{"id":"https://openalex.org/W7214744232","doi":"https://doi.org/10.48550/arxiv.2609.35575","title":"F4R: Failure-Driven Recognition, Reconstruction, Refinement, and Redeployment for Continual Robot Self-Improvement","display_name":"F4R: Failure-Driven Recognition, Reconstruction, Refinement, and Redeployment for Continual Robot Self-Improvement","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214744232","doi":"https://doi.org/10.48550/arxiv.2609.35575"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.35575","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35575","pdf_url":"https://arxiv.org/pdf/2609.35575","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":null,"license_id":null,"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/2609.35575","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153514341","display_name":"Zhuoyuan Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yu, Zhuoyuan","raw_affiliation_strings":["Nanyang Technological University , 2 Dexmal ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University , 2 Dexmal ,","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153464781","display_name":"Jiacheng Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Jiacheng","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153476349","display_name":"Tianle Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Tianle","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153432922","display_name":"Yihua Ren","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Yihua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101782326","display_name":"Peng Fei Yu","orcid":"https://orcid.org/0000-0001-9986-0438","observed_orcids":["https://orcid.org/0000-0001-9986-0438"]},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu, Peng","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153429779","display_name":"Chen Bai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153411092","display_name":"Ziheng Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Ziheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153468007","display_name":"Yufei Jia","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Yufei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004534196","display_name":"Jindou Jia","orcid":"https://orcid.org/0000-0002-1866-6180","observed_orcids":["https://orcid.org/0000-0002-1866-6180"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jia, Jindou","raw_affiliation_strings":["Nanyang Technological University , 2 Dexmal ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University , 2 Dexmal ,","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153485978","display_name":"Yuhang Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhang, Yuhang","raw_affiliation_strings":["Nanyang Technological University , 2 Dexmal ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University , 2 Dexmal ,","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153457760","display_name":"Xinrui Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xinrui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153537671","display_name":"Shang Yujing","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yujing, Shang","raw_affiliation_strings":["Nanyang Technological University , 2 Dexmal ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University , 2 Dexmal ,","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153433848","display_name":"Yuxiang Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yuxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153471598","display_name":"Chuhao Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhou, Chuhao","raw_affiliation_strings":["Nanyang Technological University , 2 Dexmal ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University , 2 Dexmal ,","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153448527","display_name":"Tiancai Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Tiancai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005666034","display_name":"Jianfei Yang","orcid":"https://orcid.org/0000-0002-8075-0439","observed_orcids":["https://orcid.org/0000-0002-8075-0439"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yang, Jianfei","raw_affiliation_strings":["Nanyang Technological University , 2 Dexmal ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University , 2 Dexmal ,","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8988999724388123,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8988999724388123,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.09889999777078629,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.000699999975040555,"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/vision-language-action-models","display_name":"vision-language-action models","score":0.824999988079071},{"id":"https://openalex.org/keywords/fault-diagnosis","display_name":"fault diagnosis","score":0.5329999923706055},{"id":"https://openalex.org/keywords/sim-to-real-transfer","display_name":"sim-to-real transfer","score":0.6340000033378601},{"id":"https://openalex.org/keywords/manipulation-tasks","display_name":"manipulation tasks","score":0.6069999933242798},{"id":"https://openalex.org/keywords/out-of-distribution-generalization","display_name":"out-of-distribution generalization","score":0.7739999890327454},{"id":"https://openalex.org/keywords/closed-loop-learning","display_name":"closed-loop learning","score":0.6129999756813049}],"concepts":[{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6865000128746033},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6308000087738037},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6287999749183655},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5740000009536743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5688999891281128},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.44909998774528503},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42800000309944153},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3714999854564667},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3231000006198883},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2874000072479248},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.28700000047683716},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2757999897003174},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.35575","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35575","pdf_url":"https://arxiv.org/pdf/2609.35575","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.35575","doi":"https://doi.org/10.48550/arxiv.2609.35575","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.35575","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.35575","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35575","pdf_url":"https://arxiv.org/pdf/2609.35575","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214744232.pdf","grobid_xml":"https://content.openalex.org/works/W7214744232.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W2009422376","https://openalex.org/W4402354170","https://openalex.org/W4414079285","https://openalex.org/W4414674749","https://openalex.org/W4416780398"],"related_works":["https://openalex.org/W7138193351","https://openalex.org/W7204574572","https://openalex.org/W7123579611","https://openalex.org/W7167093849","https://openalex.org/W7160902854","https://openalex.org/W7140755151","https://openalex.org/W4414818136","https://openalex.org/W4413947061","https://openalex.org/W7093105366","https://openalex.org/W7214044120"],"abstract_inverted_index":{"The":[0,104,122],"real-world":[1,31,67,176],"performance":[2],"of":[3,14,21,33],"current":[4],"vision-language-action":[5],"models":[6],"is":[7,27,40,106,125],"fundamentally":[8],"constrained":[9],"by":[10,114,166],"the":[11,98,119,137,161],"limited":[12],"coverage":[13],"expert":[15],"demonstrations":[16,32],"and":[17,45,81,101,140,155],"their":[18],"insufficient":[19],"understanding":[20],"physical":[22,102],"interactions.":[23],"A":[24],"common":[25],"remedy":[26],"to":[28,47,78],"collect":[29],"additional":[30,175],"newly":[34,129],"encountered":[35],"failures.":[36],"However,":[37],"this":[38,51],"process":[39],"costly,":[41],"inefficient,":[42],"potentially":[43],"unsafe,":[44],"difficult":[46],"scale.":[48],"To":[49],"address":[50],"challenge,":[52],"we":[53],"propose":[54],"Failure":[55],"for":[56],"Rising":[57],"(F4R),":[58],"a":[59],"failure-driven":[60],"real-to-sim-to-real":[61],"closed-loop":[62],"learning":[63,117,141],"framework":[64],"that":[65,96,150],"converts":[66],"failures":[68,83,131],"into":[69,136],"targeted":[70,115],"policy":[71,105,124],"improvement.":[72],"F4R":[73,151],"first":[74],"uses":[75],"an":[76,91],"agent":[77],"automatically":[79],"identify":[80],"diagnose":[82],"from":[84],"rollouts.":[85],"It":[86],"reconstructs":[87],"each":[88],"failure":[89],"as":[90],"interactive,":[92],"object-centric":[93],"table-top":[94],"environment":[95],"preserves":[97],"task-relevant":[99],"spatial":[100],"conditions.":[103],"then":[107],"refined":[108],"through":[109],"failure-conditioned":[110],"sim-real":[111],"co-training":[112],"followed":[113],"reinforcement":[116],"in":[118],"reconstructed":[120],"environments.":[121],"improved":[123],"subsequently":[126],"redeployed,":[127],"while":[128],"observed":[130],"are":[132],"continuously":[133],"fed":[134],"back":[135],"next":[138],"reconstruction":[139],"cycle.":[142],"Real-world":[143],"evaluations":[144],"on":[145],"four":[146],"manipulation":[147],"tasks":[148],"show":[149],"achieves":[152],"93.75%":[153],"In-Distribution":[154],"90.0%":[156],"Out-of-Distribution":[157],"(OOD)":[158],"success,":[159],"outperforming":[160],"budget-matched":[162],"Targeted":[163],"BC":[164],"baseline":[165],"18.75":[167],"percentage":[168],"points":[169],"under":[170],"OOD":[171],"conditions":[172],"without":[173],"collecting":[174],"corrective":[177],"demonstrations.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}