{"id":"https://openalex.org/W3196996066","doi":"https://doi.org/10.3390/s21175907","title":"Adaptive Quadruped Balance Control for Dynamic Environments Using Maximum-Entropy Reinforcement Learning","display_name":"Adaptive Quadruped Balance Control for Dynamic Environments Using Maximum-Entropy Reinforcement Learning","publication_year":2021,"publication_date":"2021-09-02","ids":{"openalex":"https://openalex.org/W3196996066","doi":"https://doi.org/10.3390/s21175907","mag":"3196996066","pmid":"https://pubmed.ncbi.nlm.nih.gov/34502796"},"language":"en","primary_location":{"id":"doi:10.3390/s21175907","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s21175907","pdf_url":"https://www.mdpi.com/1424-8220/21/17/5907/pdf?version=1630580784","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/21/17/5907/pdf?version=1630580784","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039047428","display_name":"Haoran Sun","orcid":"https://orcid.org/0000-0003-4669-9358"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Sun","raw_affiliation_strings":["School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, China"],"raw_orcid":"https://orcid.org/0000-0003-4669-9358","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033918314","display_name":"Tingting Fu","orcid":"https://orcid.org/0000-0001-7741-5528"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingting Fu","raw_affiliation_strings":["School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042454872","display_name":"Yuanhuai Ling","orcid":null},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanhuai Ling","raw_affiliation_strings":["School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101783765","display_name":"Chaoming He","orcid":"https://orcid.org/0000-0003-0192-8452"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chaoming He","raw_affiliation_strings":["School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, China"],"raw_orcid":"https://orcid.org/0000-0003-0192-8452","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, China","institution_ids":["https://openalex.org/I4800084"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101783765"],"corresponding_institution_ids":["https://openalex.org/I4800084"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":0.4137,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.56391352,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"21","issue":"17","first_page":"5907","last_page":"5907"},"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/T11170","display_name":"Biomimetic flight and propulsion mechanisms","score":0.9840999841690063,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T11372","display_name":"Hydraulic and Pneumatic Systems","score":0.9799000024795532,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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":0.7007014751434326},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6121095418930054},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5289627909660339},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.528508722782135},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.522637128829956},{"id":"https://openalex.org/keywords/supervisor","display_name":"Supervisor","score":0.5055859088897705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5024988651275635},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3636912703514099},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33802464604377747},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3283325731754303},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.274727463722229},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.27189067006111145}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7007014751434326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6121095418930054},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5289627909660339},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.528508722782135},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.522637128829956},{"id":"https://openalex.org/C2779110517","wikidata":"https://www.wikidata.org/wiki/Q1240788","display_name":"Supervisor","level":2,"score":0.5055859088897705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5024988651275635},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3636912703514099},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33802464604377747},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3283325731754303},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.274727463722229},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.27189067006111145},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.3390/s21175907","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s21175907","pdf_url":"https://www.mdpi.com/1424-8220/21/17/5907/pdf?version=1630580784","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:34502796","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34502796","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:doaj.org/article:82ca97d605df404f93998b5c809bf278","is_oa":true,"landing_page_url":"https://doaj.org/article/82ca97d605df404f93998b5c809bf278","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 21, Iss 17, p 5907 (2021)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/21/17/5907/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s21175907","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors; Volume 21; Issue 17; Pages: 5907","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:8434611","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8434611","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s21175907","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s21175907","pdf_url":"https://www.mdpi.com/1424-8220/21/17/5907/pdf?version=1630580784","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3196996066.pdf","grobid_xml":"https://content.openalex.org/works/W3196996066.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1975230295","https://openalex.org/W2061063863","https://openalex.org/W2080421646","https://openalex.org/W2096836513","https://openalex.org/W2125224533","https://openalex.org/W2173248099","https://openalex.org/W2461181622","https://openalex.org/W2464873593","https://openalex.org/W2592566710","https://openalex.org/W2600092780","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2796290181","https://openalex.org/W2798705390","https://openalex.org/W2911087563","https://openalex.org/W2920812058","https://openalex.org/W2963184939","https://openalex.org/W2967118761","https://openalex.org/W2984879732","https://openalex.org/W3010768390","https://openalex.org/W3093922502","https://openalex.org/W3104515094","https://openalex.org/W3104876774","https://openalex.org/W3120722795","https://openalex.org/W6638018090","https://openalex.org/W6719584742","https://openalex.org/W6891797237"],"related_works":["https://openalex.org/W4387731985","https://openalex.org/W2755149878","https://openalex.org/W2468425257","https://openalex.org/W2941808082","https://openalex.org/W2528721242","https://openalex.org/W4377009725","https://openalex.org/W4320164562","https://openalex.org/W2356364326","https://openalex.org/W4379086698","https://openalex.org/W2372069567"],"abstract_inverted_index":{"External":[0],"disturbance":[1],"poses":[2],"the":[3,44,78,88,91,101,129,136],"primary":[4],"threat":[5],"to":[6,25,56,84,99,135],"robot":[7],"balance":[8],"in":[9,114,148],"dynamic":[10],"environments.":[11],"This":[12],"paper":[13],"provides":[14],"a":[15,67,71,121],"learning-based":[16],"control":[17,62],"architecture":[18],"for":[19],"quadrupedal":[20],"self-balancing,":[21],"which":[22,37,41,75],"is":[23,64,97,112,146],"adaptable":[24],"multiple":[26],"unpredictable":[27],"scenes":[28],"of":[29,66],"external":[30],"continuous":[31],"disturbance.":[32],"Different":[33],"from":[34,81],"conventional":[35],"methods":[36],"construct":[38],"analytical":[39],"models":[40],"explicitly":[42],"reason":[43],"balancing":[45],"process,":[46,90],"our":[47],"work":[48],"utilized":[49],"reinforcement":[50],"learning":[51],"and":[52,70,106,117],"artificial":[53],"neural":[54,68],"network":[55,69],"avoid":[57],"incomprehensible":[58],"mathematical":[59],"modeling.":[60],"The":[61,109,125],"policy":[63,102,111,130,145],"composed":[65],"Tanh":[72],"Gaussian":[73],"policy,":[74],"implicitly":[76],"establishes":[77],"fuzzy":[79],"mapping":[80],"proprioceptive":[82],"signals":[83],"action":[85],"commands.":[86],"During":[87],"training":[89],"maximum-entropy":[92],"method":[93],"(soft":[94],"actor-critic":[95],"algorithm)":[96],"employed":[98],"endow":[100],"with":[103,120],"powerful":[104],"exploration":[105],"generalization":[107],"ability.":[108],"trained":[110,147],"validated":[113],"both":[115],"simulations":[116],"realistic":[118],"experiments":[119],"customized":[122],"quadruped":[123],"robot.":[124],"results":[126],"demonstrate":[127],"that":[128,159],"can":[131],"be":[132],"easily":[133],"transferred":[134],"real":[137],"world":[138],"without":[139],"elaborate":[140],"configurations.":[141],"Moreover,":[142],"although":[143],"this":[144],"merely":[149],"one":[150],"specific":[151],"vibration":[152],"condition,":[153],"it":[154],"demonstrates":[155],"robustness":[156],"under":[157],"conditions":[158],"were":[160],"never":[161],"encountered":[162],"during":[163],"training.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
