{"id":"https://openalex.org/W4226403863","doi":"https://doi.org/10.1109/robio54168.2021.9739300","title":"Agile Control For Quadruped Robot In Complex Environment Based on Deep Reinforcement Learning Method","display_name":"Agile Control For Quadruped Robot In Complex Environment Based on Deep Reinforcement Learning Method","publication_year":2021,"publication_date":"2021-12-27","ids":{"openalex":"https://openalex.org/W4226403863","doi":"https://doi.org/10.1109/robio54168.2021.9739300"},"language":"en","primary_location":{"id":"doi:10.1109/robio54168.2021.9739300","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio54168.2021.9739300","pdf_url":null,"source":{"id":"https://openalex.org/S4363607846","display_name":"2021 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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 International Conference on Robotics and Biomimetics (ROBIO)","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/A5101568340","display_name":"Hua Xiao","orcid":"https://orcid.org/0000-0003-3407-7009"},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hua Xiao","raw_affiliation_strings":["Beijing University of Chemical Technology,College of Information Science and Technology,Beijing,China,100029"],"affiliations":[{"raw_affiliation_string":"Beijing University of Chemical Technology,College of Information Science and Technology,Beijing,China,100029","institution_ids":["https://openalex.org/I75390827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044872738","display_name":"Shibo Shao","orcid":"https://orcid.org/0009-0009-6275-9737"},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shibo Shao","raw_affiliation_strings":["Beijing University of Chemical Technology,College of Information Science and Technology,Beijing,China,100029"],"affiliations":[{"raw_affiliation_string":"Beijing University of Chemical Technology,College of Information Science and Technology,Beijing,China,100029","institution_ids":["https://openalex.org/I75390827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100366069","display_name":"Dong Zhang","orcid":"https://orcid.org/0000-0001-7002-7661"},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Zhang","raw_affiliation_strings":["Beijing University of Chemical Technology,College of Information Science and Technology,Beijing,China,100029"],"affiliations":[{"raw_affiliation_string":"Beijing University of Chemical Technology,College of Information Science and Technology,Beijing,China,100029","institution_ids":["https://openalex.org/I75390827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101568340"],"corresponding_institution_ids":["https://openalex.org/I75390827"],"apc_list":null,"apc_paid":null,"fwci":0.3852,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55043301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1065","last_page":"1070"},"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":0.9977999925613403,"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":0.9603000283241272,"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":0.8826779127120972},{"id":"https://openalex.org/keywords/agile-software-development","display_name":"Agile software development","score":0.7356052994728088},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6961631178855896},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5696352124214172},{"id":"https://openalex.org/keywords/gait","display_name":"Gait","score":0.5092920064926147},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5051212906837463},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.482878714799881},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4749096632003784},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4715419113636017}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8826779127120972},{"id":"https://openalex.org/C14185376","wikidata":"https://www.wikidata.org/wiki/Q30232","display_name":"Agile software development","level":2,"score":0.7356052994728088},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6961631178855896},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5696352124214172},{"id":"https://openalex.org/C151800584","wikidata":"https://www.wikidata.org/wiki/Q2370000","display_name":"Gait","level":2,"score":0.5092920064926147},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5051212906837463},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.482878714799881},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4749096632003784},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4715419113636017},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio54168.2021.9739300","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio54168.2021.9739300","pdf_url":null,"source":{"id":"https://openalex.org/S4363607846","display_name":"2021 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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 International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"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":21,"referenced_works":["https://openalex.org/W2012587148","https://openalex.org/W2377098276","https://openalex.org/W2606433045","https://openalex.org/W2726187156","https://openalex.org/W2736601468","https://openalex.org/W2756071177","https://openalex.org/W2891816981","https://openalex.org/W2963184939","https://openalex.org/W2963864421","https://openalex.org/W2964393431","https://openalex.org/W2967236418","https://openalex.org/W2968095426","https://openalex.org/W2982316857","https://openalex.org/W3003817470","https://openalex.org/W3008998212","https://openalex.org/W3029509103","https://openalex.org/W3090417004","https://openalex.org/W3091304796","https://openalex.org/W6653548176","https://openalex.org/W6709469080","https://openalex.org/W6765121789"],"related_works":["https://openalex.org/W2656997359","https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W1973385172","https://openalex.org/W4391331176","https://openalex.org/W4319430762"],"abstract_inverted_index":{"Using":[0],"deep":[1],"reinforcement":[2],"learning":[3,36,110],"for":[4,25,52],"a":[5,15,34,64,70,99,122],"quadruped":[6],"robot":[7],"to":[8,14,49,87],"complete":[9],"complex":[10,57],"tasks":[11],"will":[12,19],"lead":[13],"dimension":[16],"explosion,":[17],"which":[18,96],"make":[20],"it":[21],"is":[22,47,61,85,116],"more":[23],"difficult":[24],"designing":[26],"and":[27,69],"training":[28,90],"the":[29,76,89,93,109,113],"network.":[30,74,124],"In":[31,75],"this":[32],"paper,":[33],"hierarchical":[35,123],"(HL)":[37],"framework":[38,60],"based":[39],"on":[40],"distributed":[41],"proximal":[42],"policy":[43],"optimization":[44],"(DPPO)":[45],"algorithm":[46],"proposed":[48,114],"find":[50],"strategies":[51],"realizing":[53],"agile":[54],"control":[55],"in":[56],"environment.":[58],"The":[59,104],"divided":[62],"into":[63],"low-level":[65,77],"gait":[66,102],"generation":[67],"network":[68],"high-level":[71],"environmental":[72],"adaptation":[73],"network,":[78],"some":[79],"open-loop":[80],"signals":[81],"of":[82,92,112],"different":[83],"gaits":[84],"introduced":[86],"improve":[88],"efficiency":[91],"DPPO":[94],"algorithm,":[95],"can":[97],"generate":[98],"stable":[100],"initial":[101],"faster.":[103],"experimental":[105],"results":[106],"show":[107],"that":[108,120],"effect":[111],"method":[115],"obviously":[117],"better":[118],"than":[119],"without":[121]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}