{"id":"https://openalex.org/W4317383439","doi":"https://doi.org/10.1109/robio55434.2022.10011765","title":"Quadruped Reinforcement Learning without Explicit State Estimation","display_name":"Quadruped Reinforcement Learning without Explicit State Estimation","publication_year":2022,"publication_date":"2022-12-05","ids":{"openalex":"https://openalex.org/W4317383439","doi":"https://doi.org/10.1109/robio55434.2022.10011765"},"language":"en","primary_location":{"id":"doi:10.1109/robio55434.2022.10011765","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/robio55434.2022.10011765","pdf_url":null,"source":{"id":"https://openalex.org/S4363607789","display_name":"2022 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":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5047471875","display_name":"Qikai Li","orcid":"https://orcid.org/0000-0002-4767-9474"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qikai Li","raw_affiliation_strings":["Robotics Institute, Beihang University, School of Mechanical Engineering and Automation,Beijing,China,100191"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics Institute, Beihang University, School of Mechanical Engineering and Automation,Beijing,China,100191","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022275259","display_name":"Guiyu Dong","orcid":"https://orcid.org/0009-0009-7035-9450"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guiyu Dong","raw_affiliation_strings":["Robotics Institute, Beihang University, School of Mechanical Engineering and Automation,Beijing,China,100191"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics Institute, Beihang University, School of Mechanical Engineering and Automation,Beijing,China,100191","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091081209","display_name":"Ripeng Qin","orcid":"https://orcid.org/0009-0008-7454-5333"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ripeng Qin","raw_affiliation_strings":["Robotics Institute, Beihang University, School of Mechanical Engineering and Automation,Beijing,China,100191"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics Institute, Beihang University, School of Mechanical Engineering and Automation,Beijing,China,100191","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362814","display_name":"Jiawei Chen","orcid":"https://orcid.org/0000-0002-4668-5418"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Chen","raw_affiliation_strings":["Robotics Institute, Beihang University, School of Mechanical Engineering and Automation,Beijing,China,100191"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics Institute, Beihang University, School of Mechanical Engineering and Automation,Beijing,China,100191","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059532729","display_name":"Kun Xu","orcid":"https://orcid.org/0000-0003-4733-393X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Xu","raw_affiliation_strings":["Robotics Institute, Beihang University, School of Mechanical Engineering and Automation,Beijing,China,100191"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics Institute, Beihang University, School of Mechanical Engineering and Automation,Beijing,China,100191","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059209683","display_name":"Xilun Ding","orcid":"https://orcid.org/0000-0002-9752-3937"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xilun Ding","raw_affiliation_strings":["Robotics Institute, Beihang University, School of Mechanical Engineering and Automation,Beijing,China,100191"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics Institute, Beihang University, School of Mechanical Engineering and Automation,Beijing,China,100191","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.32031294,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1989","last_page":"1994"},"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/T12810","display_name":"Real-time simulation and control systems","score":0.9837999939918518,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T11663","display_name":"Viral Infectious Diseases and Gene Expression in Insects","score":0.9710999727249146,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8018499612808228},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7711974382400513},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6278952956199646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5412004590034485},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.5104064345359802},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.49477308988571167},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4940193295478821},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47809430956840515},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.45256027579307556},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.41957223415374756},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3523463010787964},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32913562655448914},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.28738683462142944},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.27307093143463135}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8018499612808228},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7711974382400513},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6278952956199646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5412004590034485},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.5104064345359802},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.49477308988571167},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4940193295478821},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47809430956840515},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.45256027579307556},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.41957223415374756},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3523463010787964},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32913562655448914},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.28738683462142944},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.27307093143463135},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/robio55434.2022.10011765","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/robio55434.2022.10011765","pdf_url":null,"source":{"id":"https://openalex.org/S4363607789","display_name":"2022 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":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5432172654","display_name":null,"funder_award_id":"51775011,91748201","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"}],"funders":[{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1529094214","https://openalex.org/W2736601468","https://openalex.org/W2911087563","https://openalex.org/W2968213087","https://openalex.org/W3033353027","https://openalex.org/W3039737909","https://openalex.org/W3176539729","https://openalex.org/W3213974477","https://openalex.org/W3215924505","https://openalex.org/W4226143977","https://openalex.org/W4229044820","https://openalex.org/W4283787029","https://openalex.org/W4286963241","https://openalex.org/W4300892751","https://openalex.org/W4390481291","https://openalex.org/W6627932998","https://openalex.org/W6638018090","https://openalex.org/W6696904280","https://openalex.org/W6741002519","https://openalex.org/W6786146360","https://openalex.org/W6801964084","https://openalex.org/W6805822468","https://openalex.org/W6809847274"],"related_works":["https://openalex.org/W3022038857","https://openalex.org/W2030895127","https://openalex.org/W2065963568","https://openalex.org/W4205156393","https://openalex.org/W2383495909","https://openalex.org/W1534851618","https://openalex.org/W4205588766","https://openalex.org/W2907103250","https://openalex.org/W4249213554","https://openalex.org/W2999902861"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,111,130,143],"is":[2,36,174,187],"a":[3,46,137,152],"promising":[4],"approach":[5],"to":[6,25,38,76,100,112],"developing":[7],"legged":[8,40],"robot":[9,48,85,159,186],"locomotion":[10],"controllers.":[11],"The":[12,60,147,168],"gen-eral":[13],"process":[14,131],"of":[15,53,58,93,109,117,121,170,183],"development":[16,92],"is:":[17],"large-scale":[18],"training":[19,44,54,138],"in":[20,69,78,144,176],"the":[21,33,43,51,56,79,91,106,118,127,171,184],"virtual":[22],"simulation":[23,70],"environment":[24],"obtain":[26,77],"reliable":[27,153],"control":[28,101],"policy":[29,34,154],"network,":[30],"and":[31,55,103,135,162,178],"then":[32],"network":[35],"deployed":[37],"real":[39,80,179],"robot.":[41,181],"In":[42],"procedure,":[45],"complete":[47],"state":[49,86,94,160],"increases":[50],"speed":[52],"stability":[57],"policy.":[59],"robot's":[61],"states":[62],"like":[63],"body":[64],"velocities":[65],"are":[66,74,88],"easily":[67],"available":[68,188],"training,":[71],"but":[72],"they":[73],"difficult":[75],"robot,":[81],"hence":[82],"specifically":[83],"designed":[84],"estimators":[87,95],"needed.":[89],"However,":[90],"requires":[96],"expert":[97],"knowledge":[98],"related":[99],"theory":[102],"robotics,":[104],"limiting":[105],"direct":[107],"application":[108],"reinforcement":[110,129],"robots.":[113],"To":[114],"take":[115,164],"advantage":[116],"end-to-end":[119],"mapping":[120],"artificial":[122],"neural":[123],"networks,":[124],"we":[125],"simplified":[126],"existing":[128],"for":[132],"quadruped":[133],"robots":[134],"propose":[136],"method":[139,149,173],"based":[140],"on":[141],"curriculum":[142],"this":[145],"work.":[146],"proposed":[148,172],"can":[150],"produce":[151],"that":[155],"does":[156],"not":[157],"require":[158],"estimator":[161],"only":[163],"raw":[165],"sensors":[166],"data.":[167],"feasibility":[169],"verified":[175],"simulations":[177],"quadrupedal":[180,185],"Video":[182],"at":[189],"www.youtube.com/watch?v=-iho4KIlEPw.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
