{"id":"https://openalex.org/W2967815054","doi":"https://doi.org/10.1109/icra.2019.8793627","title":"Reinforcement Learning Meets Hybrid Zero Dynamics: A Case Study for RABBIT","display_name":"Reinforcement Learning Meets Hybrid Zero Dynamics: A Case Study for RABBIT","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2967815054","doi":"https://doi.org/10.1109/icra.2019.8793627","mag":"2967815054"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2019.8793627","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8793627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 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/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"],"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"],"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/A5069228447","display_name":"Ayonga Hereid","orcid":"https://orcid.org/0000-0002-4156-2013"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ayonga Hereid","raw_affiliation_strings":["EECS, University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"EECS, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045214230","display_name":"Zheng Wang","orcid":"https://orcid.org/0000-0002-7726-0770"},"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":"Zheng Wang","raw_affiliation_strings":["Department of Mechanical Engineering, University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102018772","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0003-4805-5011"},"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, China"],"affiliations":[{"raw_affiliation_string":"SUSTech Institute of Robotics, Southern University of Science and Technology, China","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5025408291"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":1.3693,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.79482746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"284","last_page":"290"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9926999807357788,"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":0.9901999831199646,"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":0.7991737127304077},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6554688811302185},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6384591460227966},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5926980972290039},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.557473361492157},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.505287230014801},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4473935663700104},{"id":"https://openalex.org/keywords/robust-control","display_name":"Robust control","score":0.43903955817222595},{"id":"https://openalex.org/keywords/adaptive-control","display_name":"Adaptive control","score":0.431222528219223},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.4271283447742462},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35501089692115784},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.28687500953674316},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.26049381494522095},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.23159897327423096},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11468639969825745}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7991737127304077},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6554688811302185},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6384591460227966},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5926980972290039},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.557473361492157},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.505287230014801},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4473935663700104},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.43903955817222595},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.431222528219223},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.4271283447742462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35501089692115784},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.28687500953674316},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.26049381494522095},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.23159897327423096},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11468639969825745},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2019.8793627","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8793627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1490862430","https://openalex.org/W1504362584","https://openalex.org/W1757796397","https://openalex.org/W1963780181","https://openalex.org/W1989901771","https://openalex.org/W1993314711","https://openalex.org/W1994923984","https://openalex.org/W2003132288","https://openalex.org/W2017382559","https://openalex.org/W2030515455","https://openalex.org/W2037729465","https://openalex.org/W2040657708","https://openalex.org/W2057380381","https://openalex.org/W2080421646","https://openalex.org/W2098787727","https://openalex.org/W2104733512","https://openalex.org/W2122903487","https://openalex.org/W2154174243","https://openalex.org/W2158782408","https://openalex.org/W2162109810","https://openalex.org/W2169814710","https://openalex.org/W2170777202","https://openalex.org/W2198582666","https://openalex.org/W2413365548","https://openalex.org/W2465284394","https://openalex.org/W2539534359","https://openalex.org/W2602963933","https://openalex.org/W2610901891","https://openalex.org/W2736601468","https://openalex.org/W2739330054","https://openalex.org/W2767942947","https://openalex.org/W2774367037","https://openalex.org/W2792099719","https://openalex.org/W2963184621","https://openalex.org/W2963315892","https://openalex.org/W2963864421","https://openalex.org/W2964114602","https://openalex.org/W4298857966","https://openalex.org/W6627932998","https://openalex.org/W6629277349","https://openalex.org/W6637967152","https://openalex.org/W6675999342","https://openalex.org/W6684921986","https://openalex.org/W6735677848","https://openalex.org/W6741002519","https://openalex.org/W6745494356","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W1512021029","https://openalex.org/W2108470770","https://openalex.org/W1980376593","https://openalex.org/W1972862722","https://openalex.org/W2281732014","https://openalex.org/W1991810297","https://openalex.org/W2063351494","https://openalex.org/W1562326332","https://openalex.org/W2319803529","https://openalex.org/W2152839317"],"abstract_inverted_index":{"The":[0,164,201],"design":[1,36],"of":[2,15,37,92,139,186,198],"feedback":[3,38],"controllers":[4,39],"for":[5,34,52,85,146],"bipedal":[6,24,53,86],"robots":[7],"is":[8,81,175,189,205],"challenging":[9],"due":[10],"to":[11,77,120,123,136,177,195],"the":[12,19,35,62,70,93,109,113,131,143,147,151,187,196,199,213,219],"hybrid":[13],"nature":[14],"its":[16],"dynamics":[17],"and":[18,44,69,170,207],"complexity":[20],"imposed":[21],"by":[22,191],"high-dimensional":[23],"models.":[25],"In":[26,97],"this":[27,98],"paper,":[28,99],"we":[29,100,118],"present":[30],"a":[31,82,102,125,137,168,182],"novel":[32],"approach":[33],"using":[40,159],"Reinforcement":[41],"Learning":[42],"(RL)":[43],"Hybrid":[45],"Zero":[46],"Dynamics":[47],"(HZD).":[48],"Existing":[49],"RL":[50,105,122,203],"approaches":[51],"walking":[54,94],"are":[55,157],"inefficient":[56],"as":[57],"they":[58],"do":[59],"not":[60,74],"consider":[61],"underlying":[63],"physics,":[64],"often":[65],"requires":[66],"substantial":[67],"training,":[68],"resulting":[71],"controller":[72],"may":[73],"be":[75],"applicable":[76],"real":[78],"robots.":[79],"HZD":[80,110],"powerful":[83],"tool":[84],"control":[87,126,172],"with":[88,212],"local":[89],"stability":[90],"guarantees":[91],"limit":[95],"cycles.":[96],"propose":[101,119],"non":[103],"traditional":[104],"structure":[106],"that":[107,128,141,174],"embeds":[108],"framework":[111,204],"into":[112],"policy":[114,127,173,188],"learning.":[115],"More":[116],"specifically,":[117],"use":[121],"find":[124],"maps":[129],"from":[130],"robot\u2019s":[132,148],"reduced":[133],"order":[134],"states":[135],"set":[138],"parameters":[140],"define":[142],"desired":[144],"trajectories":[145,156],"joints":[149],"through":[150],"virtual":[152],"constraints.":[153],"Then,":[154],"these":[155],"tracked":[158],"an":[160],"adaptive":[161],"PD":[162],"controller.":[163],"method":[165],"results":[166],"in":[167,209],"stable":[169],"robust":[171],"able":[176],"track":[178],"variable":[179],"speed":[180],"within":[181],"continuous":[183],"interval.":[184],"Robustness":[185],"evaluated":[190],"applying":[192],"external":[193],"forces":[194],"torso":[197],"robot.":[200],"proposed":[202],"implemented":[206],"demonstrated":[208],"OpenAI":[210],"Gym":[211],"MuJoCo":[214],"physics":[215],"engine":[216],"based":[217],"on":[218],"well-known":[220],"RABBIT":[221],"robot":[222],"model.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}