{"id":"https://openalex.org/W4317383326","doi":"https://doi.org/10.1109/robio55434.2022.10011921","title":"Sim-to-real: Quadruped Robot Control with Deep Reinforcement Learning and Parallel Training","display_name":"Sim-to-real: Quadruped Robot Control with Deep Reinforcement Learning and Parallel Training","publication_year":2022,"publication_date":"2022-12-05","ids":{"openalex":"https://openalex.org/W4317383326","doi":"https://doi.org/10.1109/robio55434.2022.10011921"},"language":"en","primary_location":{"id":"doi:10.1109/robio55434.2022.10011921","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/robio55434.2022.10011921","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/A5100731362","display_name":"Han Jiang","orcid":"https://orcid.org/0000-0002-4909-367X"},"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":"Han Jiang","raw_affiliation_strings":["Center for Robotics, School of Control Science and Engineering, Shandong University,China","Center for Robotics, School of Control Science and Engineering, Shandong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robotics, School of Control Science and Engineering, Shandong University,China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"Center for Robotics, School of Control Science and Engineering, Shandong University, 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":["Center for Robotics, School of Control Science and Engineering, Shandong University,China","Center for Robotics, School of Control Science and Engineering, Shandong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robotics, School of Control Science and Engineering, Shandong University,China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"Center for Robotics, School of Control Science and Engineering, Shandong University, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069853141","display_name":"Jingxuan Cao","orcid":null},"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":"Jingxuan Cao","raw_affiliation_strings":["Center for Robotics, School of Control Science and Engineering, Shandong University,China","Center for Robotics, School of Control Science and Engineering, Shandong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robotics, School of Control Science and Engineering, Shandong University,China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"Center for Robotics, School of Control Science and Engineering, Shandong University, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009366968","display_name":"Jian Bi","orcid":"https://orcid.org/0000-0003-4227-8329"},"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":"Jian Bi","raw_affiliation_strings":["Center for Robotics, School of Control Science and Engineering, Shandong University,China","Center for Robotics, School of Control Science and Engineering, Shandong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robotics, School of Control Science and Engineering, Shandong University,China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"Center for Robotics, School of Control Science and Engineering, Shandong University, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071826905","display_name":"Guanglin Lu","orcid":"https://orcid.org/0000-0001-5772-6441"},"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":"Guanglin Lu","raw_affiliation_strings":["Center for Robotics, School of Control Science and Engineering, Shandong University,China","Center for Robotics, School of Control Science and Engineering, Shandong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robotics, School of Control Science and Engineering, Shandong University,China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"Center for Robotics, School of Control Science and Engineering, Shandong University, 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":false,"raw_author_name":"Guoteng Zhang","raw_affiliation_strings":["Center for Robotics, School of Control Science and Engineering, Shandong University,China","Center for Robotics, School of Control Science and Engineering, Shandong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robotics, School of Control Science and Engineering, Shandong University,China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"Center for Robotics, School of Control Science and Engineering, Shandong University, 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":["Center for Robotics, School of Control Science and Engineering, Shandong University,China","Center for Robotics, School of Control Science and Engineering, Shandong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robotics, School of Control Science and Engineering, Shandong University,China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"Center for Robotics, School of Control Science and Engineering, Shandong University, China","institution_ids":["https://openalex.org/I154099455"]}]},{"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":["Center for Robotics, School of Control Science and Engineering, Shandong University,China","Center for Robotics, School of Control Science and Engineering, Shandong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robotics, School of Control Science and Engineering, Shandong University,China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"Center for Robotics, School of Control Science and Engineering, Shandong University, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"489","last_page":"494"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9988999962806702,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9866999983787537,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.7566249370574951},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7501665353775024},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6480402946472168},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5647141933441162},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5580861568450928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5292565226554871},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5120985507965088},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.42268800735473633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7566249370574951},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7501665353775024},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6480402946472168},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5647141933441162},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5580861568450928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5292565226554871},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5120985507965088},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.42268800735473633},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio55434.2022.10011921","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/robio55434.2022.10011921","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/G3724109181","display_name":null,"funder_award_id":"61973185,91948201,62003190","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G5032120977","display_name":null,"funder_award_id":"2021M691928","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"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"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2736601468","https://openalex.org/W2767050701","https://openalex.org/W2793035934","https://openalex.org/W2796290181","https://openalex.org/W2907537824","https://openalex.org/W2909331752","https://openalex.org/W2911087563","https://openalex.org/W2972810470","https://openalex.org/W3093922502","https://openalex.org/W3101442004","https://openalex.org/W3104515094","https://openalex.org/W3104876774","https://openalex.org/W3108412994","https://openalex.org/W3127816462","https://openalex.org/W3200962355","https://openalex.org/W3213886952","https://openalex.org/W3213974477","https://openalex.org/W3216772467","https://openalex.org/W4200273126","https://openalex.org/W4205475721","https://openalex.org/W4226143977","https://openalex.org/W4286963241","https://openalex.org/W6793715182","https://openalex.org/W6804601995"],"related_works":["https://openalex.org/W2357124094","https://openalex.org/W17155033","https://openalex.org/W2387399993","https://openalex.org/W2389739210","https://openalex.org/W2348924972","https://openalex.org/W2365736347","https://openalex.org/W2047454415","https://openalex.org/W2070040999","https://openalex.org/W3207760230","https://openalex.org/W1496222301"],"abstract_inverted_index":{"In":[0,35,78],"recent":[1],"years,":[2],"deep":[3],"reinforcement":[4],"learning":[5],"methods":[6],"provide":[7],"a":[8],"new":[9],"realization":[10],"idea":[11],"for":[12,50,72],"the":[13,17,22,27,52,59,73,84,96,103,111,119,123,126,131,134,150],"motion":[14],"control":[15],"of":[16,29,86,89,98,113],"quadruped":[18],"robot,":[19,136],"which":[20,109],"makes":[21],"neural":[23,42,90],"network":[24,43,49,91,114,121],"controller":[25],"have":[26],"characteristics":[28],"strong":[30,159],"adaptability":[31],"and":[32,61,75,101,129,146],"high":[33,87],"stability.":[34],"this":[36],"paper,":[37],"we":[38,94,117],"propose":[39],"an":[40,47,68],"end-to-end":[41],"framework":[44],"that,":[45],"contains":[46],"estimator":[48],"estimating":[51],"robot's":[53],"ontology":[54],"states":[55,65],"in":[56,80,107],"addition":[57],"to":[58,82,133],"critic":[60,74],"actor":[62,76],"networks.":[63,77],"These":[64],"serve":[66],"as":[67],"important":[69],"observation":[70],"data":[71],"addition,":[79],"order":[81],"solve":[83],"disadvantage":[85],"cost":[88],"training":[92,100,105],"time,":[93],"exploit":[95],"mechanism":[97],"parallel":[99],"deploy":[102],"entire":[104],"process":[106],"GPU,":[108],"improves":[110],"speed":[112],"convergence.":[115],"Finally,":[116],"reconstruct":[118],"forward":[120],"on":[122,144],"CPU":[124],"through":[125],"Eigen":[127],"library,":[128],"transfer":[130],"model":[132,143],"real":[135],"successfully":[137],"implementing":[138],"sim-to-real.":[139],"We":[140],"demonstrate":[141],"our":[142],"SDUQuad-48,":[145],"experiments":[147],"show":[148],"that":[149],"learned":[151],"policy":[152],"can":[153],"achieve":[154],"various":[155],"dynamic":[156],"motions":[157],"with":[158],"robustness.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}