{"id":"https://openalex.org/W4385781536","doi":"https://doi.org/10.1142/s0219843623500135","title":"A Heuristics-Based Reinforcement Learning Method to Control Bipedal Robots","display_name":"A Heuristics-Based Reinforcement Learning Method to Control Bipedal Robots","publication_year":2023,"publication_date":"2023-08-12","ids":{"openalex":"https://openalex.org/W4385781536","doi":"https://doi.org/10.1142/s0219843623500135"},"language":"en","primary_location":{"id":"doi:10.1142/s0219843623500135","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219843623500135","pdf_url":null,"source":{"id":"https://openalex.org/S75343556","display_name":"International Journal of Humanoid Robotics","issn_l":"0219-8436","issn":["0219-8436","1793-6942"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Humanoid Robotics","raw_type":"journal-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/A5047706378","display_name":"Daoling Qin","orcid":"https://orcid.org/0000-0003-2931-4997"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daoling Qin","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan 250061, P. R. China"],"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan 250061, P. R. China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070648653","display_name":"Guoteng Zhang","orcid":"https://orcid.org/0000-0001-7705-2819"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guoteng Zhang","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan 250061, P. R. China"],"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan 250061, P. R. China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042857298","display_name":"Zhengguo Zhu","orcid":"https://orcid.org/0000-0002-3041-4314"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengguo Zhu","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan 250061, P. R. China"],"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan 250061, P. R. China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100637772","display_name":"Teng Chen","orcid":"https://orcid.org/0000-0002-7905-564X"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Teng Chen","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan 250061, P. R. China"],"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan 250061, P. R. China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035738062","display_name":"Weiliang Zhu","orcid":"https://orcid.org/0000-0001-7489-7744"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiliang Zhu","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan 250061, P. R. China"],"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan 250061, P. R. China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025820722","display_name":"Xuewen Rong","orcid":"https://orcid.org/0000-0003-3283-5347"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuewen Rong","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan 250061, P. R. China"],"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan 250061, P. R. China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032102869","display_name":"Anhuan Xie","orcid":"https://orcid.org/0000-0002-8348-0067"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Anhuan Xie","raw_affiliation_strings":["Intelligent Robot Research Center, Zhejiang Laboratory, Hangzhou 311121, P. R. China"],"affiliations":[{"raw_affiliation_string":"Intelligent Robot Research Center, Zhejiang Laboratory, Hangzhou 311121, P. R. China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100724411","display_name":"Yibin Li","orcid":"https://orcid.org/0000-0002-5906-5074"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibin Li","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan 250061, P. R. China"],"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan 250061, P. R. China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5032102869","https://openalex.org/A5070648653"],"corresponding_institution_ids":["https://openalex.org/I154099455","https://openalex.org/I4210123185"],"apc_list":null,"apc_paid":null,"fwci":0.3379,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.5320172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"21","issue":"03","first_page":null,"last_page":null},"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":0.97079998254776,"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":0.9693999886512756,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8498029112815857},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7323368787765503},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6299171447753906},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4900258779525757},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.46669748425483704},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4599451422691345},{"id":"https://openalex.org/keywords/robot-locomotion","display_name":"Robot locomotion","score":0.44425490498542786},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4134840965270996},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4103355407714844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3915538489818573},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.3880431056022644},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2962711453437805},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.21610456705093384},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.15379273891448975}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8498029112815857},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7323368787765503},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6299171447753906},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4900258779525757},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.46669748425483704},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4599451422691345},{"id":"https://openalex.org/C6101204","wikidata":"https://www.wikidata.org/wiki/Q7353391","display_name":"Robot locomotion","level":5,"score":0.44425490498542786},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4134840965270996},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4103355407714844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3915538489818573},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3880431056022644},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2962711453437805},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.21610456705093384},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.15379273891448975},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0219843623500135","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219843623500135","pdf_url":null,"source":{"id":"https://openalex.org/S75343556","display_name":"International Journal of Humanoid Robotics","issn_l":"0219-8436","issn":["0219-8436","1793-6942"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Humanoid Robotics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1144462046","display_name":null,"funder_award_id":"62003190","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2339313472","display_name":null,"funder_award_id":"91948201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1661970104","https://openalex.org/W2037729465","https://openalex.org/W2110612452","https://openalex.org/W2118495694","https://openalex.org/W2169564405","https://openalex.org/W2228102949","https://openalex.org/W2239166089","https://openalex.org/W2296073425","https://openalex.org/W2465284394","https://openalex.org/W2789316480","https://openalex.org/W2804790641","https://openalex.org/W2911087563","https://openalex.org/W2964114602","https://openalex.org/W2972798201","https://openalex.org/W2991542025","https://openalex.org/W3093922502","https://openalex.org/W3104876774","https://openalex.org/W3136437429","https://openalex.org/W3150249871","https://openalex.org/W3202243720","https://openalex.org/W3206620955","https://openalex.org/W3206762371","https://openalex.org/W3206804182","https://openalex.org/W3213426571","https://openalex.org/W4206474659","https://openalex.org/W4226143977","https://openalex.org/W4229081732","https://openalex.org/W4308140687","https://openalex.org/W4312986762"],"related_works":["https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W3177062893","https://openalex.org/W3125143773","https://openalex.org/W2007032764","https://openalex.org/W803550684","https://openalex.org/W2483226803","https://openalex.org/W4352977312","https://openalex.org/W4312926500","https://openalex.org/W2041180560"],"abstract_inverted_index":{"A":[0],"new":[1],"method":[2],"is":[3,68],"proposed":[4],"to":[5,9,60,70,112],"control":[6],"bipedal":[7,100],"robots":[8],"achieve":[10],"flexible":[11],"omni-directional":[12,114],"motion":[13],"and":[14,53,74,89,134],"robust":[15],"locomotion":[16,115],"under":[17,131],"complex":[18],"disturbances,":[19],"called":[20],"the":[21,45,62,91,117],"heuristics-based":[22],"reinforcement":[23],"learning":[24],"(HBRL)":[25],"framework.":[26],"HBRL":[27],"shows":[28],"great":[29],"training":[30,46,63],"efficiency":[31],"in":[32,41,84],"simulation.":[33,85],"Heuristic":[34],"reference":[35],"trajectories":[36],"play":[37],"a":[38,98],"crucial":[39],"role":[40],"HBRL,":[42],"which":[43],"guide":[44],"process.":[47,64],"Exploration":[48],"rewards,":[49],"leg-foot":[50],"reset":[51],"condition,":[52],"command":[54],"curriculum":[55],"are":[56],"three":[57,103],"significant":[58],"components":[59],"optimize":[61],"An":[65],"estimator":[66],"network":[67],"utilized":[69],"supply":[71],"linear":[72],"velocities":[73],"foot":[75],"contact":[76],"information.":[77],"We":[78],"train":[79],"controllers":[80,93,109],"on":[81,96,105],"flat":[82],"ground":[83],"To":[86],"demonstrate":[87],"robustness":[88],"versatility,":[90],"trained":[92],"were":[94],"tested":[95],"BRAVER,":[97],"point-foot":[99],"robot":[101,126],"with":[102,116],"joints":[104],"each":[106],"leg.":[107],"The":[108,125],"enabled":[110],"BRAVER":[111],"perform":[113],"maximum":[118],"forward":[119],"speed":[120],"reaching":[121],"2[Formula:":[122],"see":[123],"text]m/s.":[124],"could":[127],"also":[128],"maintain":[129],"balance":[130],"external":[132],"pushing":[133],"over":[135],"uneven":[136],"terrains.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
