{"id":"https://openalex.org/W3201674474","doi":"https://doi.org/10.1109/tcds.2021.3118294","title":"A Novel Simulation-Reality Closed-Loop Learning Framework for Autonomous Robot Skill Learning","display_name":"A Novel Simulation-Reality Closed-Loop Learning Framework for Autonomous Robot Skill Learning","publication_year":2021,"publication_date":"2021-10-07","ids":{"openalex":"https://openalex.org/W3201674474","doi":"https://doi.org/10.1109/tcds.2021.3118294","mag":"3201674474"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2021.3118294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2021.3118294","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","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/A5102022958","display_name":"Rong Jiang","orcid":"https://orcid.org/0000-0001-9908-7617"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rong Jiang","raw_affiliation_strings":["Department of Control Science and Engineering, Tongji University, Shanghai, China","Frontiers Science Center for Intelligent Autonomous Systems, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Control Science and Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Frontiers Science Center for Intelligent Autonomous Systems, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049557511","display_name":"Bin He","orcid":"https://orcid.org/0000-0003-3193-6269"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin He","raw_affiliation_strings":["Department of Control Science and Engineering, Tongji University, Shanghai, China","Frontiers Science Center for Intelligent Autonomous Systems, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Control Science and Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Frontiers Science Center for Intelligent Autonomous Systems, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100424178","display_name":"Zhipeng Wang","orcid":"https://orcid.org/0000-0003-4632-9170"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]},{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhipeng Wang","raw_affiliation_strings":["Department of Control Science and Engineering, Tongji University, Shanghai, China","Beijing Advanced Innovation Center for Intelligent Robots and Systems, Beijing Institute of Technology, Beijing, China","Frontiers Science Center for Intelligent Autonomous Systems, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Control Science and Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Beijing Advanced Innovation Center for Intelligent Robots and Systems, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Frontiers Science Center for Intelligent Autonomous Systems, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032983330","display_name":"Yanmin Zhou","orcid":"https://orcid.org/0000-0001-7824-1179"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Zhou","raw_affiliation_strings":["Department of Control Science and Engineering, Tongji University, Shanghai, China","Frontiers Science Center for Intelligent Autonomous Systems, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Control Science and Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Frontiers Science Center for Intelligent Autonomous Systems, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011827358","display_name":"Shoulin Xu","orcid":"https://orcid.org/0000-0002-7075-7872"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shoulin Xu","raw_affiliation_strings":["Department of Control Science and Engineering, Tongji University, Shanghai, China","Frontiers Science Center for Intelligent Autonomous Systems, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Control Science and Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Frontiers Science Center for Intelligent Autonomous Systems, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100353701","display_name":"Xin Li","orcid":"https://orcid.org/0000-0001-6003-7719"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["Department of Control Science and Engineering, Tongji University, Shanghai, China","Frontiers Science Center for Intelligent Autonomous Systems, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Control Science and Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Frontiers Science Center for Intelligent Autonomous Systems, Shanghai, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102022958"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":1.2237,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.83477902,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"14","issue":"4","first_page":"1520","last_page":"1531"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.998199999332428,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9962000250816345,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8375650644302368},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6795480251312256},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.602744996547699},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5407419800758362},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.491129606962204},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45257797837257385},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4314650893211365},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4192246198654175},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.34257927536964417},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.30567002296447754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8375650644302368},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6795480251312256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.602744996547699},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5407419800758362},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.491129606962204},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45257797837257385},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4314650893211365},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4192246198654175},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.34257927536964417},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30567002296447754},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2021.3118294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2021.3118294","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2216098178","display_name":null,"funder_award_id":"62003242","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2552637886","display_name":null,"funder_award_id":"61825303","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4456576707","display_name":null,"funder_award_id":"U1713215","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6903526350","display_name":null,"funder_award_id":"51975415","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7704450024","display_name":null,"funder_award_id":"2019IRS04","funder_id":"https://openalex.org/F4320335791","funder_display_name":"Beijing Advanced Innovation Center for Intelligent Robots and Systems, Beijing Institute of Technology"},{"id":"https://openalex.org/G7719261434","display_name":null,"funder_award_id":"2020AAA0108905","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335791","display_name":"Beijing Advanced Innovation Center for Intelligent Robots and Systems, Beijing Institute of Technology","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2127412976","https://openalex.org/W2145339207","https://openalex.org/W2558355904","https://openalex.org/W2605102758","https://openalex.org/W2634239194","https://openalex.org/W2781585732","https://openalex.org/W2790924949","https://openalex.org/W2810785043","https://openalex.org/W2962793481","https://openalex.org/W2962808524","https://openalex.org/W2962887844","https://openalex.org/W2962894046","https://openalex.org/W2962899390","https://openalex.org/W2963184124","https://openalex.org/W2963390419","https://openalex.org/W2963634205","https://openalex.org/W2963669336","https://openalex.org/W2963713397","https://openalex.org/W2963864421","https://openalex.org/W2964157221","https://openalex.org/W2964198579","https://openalex.org/W2969277962","https://openalex.org/W2969329576","https://openalex.org/W2975504670","https://openalex.org/W2986925736","https://openalex.org/W2998381804","https://openalex.org/W3005451807","https://openalex.org/W3011732969","https://openalex.org/W3016392643","https://openalex.org/W3049043369","https://openalex.org/W4297818513","https://openalex.org/W6740023956","https://openalex.org/W6746282794"],"related_works":["https://openalex.org/W2122871747","https://openalex.org/W3114279067","https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W4220829754","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W2351343564"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"data-driven":[3],"learning":[4,49,55,108],"methods":[5,17],"have":[6],"been":[7],"widely":[8],"studied":[9],"for":[10,26,51,173],"autonomous":[11,52,175],"robot":[12,53],"skill":[13,54,176],"learning.":[14,177],"However,":[15],"these":[16],"rely":[18],"on":[19],"large":[20],"amounts":[21],"of":[22,161],"robot\u2013environment":[23],"interaction":[24],"data":[25,59],"training,":[27],"which":[28,101],"largely":[29],"prevents":[30],"them":[31],"from":[32],"being":[33],"applied":[34],"to":[35,94,106,121,125],"real-world":[36],"robots.":[37],"To":[38],"address":[39],"this":[40,42],"problem,":[41],"article":[43],"proposes":[44],"a":[45,72,111,147],"novel":[46,112],"simulation-reality":[47],"closed-loop":[48],"framework":[50],"that":[56],"can":[57,102,139],"improve":[58,107],"efficiency,":[60],"enhance":[61],"policy":[62,67,81,135],"stability,":[63],"and":[64,85,170],"achieve":[65],"effective":[66],"simulation-to-reality":[68],"(sim2real)":[69],"transfer.":[70],"First,":[71],"hybrid":[73],"control":[74,89],"model":[75,84,91],"combining":[76],"the":[77,86,131,152,159,162],"asymmetric":[78],"deep":[79],"deterministic":[80],"gradients":[82],"(Asym-DDPGs)":[83],"forward":[87],"prediction":[88],"(FPC)":[90],"is":[92,119],"proposed":[93,163],"learn":[95],"vision-based":[96],"manipulation":[97],"policies":[98],"in":[99,137,146],"simulations,":[100],"decompose":[103],"complex":[104],"tasks":[105],"efficiency.":[109],"Second,":[110],"pixel-level":[113],"domain":[114],"adaptation":[115],"method":[116],"named":[117],"Position-CycleGAN":[118,153],"designed":[120],"translate":[122],"real":[123,144],"images":[124,127],"simulated":[126],"while":[128],"also":[129],"preserving":[130],"task-related":[132],"information.":[133],"The":[134,155],"trained":[136],"simulations":[138],"be":[140],"directly":[141],"migrated":[142],"into":[143],"robots":[145],"reverse":[148],"reality-to-simulation":[149],"manner":[150],"using":[151],"model.":[154],"experimental":[156],"results":[157],"validate":[158],"effectiveness":[160],"framework.":[164],"This":[165],"work":[166],"provides":[167],"an":[168],"efficient":[169],"feasible":[171],"path":[172],"achieving":[174]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}