{"id":"https://openalex.org/W7164019079","doi":"https://doi.org/10.48550/arxiv.2606.09337","title":"TORL-VLA: Tactile Guided Online Reinforcement Learning for Contact-Rich Manipulation","display_name":"TORL-VLA: Tactile Guided Online Reinforcement Learning for Contact-Rich Manipulation","publication_year":2026,"publication_date":"2026-06-08","ids":{"openalex":"https://openalex.org/W7164019079","doi":"https://doi.org/10.48550/arxiv.2606.09337"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.09337","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09337","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.09337","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076659062","display_name":"Huaihang Zheng","orcid":"https://orcid.org/0000-0003-0468-8132"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Huaihang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138201790","display_name":"Yi Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138230418","display_name":"Kai Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Kai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138257080","display_name":"Shenglin Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Shenglin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138226602","display_name":"Tian Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101372236","display_name":"Guozheng Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Guozheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138278234","display_name":"Xiangyu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiangyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138208056","display_name":"Yiren Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Yiren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138211516","display_name":"Si Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Si","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113278417","display_name":"Yinian Mao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mao, Yinian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138233090","display_name":"Baoxu Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Baoxu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.7605000138282776,"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":0.7605000138282776,"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":0.10599999874830246,"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"}},{"id":"https://openalex.org/T10338","display_name":"Advanced Sensor and Energy Harvesting Materials","score":0.034299999475479126,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7538999915122986},{"id":"https://openalex.org/keywords/wrench","display_name":"Wrench","score":0.5235999822616577},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.42649999260902405},{"id":"https://openalex.org/keywords/online-model","display_name":"Online model","score":0.38440001010894775},{"id":"https://openalex.org/keywords/tactile-sensor","display_name":"Tactile sensor","score":0.3815999925136566},{"id":"https://openalex.org/keywords/haptic-technology","display_name":"Haptic technology","score":0.3691999912261963},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.36800000071525574},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.33629998564720154}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7538999915122986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6945000290870667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5383999943733215},{"id":"https://openalex.org/C29302406","wikidata":"https://www.wikidata.org/wiki/Q154411","display_name":"Wrench","level":2,"score":0.5235999822616577},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4740999937057495},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.42649999260902405},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C46722567","wikidata":"https://www.wikidata.org/wiki/Q7674139","display_name":"Tactile sensor","level":3,"score":0.3815999925136566},{"id":"https://openalex.org/C152086174","wikidata":"https://www.wikidata.org/wiki/Q3030571","display_name":"Haptic technology","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C2775960376","wikidata":"https://www.wikidata.org/wiki/Q1435859","display_name":"Grippers","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C81302111","wikidata":"https://www.wikidata.org/wiki/Q2916417","display_name":"Contact force","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2870999872684479},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28519999980926514},{"id":"https://openalex.org/C136434205","wikidata":"https://www.wikidata.org/wiki/Q3437269","display_name":"Hexapod","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.2786000072956085},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.27559998631477356},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C2987654038","wikidata":"https://www.wikidata.org/wiki/Q859031","display_name":"Tactile stimuli","level":3,"score":0.27549999952316284},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2632000148296356},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2590000033378601},{"id":"https://openalex.org/C12298181","wikidata":"https://www.wikidata.org/wiki/Q7246814","display_name":"Proactive learning","level":5,"score":0.257999986410141}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.09337","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09337","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.09337","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09337","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7361952066421509}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language-Action":[0],"(VLA)":[1],"models":[2,28],"have":[3,14],"become":[4],"a":[5,64,83,96],"powerful":[6],"framework":[7,69],"for":[8,77],"robotic":[9],"manipulation,":[10,144],"and":[11,57,91,115,147,159],"recent":[12],"studies":[13],"introduced":[15],"tactile":[16,72],"or":[17],"force":[18],"feedback":[19,73],"into":[20],"VLAs":[21],"to":[22,50,87,103,131],"address":[23],"contact-rich":[24,78,140],"tasks.":[25],"However,":[26],"these":[27],"are":[29],"typically":[30],"deployed":[31],"as":[32,53,162,164],"offline":[33],"policies.":[34],"When":[35],"contact":[36,55],"conditions":[37],"shift":[38],"from":[39,111,127],"the":[40,43,105],"training":[41],"distribution,":[42],"policy":[44,75],"cannot":[45],"perform":[46],"online":[47,66,98],"adaptation,":[48],"leading":[49],"problems":[51],"such":[52],"inappropriate":[54],"forces":[56],"inefficient":[58],"retries.":[59],"Therefore,":[60],"we":[61,118],"propose":[62],"TORL-VLA,":[63],"tactile-guided":[65],"reinforcement":[67],"learning":[68,110],"that":[70,123,151],"couples":[71],"with":[74],"refinement":[76],"manipulation.":[79],"Our":[80],"method":[81],"introduces":[82],"tactile-derived":[84],"wrench-aware":[85],"VLA":[86],"predict":[88],"reference":[89,106],"actions":[90,133],"future":[92],"wrench":[93],"sequences,":[94],"while":[95],"lightweight":[97],"RL":[99],"module":[100],"is":[101],"used":[102],"refine":[104],"actions.":[107],"To":[108],"stabilize":[109],"mixed":[112],"exploratory":[113],"policy-generated":[114,132],"human-intervention":[116],"data,":[117],"introduce":[119],"an":[120],"intervention-censored":[121],"critic":[122],"prevents":[124],"post-intervention":[125],"success":[126,154],"being":[128],"wrongly":[129],"credited":[130],"preceding":[134],"intervention.":[135],"Real-robot":[136],"experiments":[137],"on":[138],"long-horizon":[139],"tasks,":[141],"including":[142],"latch":[143],"coffee-cup":[145],"placement,":[146],"egg":[148],"handling,":[149],"show":[150],"TORL-VLA":[152],"improves":[153],"rates":[155],"at":[156],"both":[157],"subtask":[158],"full-task":[160],"levels,":[161],"well":[163],"time-bounded":[165],"execution":[166],"efficiency":[167],"over":[168],"strong":[169],"baselines.":[170],"Project":[171],"page:":[172],"https://torl-vla.github.io/":[173]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-10T00:00:00"}