{"id":"https://openalex.org/W3107637065","doi":"https://doi.org/10.1109/icca51439.2020.9264548","title":"Locomotion Control Method for Humanoid Robot Based on United Hierarchical Reinforcement Learning","display_name":"Locomotion Control Method for Humanoid Robot Based on United Hierarchical Reinforcement Learning","publication_year":2020,"publication_date":"2020-10-09","ids":{"openalex":"https://openalex.org/W3107637065","doi":"https://doi.org/10.1109/icca51439.2020.9264548","mag":"3107637065"},"language":"en","primary_location":{"id":"doi:10.1109/icca51439.2020.9264548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca51439.2020.9264548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 16th International Conference on Control & Automation (ICCA)","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/A5029670134","display_name":"Boying Liu","orcid":"https://orcid.org/0009-0002-6536-502X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Boying Liu","raw_affiliation_strings":["Shanghai Cultural Foundation"],"affiliations":[{"raw_affiliation_string":"Shanghai Cultural Foundation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110796347","display_name":"Lu Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Ma","raw_affiliation_strings":["Department of Electronics and Information Engineering, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013001585","display_name":"Chenju Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenju Liu","raw_affiliation_strings":["Department of Electronics and Information Engineering, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050916383","display_name":"BinChen Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"BinChen Xu","raw_affiliation_strings":["Department of Electronics and Information Engineering, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5029670134"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0858,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4092943,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"3","issue":null,"first_page":"1161","last_page":"1166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9858999848365784,"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":0.9435999989509583,"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":0.8315833806991577},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.780827522277832},{"id":"https://openalex.org/keywords/particle-swarm-optimization","display_name":"Particle swarm optimization","score":0.6647103428840637},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5946701169013977},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5581402778625488},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.507133960723877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4941418468952179},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45159149169921875},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4367208182811737},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.43557724356651306},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3725576102733612},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.31106826663017273},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2502014935016632}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8315833806991577},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.780827522277832},{"id":"https://openalex.org/C85617194","wikidata":"https://www.wikidata.org/wiki/Q2072794","display_name":"Particle swarm optimization","level":2,"score":0.6647103428840637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5946701169013977},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5581402778625488},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.507133960723877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4941418468952179},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45159149169921875},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4367208182811737},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.43557724356651306},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3725576102733612},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.31106826663017273},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2502014935016632},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icca51439.2020.9264548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca51439.2020.9264548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 16th International Conference on Control & Automation (ICCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1491430245","https://openalex.org/W1506414135","https://openalex.org/W1553786746","https://openalex.org/W1592847719","https://openalex.org/W1820051232","https://openalex.org/W2028022601","https://openalex.org/W2044912276","https://openalex.org/W2057347169","https://openalex.org/W2064779083","https://openalex.org/W2115611942","https://openalex.org/W2121517924","https://openalex.org/W2152195021","https://openalex.org/W2260028708","https://openalex.org/W2417280899","https://openalex.org/W2543580944","https://openalex.org/W2608976729","https://openalex.org/W2739330054","https://openalex.org/W2775046486","https://openalex.org/W2875797025","https://openalex.org/W2963610279","https://openalex.org/W2969926105","https://openalex.org/W3143860690"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2100910774","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W4376605461","https://openalex.org/W4400868993","https://openalex.org/W2361647908"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,17,21],"hierarchical":[4,38],"reinforcement":[5,22,39],"learning":[6,23,40],"control":[7,15,52],"method":[8],"and":[9,49],"applies":[10],"it":[11],"to":[12,62,96,116],"the":[13,55,64,72,80,83,93,98,107,111,118,124],"walking":[14,77],"of":[16,68,82,110],"humanoid":[18,119],"robot.":[19],"Firstly,":[20],"algorithm":[24,59],"called":[25],"proximal":[26],"policy":[27],"optimization(PPO)":[28],"is":[29,42,60,90,114],"combined":[30],"with":[31,47],"central":[32],"pattern":[33],"generator(CPG).":[34],"Thus":[35],"an":[36],"united":[37],"(UHRL)":[41],"built":[43],"which":[44],"could":[45],"cooperates":[46],"high":[48],"low":[50],"levels":[51],"tasks.":[53],"Secondly,":[54],"particle":[56,86],"swarm":[57,87],"optimization":[58,99],"used":[61,91],"obtain":[63],"initial":[65],"parameter":[66],"configuration":[67],"CPG.":[69],"So":[70],"that":[71],"robot":[73,120],"can":[74],"generate":[75],"basic":[76],"gait":[78],"at":[79],"beginning":[81],"experiment.":[84],"The":[85],"variance":[88],"fitness":[89],"as":[92],"variation":[94],"constraint":[95],"prevent":[97],"process":[100],"from":[101,123],"falling":[102],"into":[103],"precocious":[104],"convergence.":[105],"Thirdly,":[106],"reward":[108],"function":[109],"high-level":[112],"controller":[113],"designed":[115],"help":[117],"avoid":[121],"deviation":[122],"original":[125],"path.":[126]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}