{"id":"https://openalex.org/W4416748668","doi":"https://doi.org/10.1109/iros60139.2025.11246723","title":"ARC: Robots Adaptive Risk-aware Robust Control via Distributional Reinforcement Learning","display_name":"ARC: Robots Adaptive Risk-aware Robust Control via Distributional Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748668","doi":"https://doi.org/10.1109/iros60139.2025.11246723"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5101806403","display_name":"Junlong Wu","orcid":"https://orcid.org/0000-0002-3270-3865"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junlong Wu","raw_affiliation_strings":["Tsinghua University,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041725554","display_name":"Yi Cheng","orcid":"https://orcid.org/0000-0002-0135-5546"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Cheng","raw_affiliation_strings":["Tsinghua University,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119011911","display_name":"Hang Liu","orcid":"https://orcid.org/0009-0001-2928-1040"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Hang Liu","raw_affiliation_strings":["Tsinghua University,Beijing,China,100084","University of Michigan,Ann Arbor,MI,USA,48109"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"University of Michigan,Ann Arbor,MI,USA,48109","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076885280","display_name":"Houde Liu","orcid":"https://orcid.org/0000-0002-7314-3366"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Houde Liu","raw_affiliation_strings":["Tsinghua University,Beijing,China,100084","University of Michigan,Ann Arbor,MI,USA,48109"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"University of Michigan,Ann Arbor,MI,USA,48109","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30372232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10656","last_page":"10663"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.8427000045776367,"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"}},"topics":[{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.8427000045776367,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.06930000334978104,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.01360000018030405,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6887999773025513},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.632099986076355},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.5978999733924866},{"id":"https://openalex.org/keywords/robust-control","display_name":"Robust control","score":0.48330000042915344},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4496000111103058},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.44609999656677246},{"id":"https://openalex.org/keywords/adaptive-control","display_name":"Adaptive control","score":0.4392000138759613},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.43709999322891235}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6887999773025513},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.632099986076355},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.5978999733924866},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5468000173568726},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.48330000042915344},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4496000111103058},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.4392000138759613},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.43709999322891235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40369999408721924},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.38339999318122864},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.36489999294281006},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3458999991416931},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3431999981403351},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.3073999881744385},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2989000082015991},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2883000075817108},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.27410000562667847},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.26930001378059387}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2053984877","https://openalex.org/W2055921164","https://openalex.org/W2101421095","https://openalex.org/W2169206416","https://openalex.org/W2765302304","https://openalex.org/W2788200022","https://openalex.org/W2951360122","https://openalex.org/W2977518448","https://openalex.org/W3015082424","https://openalex.org/W3093922502","https://openalex.org/W3107153805","https://openalex.org/W3175254947","https://openalex.org/W3176539729","https://openalex.org/W4382981485","https://openalex.org/W4383108274","https://openalex.org/W4392763392","https://openalex.org/W4394674699","https://openalex.org/W4394872716","https://openalex.org/W4401415792","https://openalex.org/W4401416328","https://openalex.org/W4401416919","https://openalex.org/W4402354017","https://openalex.org/W4402354114","https://openalex.org/W4402354142","https://openalex.org/W4403741606","https://openalex.org/W4405786988"],"related_works":[],"abstract_inverted_index":{"Locomotion":[0],"in":[1,101,142],"robots":[2,22,152],"remains":[3],"an":[4],"unsolved":[5],"challenge,":[6],"particularly":[7],"for":[8,20,59,120,131],"those":[9],"with":[10],"complex":[11],"structures":[12],"and":[13,30,36,70,125],"dynamic":[14],"environments.":[15,61],"Consequently,":[16],"the":[17,51,56,65,75,115,175],"control":[18],"systems":[19],"such":[21],"must":[23],"place":[24],"greater":[25],"emphasis":[26],"on":[27,87,148,170],"risk":[28,44,57,98,143],"mitigation":[29],"safety":[31],"considerations":[32],"to":[33,53,73,103,164],"ensure":[34],"reliable":[35],"stable":[37],"operation.":[38],"Existing":[39],"studies":[40],"have":[41,153],"explicitly":[42],"incorporated":[43],"factors":[45],"into":[46],"policy":[47],"training,":[48],"but":[49],"lacked":[50],"ability":[52],"adaptively":[54],"adjust":[55],"sensitivity":[58,99],"hazardous":[60],"This":[62,135],"deficiency":[63],"impacts":[64],"agent\u2019s":[66],"exploration":[67],"during":[68],"training":[69],"thus":[71],"fails":[72],"select":[74],"optimal":[76],"action.":[77],"We":[78],"innovatively":[79],"introduce":[80],"Adaptive":[81],"Risk-aware":[82],"Control":[83],"(ARC)":[84],"policies":[85],"based":[86],"Distributional":[88],"Reinforcement":[89],"Learning":[90],"(Dist.RL),":[91],"a":[92,139,149,171],"novel":[93],"framework":[94],"that":[95,155],"dynamically":[96],"adjusts":[97],"levels":[100],"response":[102],"changing":[104],"environmental":[105,123],"conditions.":[106],"Our":[107],"approach":[108],"uniquely":[109],"integrates":[110],"two":[111],"key":[112],"components:":[113],"(1)":[114],"Inter":[116],"Quartile":[117],"Range":[118],"(IQR)":[119],"quantifying":[121],"intrinsic":[122],"uncertainty,":[124],"(2)":[126],"Random":[127],"Network":[128],"Distillation":[129],"(RND)":[130],"evaluating":[132],"parameter":[133],"uncertainty.":[134],"dual-mechanism":[136],"architecture":[137],"represents":[138],"significant":[140],"advancement":[141],"assessment":[144],"methodologies.":[145],"Simulations":[146],"conducted":[147],"variety":[150],"of":[151,178],"demonstrated":[154],"our":[156,179],"method":[157],"achieves":[158],"significantly":[159],"more":[160],"robust":[161],"performance":[162],"compared":[163],"other":[165],"approaches.":[166],"Furthermore,":[167],"sim2real":[168],"validation":[169],"humanoid":[172],"robot":[173],"confirms":[174],"practical":[176],"viability":[177],"approach.":[180]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}