{"id":"https://openalex.org/W4383066282","doi":"https://doi.org/10.1109/icra48891.2023.10160889","title":"Failure-aware Policy Learning for Self-assessable Robotics Tasks","display_name":"Failure-aware Policy Learning for Self-assessable Robotics Tasks","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383066282","doi":"https://doi.org/10.1109/icra48891.2023.10160889"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","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/A5062930488","display_name":"Kechun Xu","orcid":"https://orcid.org/0000-0002-3632-917X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kechun Xu","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000349453","display_name":"Runjian Chen","orcid":"https://orcid.org/0000-0003-0519-496X"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Runjian Chen","raw_affiliation_strings":["The University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100929934","display_name":"Shuqi Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuqi Zhao","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022254711","display_name":"Zizhang Li","orcid":"https://orcid.org/0000-0001-7818-5162"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zizhang Li","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100337974","display_name":"Hongxiang Yu","orcid":"https://orcid.org/0000-0003-0954-0348"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongxiang Yu","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074507207","display_name":"Ci Chen","orcid":"https://orcid.org/0000-0003-0813-5543"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ci Chen","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371992","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0002-0981-935X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Wang","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019081110","display_name":"Rong Xiong","orcid":"https://orcid.org/0000-0001-9318-9014"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Xiong","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5062930488"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.5289,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70993555,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9544","last_page":"9550"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9901999831199646,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9901999831199646,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.984499990940094,"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":0.9797000288963318,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7790175676345825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6281182765960693},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.625275194644928},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6197452545166016},{"id":"https://openalex.org/keywords/memorization","display_name":"Memorization","score":0.6017875671386719},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5532745122909546},{"id":"https://openalex.org/keywords/affordance","display_name":"Affordance","score":0.5504655241966248},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5448070764541626},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.528436005115509},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5064979791641235},{"id":"https://openalex.org/keywords/summit","display_name":"Summit","score":0.4115288257598877},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.27523303031921387},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08844643831253052}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7790175676345825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6281182765960693},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.625275194644928},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6197452545166016},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.6017875671386719},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5532745122909546},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.5504655241966248},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5448070764541626},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.528436005115509},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5064979791641235},{"id":"https://openalex.org/C2778848561","wikidata":"https://www.wikidata.org/wiki/Q207326","display_name":"Summit","level":2,"score":0.4115288257598877},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27523303031921387},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08844643831253052},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C100970517","wikidata":"https://www.wikidata.org/wiki/Q52107","display_name":"Physical geography","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10160889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2543133814","display_name":null,"funder_award_id":"2021ZD0114500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1499669280","https://openalex.org/W2053850238","https://openalex.org/W2064675550","https://openalex.org/W2108598243","https://openalex.org/W2121658992","https://openalex.org/W2145339207","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2417786368","https://openalex.org/W2528489519","https://openalex.org/W2586067474","https://openalex.org/W2734960757","https://openalex.org/W2902125520","https://openalex.org/W2909414402","https://openalex.org/W2949475445","https://openalex.org/W2962764167","https://openalex.org/W2963276097","https://openalex.org/W2963523627","https://openalex.org/W2964067469","https://openalex.org/W2966271811","https://openalex.org/W2968104655","https://openalex.org/W2995089744","https://openalex.org/W2997289589","https://openalex.org/W3000916453","https://openalex.org/W3023565369","https://openalex.org/W3035624836","https://openalex.org/W3096784327","https://openalex.org/W3100396494","https://openalex.org/W3115737827","https://openalex.org/W3130934167","https://openalex.org/W3163844809","https://openalex.org/W3174796182","https://openalex.org/W3176770340","https://openalex.org/W3201276757","https://openalex.org/W4214717370","https://openalex.org/W4224057949","https://openalex.org/W4287078276","https://openalex.org/W4287123016","https://openalex.org/W4287370827","https://openalex.org/W4287629996","https://openalex.org/W4308900803","https://openalex.org/W6716474083","https://openalex.org/W6717230150","https://openalex.org/W6730641667","https://openalex.org/W6733118196","https://openalex.org/W6756303580","https://openalex.org/W6756908582","https://openalex.org/W6777873367","https://openalex.org/W6784607570","https://openalex.org/W6784630725","https://openalex.org/W6795721140","https://openalex.org/W6797007026","https://openalex.org/W6797010411","https://openalex.org/W6798316476","https://openalex.org/W6803464670","https://openalex.org/W7033622795"],"related_works":["https://openalex.org/W1982074779","https://openalex.org/W4241376597","https://openalex.org/W1972718289","https://openalex.org/W1791514435","https://openalex.org/W3203904831","https://openalex.org/W630050097","https://openalex.org/W4246070377","https://openalex.org/W2346831895","https://openalex.org/W2315316873","https://openalex.org/W4308629216"],"abstract_inverted_index":{"Self-assessment":[0],"rules":[1],"play":[2],"an":[3],"essential":[4],"role":[5],"in":[6],"safe":[7],"and":[8,50,69,124],"effective":[9],"real-world":[10],"robotic":[11],"applications,":[12],"which":[13,61],"verify":[14],"the":[15,18,28,40,47,54,63,66,70,80,86,109,114,121,132,158,171],"feasibility":[16],"of":[17,117],"selected":[19,41],"action":[20,42],"before":[21],"actual":[22],"execution.":[23],"But":[24],"how":[25],"to":[26,31,95,129],"utilize":[27],"self-assessment":[29,48,67,115],"results":[30,68,116],"re-choose":[32,51],"actions":[33,159],"remains":[34],"a":[35,101,163],"challenge.":[36],"Previous":[37],"methods":[38],"eliminate":[39],"evaluated":[43],"as":[44,120],"failed":[45],"by":[46,99,112,153],"rules,":[49],"one":[52],"with":[53,148],"next-highest":[55],"affordance":[56],"(i.e.":[57],"process-of-elimination":[58,172],"strategy":[59],"[1]),":[60],"ignores":[62],"dependency":[64,76,98],"between":[65],"remaining":[71,87],"untried":[72],"actions.":[73,89],"However,":[74],"this":[75,91,97],"is":[77],"important":[78],"since":[79],"previous":[81,118,133],"failures":[82,119],"might":[83],"help":[84],"trim":[85],"over-estimated":[88],"In":[90],"paper,":[92],"we":[93],"set":[94],"investigate":[96],"learning":[100,162],"failure-aware":[102,110,164],"policy.":[103],"We":[104],"propose":[105],"two":[106],"architectures":[107],"for":[108],"policy":[111,165],"representing":[113],"variable":[122],"state,":[123],"leveraging":[125],"recurrent":[126],"neural":[127],"networks":[128],"implicitly":[130],"memorize":[131],"failures.":[134],"Experiments":[135],"conducted":[136],"on":[137],"three":[138],"tasks":[139],"demonstrate":[140],"that":[141],"our":[142],"method":[143],"can":[144,166],"achieve":[145,167],"better":[146,168],"performances":[147],"higher":[149],"task":[150],"success":[151],"rates":[152],"less":[154],"trials.":[155],"Moreover,":[156],"when":[157],"are":[160],"correlated,":[161],"performance":[169],"than":[170],"strategy.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}