5156000256538391},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.486299991607666},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4415000081062317},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3547999858856201},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3095000088214874},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30219998955726624},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.2874999940395355},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.2662000060081482},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.2635999917984009},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.26260000467300415}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3629984","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3629984","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2119709400","https://openalex.org/W2161414194","https://openalex.org/W2980400095","https://openalex.org/W3001865277","https://openalex.org/W3004407706","https://openalex.org/W4313131480","https://openalex.org/W4323022443","https://openalex.org/W4367663367","https://openalex.org/W4380606960","https://openalex.org/W4384518901","https://openalex.org/W4385430679","https://openalex.org/W4388273911","https://openalex.org/W4390874280","https://openalex.org/W4401413802","https://openalex.org/W4401500831","https://openalex.org/W4404612908"],"related_works":[],"abstract_inverted_index":{"Vision-language-action":[0],"models":[1],"(VLAs)":[2],"use":[3],"an":[4],"end-to-end":[5],"learning":[6,76],"architecture,":[7],"which":[8],"can":[9,132],"realize":[10],"the":[11,25,59,88,95,106,115,119],"integration":[12],"of":[13,58],"visual":[14,111],"perception,":[15],"semantic":[16],"understanding":[17,68],"and":[18,34,44,69,74,84,135,151],"motion":[19,79],"control.":[20],"However,":[21],"when":[22],"tackling":[23],"with":[24,81],"dynamic":[26,103,148],"or":[27],"long-horizon":[28,152],"tasks,":[29],"VLAs":[30],"have":[31],"poor":[32],"robustness":[33],"real-time":[35],"adjustment":[36],"ability":[37],"against":[38],"changes":[39,91],"in":[40,98],"target":[41],"objects,":[42],"instructions,":[43],"environments.":[45],"To":[46],"handles":[47],"these":[48],"limitations,":[49],"we":[50],"propose":[51],"VL-RL,":[52],"a":[53],"hierarchical":[54],"framework":[55],"that":[56,63,130],"consists":[57],"vision-language":[60],"(VL)":[61],"planner":[62,80,97],"owns":[64],"excellent":[65],"VL":[66,126],"information":[67,123],"high-level":[70],"task":[71,93,116],"planning":[72],"abilities":[73],"reinforcement":[75],"(RL)-based":[77],"low-level":[78],"enhanced":[82],"flexibility":[83],"broader":[85],"applicability.":[86],"If":[87],"environmental":[89],"state":[90],"during":[92],"execution,":[94],"RL":[96],"VL-RL":[99,131],"will":[100],"directly":[101],"make":[102],"adjustments":[104],"at":[105],"subtask":[107],"level":[108],"based":[109],"on":[110],"feedback":[112],"to":[113],"achieve":[114],"goals,":[117],"without":[118],"need":[120],"for":[121],"time-consuming":[122],"processing":[124],"from":[125],"planner.":[127],"Experiments":[128],"demonstrate":[129],"more":[133],"efficiently":[134],"stably":[136],"complete":[137],"dual-robot":[138],"collaborative":[139],"manipulation":[140],"tasks.":[141,154],"Finally,":[142],"our":[143],"work":[144],"is":[145],"verified":[146],"by":[147],"grasping":[149],"tasks":[150],"complex":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-06T00:00:00"}
