{"id":"https://openalex.org/W3197992384","doi":"https://doi.org/10.1109/acirs52449.2021.9519311","title":"Sim-to-Real Transfer with Action Mapping and State Prediction for Robot Motion Control","display_name":"Sim-to-Real Transfer with Action Mapping and State Prediction for Robot Motion Control","publication_year":2021,"publication_date":"2021-07-16","ids":{"openalex":"https://openalex.org/W3197992384","doi":"https://doi.org/10.1109/acirs52449.2021.9519311","mag":"3197992384"},"language":"en","primary_location":{"id":"doi:10.1109/acirs52449.2021.9519311","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acirs52449.2021.9519311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 6th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","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/A5059444883","display_name":"Xianjin Zhu","orcid":"https://orcid.org/0000-0001-8894-5700"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianjin Zhu","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005464184","display_name":"Xudong Zheng","orcid":"https://orcid.org/0000-0002-9056-2116"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xudong Zheng","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100739520","display_name":"Qiyuan Zhang","orcid":"https://orcid.org/0000-0002-8519-4259"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiyuan Zhang","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452418","display_name":"Zhang Chen","orcid":"https://orcid.org/0000-0003-4498-1165"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang Chen","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068679305","display_name":"Yu Liu","orcid":"https://orcid.org/0000-0002-4191-5974"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Liu","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101626172","display_name":"Bin Liang","orcid":"https://orcid.org/0000-0001-6310-6214"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Liang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4166,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.61520363,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9969000220298767,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9969000220298767,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9957000017166138,"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":0.9941999912261963,"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/robot","display_name":"Robot","score":0.7013620138168335},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6805523633956909},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.6456024646759033},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6025917530059814},{"id":"https://openalex.org/keywords/compensation","display_name":"Compensation (psychology)","score":0.5958942770957947},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5891070365905762},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5612362027168274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5254392027854919},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.49592718482017517},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.47895413637161255},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.43802303075790405},{"id":"https://openalex.org/keywords/motion-control","display_name":"Motion control","score":0.42143091559410095},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.38201379776000977},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.31098225712776184},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2755504548549652},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22706085443496704},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.0882284939289093}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7013620138168335},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6805523633956909},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.6456024646759033},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6025917530059814},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.5958942770957947},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5891070365905762},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5612362027168274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5254392027854919},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.49592718482017517},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.47895413637161255},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.43802303075790405},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.42143091559410095},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.38201379776000977},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.31098225712776184},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2755504548549652},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22706085443496704},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.0882284939289093},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acirs52449.2021.9519311","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acirs52449.2021.9519311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 6th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"No poverty","score":0.550000011920929,"id":"https://metadata.un.org/sdg/1"}],"awards":[{"id":"https://openalex.org/G465563164","display_name":null,"funder_award_id":"62073183,61903219","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1845972764","https://openalex.org/W2121863487","https://openalex.org/W2341171179","https://openalex.org/W2530944449","https://openalex.org/W2605102758","https://openalex.org/W2888499542","https://openalex.org/W2960705509","https://openalex.org/W2973454014","https://openalex.org/W2990747716","https://openalex.org/W3013562692","https://openalex.org/W3013699912","https://openalex.org/W3101442004","https://openalex.org/W3121342653","https://openalex.org/W3128189070","https://openalex.org/W3135759888","https://openalex.org/W3140042148","https://openalex.org/W3161634385","https://openalex.org/W4237591687","https://openalex.org/W6639175102","https://openalex.org/W6736179038","https://openalex.org/W6775891677","https://openalex.org/W6789246195","https://openalex.org/W6795052775","https://openalex.org/W6966558720"],"related_works":["https://openalex.org/W962423920","https://openalex.org/W2387968248","https://openalex.org/W2350715914","https://openalex.org/W2120821724","https://openalex.org/W2379529020","https://openalex.org/W2101175215","https://openalex.org/W2893549521","https://openalex.org/W2979398413","https://openalex.org/W1532677580","https://openalex.org/W2386719143"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2],"(DRL)":[3],"has":[4,46],"been":[5],"proved":[6],"to":[7,42,169],"be":[8],"a":[9,21,62,90],"very":[10],"promising":[11],"method":[12,117,134],"for":[13],"robot":[14],"motion":[15],"control.":[16],"However,":[17],"it":[18,45],"usually":[19],"needs":[20],"large":[22],"number":[23],"of":[24,49,58,81,167,184],"samples":[25],"in":[26,32,40,54,65,105,135,140,149,164],"training,":[27],"which":[28,67,100,180],"restricts":[29],"its":[30],"application":[31],"real-world":[33],"robots.":[34],"Sim-to-Real":[35],"means":[36],"transferring":[37],"training":[38,106],"strategies":[39],"simulation":[41,172],"reality,":[43],"and":[44,79,96,113,126,145,157,177],"become":[47],"one":[48],"the":[50,146,150,165,170,182],"hottest":[51],"research":[52],"areas":[53],"recent":[55],"years.":[56],"Embodiment":[57],"DRL":[59],"algorithms":[60],"is":[61,68,138,161],"necessary":[63],"step":[64],"Sim-to-Real,":[66],"faced":[69],"with":[70,153,174],"many":[71],"challenges,":[72],"such":[73],"as":[74],"poor":[75],"sample":[76],"efficiency,":[77],"wear":[78],"tear":[80],"robots,":[82],"safety,":[83],"etc.":[84],"In":[85],"this":[86,136],"paper,":[87],"we":[88],"present":[89],"new":[91],"algorithm":[92],"called":[93],"action":[94,111,114,124,155,159,175,178],"mapping":[95],"state":[97,131],"prediction":[98],"(AMSP),":[99],"considers":[101],"three":[102],"main":[103],"factors":[104],"including":[107],"inaccurate":[108],"parameters,":[109],"unmodeled":[110],"damping":[112,156,176],"delay.":[115],"This":[116],"includes":[118],"model":[119],"error":[120],"compensation":[121,128],"based":[122,129],"on":[123,130],"mapping,":[125],"delay":[127,160],"prediction.":[132],"The":[133],"paper":[137],"demonstrated":[139],"OpenAI":[141],"inverted":[142],"pendulum":[143],"environment,":[144],"strategy":[147],"trained":[148],"ideal":[151],"environments":[152],"no":[154,158],"successfully":[162],"transferred":[163],"form":[166],"zero-shot":[168],"artificial":[171],"environment":[173],"delay,":[179],"shows":[181],"effectiveness":[183],"AMSP.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}