{"id":"https://openalex.org/W7203798043","doi":"https://doi.org/10.48550/arxiv.2608.17323","title":"ORPA: Online Residual Policy Adaptation for Robot Manipulation Control with Human Feedback","display_name":"ORPA: Online Residual Policy Adaptation for Robot Manipulation Control with Human Feedback","publication_year":2026,"publication_date":"2026-08-18","ids":{"openalex":"https://openalex.org/W7203798043","doi":"https://doi.org/10.48550/arxiv.2608.17323"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.17323","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.17323","pdf_url":"https://arxiv.org/pdf/2608.17323","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.17323","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099022396","display_name":"Muhammad A. Muttaqien","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Muttaqien, Muhammad A.","raw_affiliation_strings":["Embodied AI Research Team National Institute of AIST Tokyo , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Embodied AI Research Team National Institute of AIST Tokyo , Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047994804","display_name":"Tomohiro Motoda","orcid":"https://orcid.org/0000-0003-3339-6147","observed_orcids":["https://orcid.org/0000-0003-3339-6147"]},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Motoda, Tomohiro","raw_affiliation_strings":["Embodied AI Research Team National Institute of AIST Tokyo , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Embodied AI Research Team National Institute of AIST Tokyo , Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102871528","display_name":"Ryo Hanai","orcid":"https://orcid.org/0000-0003-4216-4866","observed_orcids":["https://orcid.org/0000-0003-4216-4866"]},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hanai, Ryo","raw_affiliation_strings":["Embodied AI Research Team National Institute of AIST Tokyo , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Embodied AI Research Team National Institute of AIST Tokyo , Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068377110","display_name":"Yukiyasu Domae","orcid":"https://orcid.org/0000-0002-1366-9657","observed_orcids":["https://orcid.org/0000-0002-1366-9657"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Domae, Yukiyasu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":0.9384999871253967,"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":0.9384999871253967,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.06019999831914902,"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"}},{"id":"https://openalex.org/T10982","display_name":"Motor Control and Adaptation","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/human-feedback","display_name":"human feedback","score":0.890999972820282},{"id":"https://openalex.org/keywords/imitation-learning","display_name":"imitation learning","score":0.6809999942779541},{"id":"https://openalex.org/keywords/distribution-shift","display_name":"distribution shift","score":0.7129999995231628}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.736299991607666},{"id":"https://openalex.org/C17816587","wikidata":"https://www.wikidata.org/wiki/Q1501872","display_name":"Inverse kinematics","level":3,"score":0.578499972820282},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5580000281333923},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5246999859809875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47540000081062317},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4196000099182129},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C187523126","wikidata":"https://www.wikidata.org/wiki/Q17098330","display_name":"Inverse dynamics","level":3,"score":0.3506999909877777},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.321399986743927},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.31459999084472656},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.2989000082015991},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C172707124","wikidata":"https://www.wikidata.org/wiki/Q423488","display_name":"Actuator","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.2842000126838684},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2827000021934509},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2773999869823456},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.27399998903274536},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.25369998812675476},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.2524999976158142},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25220000743865967}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.17323","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.17323","pdf_url":"https://arxiv.org/pdf/2608.17323","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.17323","doi":"https://doi.org/10.48550/arxiv.2608.17323","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.17323","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.17323","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.17323","pdf_url":"https://arxiv.org/pdf/2608.17323","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311508","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203798043.pdf","grobid_xml":"https://content.openalex.org/works/W7203798043.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4396786887"],"related_works":["https://openalex.org/W7161830382","https://openalex.org/W7103159453","https://openalex.org/W3204569274","https://openalex.org/W7214346189","https://openalex.org/W7131471832","https://openalex.org/W4416749370","https://openalex.org/W7131633476","https://openalex.org/W4415089933","https://openalex.org/W7223233714","https://openalex.org/W7162755431"],"abstract_inverted_index":{"Robotic":[0],"manipulation":[1,113],"policies":[2,133],"trained":[3],"via":[4],"imitation":[5],"learning,":[6],"such":[7],"as":[8],"Action":[9],"Chunking":[10],"with":[11,83],"Transformers":[12],"(ACT),":[13],"can":[14],"achieve":[15],"strong":[16],"performance":[17],"under":[18],"ideal":[19],"conditions":[20],"but":[21],"often":[22],"remain":[23],"sensitive":[24],"to":[25,99,130],"small":[26,127],"execution":[27],"errors":[28],"and":[29,39,46,124,134],"distribution":[30],"shifts.":[31],"Correcting":[32],"these":[33],"failures":[34],"typically":[35],"requires":[36],"dataset":[37],"aggregation":[38],"full-policy":[40],"retraining,":[41],"which":[42],"is":[43],"computationally":[44],"expensive":[45],"unsuitable":[47],"for":[48],"real-time":[49],"deployment.":[50],"In":[51],"this":[52],"work,":[53],"we":[54],"propose":[55],"Online":[56],"Residual":[57],"Policy":[58],"Adaptation":[59],"(ORPA),":[60],"a":[61,79,84,109],"framework":[62],"that":[63,88],"enables":[64],"immediate,":[65],"feedback-driven":[66],"correction":[67],"of":[68,111],"robot":[69],"actions":[70],"without":[71],"modifying":[72],"the":[73,97,116],"underlying":[74],"policy":[75,82],"parameters.":[76],"ORPA":[77,107],"augments":[78],"pretrained":[80],"control":[81,132],"lightweight,":[85],"feedback-conditioned":[86],"module":[87],"predicts":[89],"residual":[90],"adjustments":[91],"directly":[92],"in":[93,121],"joint":[94],"space,":[95],"allowing":[96],"system":[98],"adapt":[100],"its":[101],"behavior":[102],"at":[103],"runtime.":[104],"We":[105],"evaluate":[106],"on":[108],"set":[110],"precision-sensitive":[112],"tasks":[114],"using":[115],"ALOHA":[117],"platform,":[118],"demonstrating":[119],"improvements":[120],"success":[122],"rate":[123],"recovery":[125],"from":[126],"perturbations":[128],"compared":[129],"baseline":[131],"rule-based":[135],"inverse":[136],"kinematics":[137],"corrections.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-20T00:00:00"}