{"id":"https://openalex.org/W4320057380","doi":"https://doi.org/10.1145/3573834.3574484","title":"A Biped Robot Learning to Walk like Human by Reinforcement Learning","display_name":"A Biped Robot Learning to Walk like Human by Reinforcement Learning","publication_year":2022,"publication_date":"2022-11-25","ids":{"openalex":"https://openalex.org/W4320057380","doi":"https://doi.org/10.1145/3573834.3574484"},"language":"en","primary_location":{"id":"doi:10.1145/3573834.3574484","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3573834.3574484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Advanced Information Science and System","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/A5090160606","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0002-3615-498X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi Liu","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034725449","display_name":"Honglei An","orcid":"https://orcid.org/0000-0002-2865-7034"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honglei An","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032729336","display_name":"Hongxu Ma","orcid":"https://orcid.org/0000-0002-4662-2986"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongxu Ma","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5090160606"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15228771,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.992900013923645,"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":0.9592999815940857,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8530555963516235},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7166049480438232},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6281472444534302},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5502118468284607},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5270614624023438},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49318617582321167},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4837205708026886},{"id":"https://openalex.org/keywords/gait","display_name":"Gait","score":0.4834383428096771},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4727148711681366},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.4195808470249176},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.41316545009613037},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.35828137397766113},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.32121315598487854},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.2524073123931885}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8530555963516235},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7166049480438232},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6281472444534302},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5502118468284607},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5270614624023438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49318617582321167},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4837205708026886},{"id":"https://openalex.org/C151800584","wikidata":"https://www.wikidata.org/wiki/Q2370000","display_name":"Gait","level":2,"score":0.4834383428096771},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4727148711681366},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.4195808470249176},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.41316545009613037},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.35828137397766113},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.32121315598487854},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2524073123931885},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C42407357","wikidata":"https://www.wikidata.org/wiki/Q521","display_name":"Physiology","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/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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:10.1145/3573834.3574484","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3573834.3574484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Advanced Information Science and System","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1963997705","https://openalex.org/W1984120922","https://openalex.org/W2033629346","https://openalex.org/W2074042377","https://openalex.org/W2086587468","https://openalex.org/W2228102949","https://openalex.org/W2914653242","https://openalex.org/W2980301669","https://openalex.org/W3035707643","https://openalex.org/W3193576605","https://openalex.org/W4207045767","https://openalex.org/W4288061557"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548","https://openalex.org/W2100910774"],"abstract_inverted_index":{"It's":[0],"challenging":[1],"to":[2,40,44,53,58,62,105,162],"make":[3],"a":[4,9,71,77,131],"biped":[5,36,72,128],"robot":[6,61,73,129],"walk":[7,63],"like":[8,66],"human.":[10,67],"Many":[11],"researches":[12],"have":[13],"been":[14],"made":[15],"such":[16],"as":[17],"gait":[18],"planning,":[19],"stable":[20],"walking":[21],"controller":[22],"and":[23,26,64,75,102,137,140,160],"so":[24],"on":[25,84,165],"achieve":[27],"great":[28],"progress.":[29],"Reinforcement":[30],"learning":[31,82],"methods":[32],"are":[33],"used":[34],"in":[35,144,148],"robots":[37],"recently":[38],"due":[39],"their":[41],"powerful":[42],"ability":[43],"deal":[45],"with":[46],"high-dimensional":[47],"computing":[48],"problem.":[49],"However,":[50],"it's":[51],"hard":[52],"design":[54],"good":[55,132,142],"reward":[56,91,156],"function":[57,92,157],"guide":[59],"the":[60,94,97,118,127,154],"behavior":[65],"This":[68],"paper":[69],"builds":[70],"model":[74],"presents":[76],"control":[78,139],"framework":[79],"of":[80,99,134],"reinforcement":[81],"based":[83],"Isaac":[85],"Gym":[86],"simulation":[87],"platform.":[88],"The":[89,109,121,150],"designed":[90,155],"considers":[93],"velocity":[95,135],"tracking,":[96],"symmetry":[98],"hip":[100],"angle":[101],"leg":[103],"lifting":[104],"simulate":[106],"human":[107],"motion.":[108],"training":[110,126],"process":[111],"only":[112],"lasts":[113],"for":[114],"2":[115],"hours":[116],"from":[117],"very":[119],"beginning.":[120],"results":[122,151],"show":[123],"that":[124],"after":[125],"has":[130],"performance":[133],"tracking":[136],"attitude":[138],"shows":[141],"symmetries":[143],"joint":[145],"angles":[146],"especially":[147],"hip.":[149],"also":[152],"prove":[153],"is":[158],"effective":[159],"hopeful":[161],"be":[163],"available":[164],"other":[166],"applications.":[167]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
