{"id":"https://openalex.org/W4294936113","doi":"https://doi.org/10.1017/s0263574722001230","title":"Zero-shot sim-to-real transfer of reinforcement learning framework for robotics manipulation with demonstration and force feedback","display_name":"Zero-shot sim-to-real transfer of reinforcement learning framework for robotics manipulation with demonstration and force feedback","publication_year":2022,"publication_date":"2022-09-07","ids":{"openalex":"https://openalex.org/W4294936113","doi":"https://doi.org/10.1017/s0263574722001230"},"language":"en","primary_location":{"id":"doi:10.1017/s0263574722001230","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s0263574722001230","pdf_url":null,"source":{"id":"https://openalex.org/S92163612","display_name":"Robotica","issn_l":"0263-5747","issn":["0263-5747","1469-8668"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotica","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/A5018250214","display_name":"Yuanpei Chen","orcid":"https://orcid.org/0000-0002-0033-492X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanpei Chen","raw_affiliation_strings":["College of Automation Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0033-492X","affiliations":[{"raw_affiliation_string":"College of Automation Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101850792","display_name":"Chao Zeng","orcid":"https://orcid.org/0000-0001-8685-8101"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zeng","raw_affiliation_strings":["School of Automation, Guangdong University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100387995","display_name":"Zhiping Wang","orcid":"https://orcid.org/0000-0002-6438-1418"},"institutions":[{"id":"https://openalex.org/I2799850029","display_name":"Dongguan University of Technology","ror":"https://ror.org/01m8p7q42","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799850029"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiping Wang","raw_affiliation_strings":["School of Electronic Engineering, Dongguan University of Technology, Dongguan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Dongguan University of Technology, Dongguan, China","institution_ids":["https://openalex.org/I2799850029"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017071421","display_name":"Peng Lu","orcid":"https://orcid.org/0000-0001-5611-4902"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Peng Lu","raw_affiliation_strings":["Department of Mechanical Engineering, The University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019906827","display_name":"Chenguang Yang","orcid":"https://orcid.org/0000-0001-5255-5559"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenguang Yang","raw_affiliation_strings":["College of Automation Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Automation Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5019906827"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":1.1809,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82075028,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"41","issue":"3","first_page":"1015","last_page":"1024"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.983299970626831,"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":0.983299970626831,"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":0.9810000061988831,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9053000211715698,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7424054741859436},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6509488821029663},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5403376817703247},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5069325566291809},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4843105375766754},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.48146024346351624},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4384111166000366},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.3751299977302551}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7424054741859436},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6509488821029663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5403376817703247},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5069325566291809},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4843105375766754},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.48146024346351624},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4384111166000366},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3751299977302551},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s0263574722001230","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s0263574722001230","pdf_url":null,"source":{"id":"https://openalex.org/S92163612","display_name":"Robotica","issn_l":"0263-5747","issn":["0263-5747","1469-8668"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotica","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2173248099","https://openalex.org/W2530944449","https://openalex.org/W2605102758","https://openalex.org/W2605368761","https://openalex.org/W2767050701","https://openalex.org/W2788862220","https://openalex.org/W2904246096","https://openalex.org/W2930863966","https://openalex.org/W2968116426","https://openalex.org/W2981664222","https://openalex.org/W2990747716","https://openalex.org/W3003629310","https://openalex.org/W3028308378","https://openalex.org/W3041382148","https://openalex.org/W3088310808","https://openalex.org/W3100172161","https://openalex.org/W3101442004","https://openalex.org/W3108395128","https://openalex.org/W3120778962","https://openalex.org/W3127166206","https://openalex.org/W3167796319","https://openalex.org/W3176646219","https://openalex.org/W3193576605","https://openalex.org/W3203483019"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W1508899372"],"abstract_inverted_index":{"Abstract":[0],"In":[1,79],"the":[2,9,19,40,63,66,80,93,104,120,130,134,143,151,159],"field":[3],"of":[4,23,52],"robot":[5],"reinforcement":[6],"learning":[7],"(RL),":[8],"reality":[10,45,125,160],"gap":[11,161],"has":[12],"always":[13],"been":[14],"a":[15,31,53,72,88],"problem":[16],"that":[17,35,154],"restricts":[18],"robustness":[20],"and":[21,56,76,86,124,127],"generalization":[22],"algorithms.":[24],"We":[25,61,141],"propose":[26],"Simulation":[27],"Twin":[28],"(SimTwin)":[29],":":[30],"deep":[32],"RL":[33,54],"framework":[34,156],"can":[36,157],"help":[37],"directly":[38],"transfer":[39],"model":[41],"from":[42],"simulation":[43],"to":[44,91,111],"without":[46,138,162],"any":[47,163],"real-world":[48,113,164],"training.":[49,140,165],"SimTwin":[50],"consists":[51],"module":[55],"an":[57,147],"adaptive":[58,81],"correct":[59,82,115,131],"module.":[60],"train":[62,87],"policy":[64,136],"using":[65,98],"soft":[67],"actor-critic":[68],"algorithm":[69],"only":[70],"in":[71,146],"simulator":[73,116,123],"with":[74],"demonstration":[75],"domain":[77],"randomization.":[78],"module,":[83],"we":[84,102],"design":[85],"neural":[89],"network":[90,137],"simulate":[92],"human":[94],"error":[95],"correction":[96],"process":[97],"force":[99],"feedback.":[100],"Subsequently,":[101],"combine":[103],"above":[105],"two":[106],"modules":[107],"through":[108,133],"digital":[109],"twin":[110],"control":[112],"robots,":[114],"parameters":[117],"by":[118],"comparing":[119],"difference":[121],"between":[122],"automatically,":[126],"then":[128],"generalize":[129],"action":[132],"trained":[135],"additional":[139],"demonstrate":[142],"proposed":[144],"method":[145],"open":[148],"cabinet":[149],"task;":[150],"experiments":[152],"show":[153],"our":[155],"reduce":[158]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}