{"id":"https://openalex.org/W3150249871","doi":"https://doi.org/10.1109/iros51168.2021.9636467","title":"Robust Feedback Motion Policy Design Using Reinforcement Learning on a 3D Digit Bipedal Robot","display_name":"Robust Feedback Motion Policy Design Using Reinforcement Learning on a 3D Digit Bipedal Robot","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W3150249871","doi":"https://doi.org/10.1109/iros51168.2021.9636467","mag":"3150249871"},"language":"en","primary_location":{"id":"doi:10.1109/iros51168.2021.9636467","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636467","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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/A5025408291","display_name":"Guillermo A. Castillo","orcid":"https://orcid.org/0000-0003-1326-5836"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Guillermo A. Castillo","raw_affiliation_strings":["Electrical and Computer Engineering, Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033842396","display_name":"Bowen Weng","orcid":"https://orcid.org/0000-0002-7868-9747"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bowen Weng","raw_affiliation_strings":["Electrical and Computer Engineering, Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038039971","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-4184-8855"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["SUSTech Institute of Robotics, Southern University of Science and Technology (SUSTech), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SUSTech Institute of Robotics, Southern University of Science and Technology (SUSTech), China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069228447","display_name":"Ayonga Hereid","orcid":"https://orcid.org/0000-0002-4156-2013"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ayonga Hereid","raw_affiliation_strings":["Mechanical and Aerospace Engineering, Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mechanical and Aerospace Engineering, Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025408291"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":20.4154,"has_fulltext":false,"cited_by_count":67,"citation_normalized_percentile":{"value":0.99796074,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5136","last_page":"5143"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9970999956130981,"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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.9955999851226807,"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":0.7512584924697876},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6777064800262451},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6768062114715576},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6525091528892517},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5016086101531982},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49153122305870056},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.43346428871154785},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.41393816471099854},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.4116475582122803},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.23232698440551758},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20084848999977112}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7512584924697876},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6777064800262451},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6768062114715576},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6525091528892517},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5016086101531982},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49153122305870056},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.43346428871154785},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.41393816471099854},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.4116475582122803},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.23232698440551758},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20084848999977112},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros51168.2021.9636467","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636467","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.47999998927116394,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2098523767","https://openalex.org/W2158782408","https://openalex.org/W2167210454","https://openalex.org/W2173248099","https://openalex.org/W2239166089","https://openalex.org/W2413990562","https://openalex.org/W2465284394","https://openalex.org/W2593996575","https://openalex.org/W2596367596","https://openalex.org/W2737825825","https://openalex.org/W2774367037","https://openalex.org/W2911251203","https://openalex.org/W2919616510","https://openalex.org/W2951815129","https://openalex.org/W2963864421","https://openalex.org/W2967815054","https://openalex.org/W2968717280","https://openalex.org/W2972798201","https://openalex.org/W3003647188","https://openalex.org/W3024855617","https://openalex.org/W3091173443","https://openalex.org/W3093922502","https://openalex.org/W3096243380","https://openalex.org/W3104876774","https://openalex.org/W3106249594","https://openalex.org/W3108412994","https://openalex.org/W3113883030","https://openalex.org/W3154435961","https://openalex.org/W3206762371","https://openalex.org/W6684921986","https://openalex.org/W6735641298","https://openalex.org/W6778026261","https://openalex.org/W6784993256","https://openalex.org/W6786939513"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W4220829754","https://openalex.org/W2351343564","https://openalex.org/W2170052867","https://openalex.org/W2171010636"],"abstract_inverted_index":{"In":[0],"this":[1,192],"paper,":[2],"a":[3,29,53,109,197],"hierarchical":[4],"and":[5,14,49,56,66,91,177],"robust":[6,48],"framework":[7,45,82],"for":[8],"learning":[9,35,73,110,122,131],"bipedal":[10],"locomotion":[11],"is":[12,132,193,200],"presented":[13],"successfully":[15,157,202],"implemented":[16],"on":[17],"the":[18,34,44,60,64,68,72,81,84,87,93,96,100,118,121,126,130,139,143,151,159,165,183,187,194,204],"3D":[19],"biped":[20],"robot":[21,119,144,167,206],"Digit":[22,166,205],"built":[23],"by":[24,156],"Agility":[25],"Robotics.":[26],"We":[27,106],"propose":[28],"cascade-structure":[30],"controller":[31,102],"that":[32,112],"combines":[33],"process":[36,123],"with":[37,52,103],"intuitive":[38],"feedback":[39,78],"regulations.":[40],"This":[41],"design":[42,65],"allows":[43],"to":[46,124,138,164,203],"realize":[47],"stable":[50],"walking":[51,89,171],"reduced-dimensional":[54],"state":[55,128,141],"action":[57],"spaces":[58],"of":[59,71,77,86,95,99,117,129,142,153,189],"policy,":[61],"significantly":[62],"simplifying":[63],"increasing":[67],"sampling":[69],"efficiency":[70],"method.":[74],"The":[75],"inclusion":[76],"regulation":[79],"into":[80],"improves":[83],"robustness":[85],"learned":[88,160],"gait":[90],"ensures":[92],"success":[94],"sim-to-real":[97],"transfer":[98],"proposed":[101],"minimal":[104],"tuning.":[105],"specifically":[107],"present":[108],"pipeline":[111],"considers":[113],"hardware-feasible":[114],"initial":[115,127,140],"poses":[116],"within":[120],"ensure":[125],"replicated":[133],"as":[134,136],"close":[135],"possible":[137],"in":[145,162,207],"hardware":[146,208],"experiments.":[147,209],"Finally,":[148],"we":[149],"demonstrate":[150],"feasibility":[152],"our":[154,190],"method":[155],"transferring":[158],"policy":[161,199],"simulation":[163],"hardware,":[168],"realizing":[169],"sustained":[170],"gaits":[172],"under":[173],"external":[174],"force":[175],"disturbances":[176],"challenging":[178],"terrains":[179],"not":[180],"incurred":[181],"during":[182],"training":[184],"process.":[185],"To":[186],"best":[188],"knowledge,":[191],"first":[195],"time":[196],"learning-based":[198],"transferred":[201]},"counts_by_year":[{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":3}],"updated_date":"2026-05-01T08:36:08.643496","created_date":"2025-10-10T00:00:00"}