{"id":"https://openalex.org/W4285129493","doi":"https://doi.org/10.1109/tase.2022.3185071","title":"Integrating Reinforcement Learning and Learning From Demonstrations to Learn Nonprehensile Manipulation","display_name":"Integrating Reinforcement Learning and Learning From Demonstrations to Learn Nonprehensile Manipulation","publication_year":2022,"publication_date":"2022-06-29","ids":{"openalex":"https://openalex.org/W4285129493","doi":"https://doi.org/10.1109/tase.2022.3185071"},"language":"en","primary_location":{"id":"doi:10.1109/tase.2022.3185071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2022.3185071","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","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/A5101559580","display_name":"Xilong Sun","orcid":"https://orcid.org/0000-0002-6093-9656"},"institutions":[{"id":"https://openalex.org/I117963711","display_name":"Kuban State University","ror":"https://ror.org/01yqewm58","country_code":"RU","type":"education","lineage":["https://openalex.org/I117963711"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN","RU"],"is_corresponding":true,"raw_author_name":"Xilong Sun","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","Department of Data Analysis and Artificial Intelligence, Kuban State University, Krasnodar, Russia"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Department of Data Analysis and Artificial Intelligence, Kuban State University, Krasnodar, Russia","institution_ids":["https://openalex.org/I117963711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101982308","display_name":"Jiqing Li","orcid":"https://orcid.org/0000-0003-3708-5573"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiqing Li","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041946248","display_name":"Anna Kovalenko","orcid":"https://orcid.org/0000-0002-3991-3953"},"institutions":[{"id":"https://openalex.org/I117963711","display_name":"Kuban State University","ror":"https://ror.org/01yqewm58","country_code":"RU","type":"education","lineage":["https://openalex.org/I117963711"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Anna Vladimirovna Kovalenko","raw_affiliation_strings":["Department of Data Analysis and Artificial Intelligence, Kuban State University, Krasnodar, Russia"],"affiliations":[{"raw_affiliation_string":"Department of Data Analysis and Artificial Intelligence, Kuban State University, Krasnodar, Russia","institution_ids":["https://openalex.org/I117963711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052037779","display_name":"Wei Feng","orcid":"https://orcid.org/0000-0002-9845-999X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Feng","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066181483","display_name":"Yongsheng Ou","orcid":"https://orcid.org/0000-0003-2998-267X"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongsheng Ou","raw_affiliation_strings":["CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, the Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, and the Guangdong Provincial Key Laboratory of Robotics and Intelligent System, Chinese Academy of Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, the Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, and the Guangdong Provincial Key Laboratory of Robotics and Intelligent System, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101559580"],"corresponding_institution_ids":["https://openalex.org/I117963711","https://openalex.org/I19820366","https://openalex.org/I4210145761"],"apc_list":null,"apc_paid":null,"fwci":2.3033,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.87907371,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"20","issue":"3","first_page":"1735","last_page":"1744"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9983999729156494,"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/T10784","display_name":"Muscle activation and electromyography studies","score":0.9911999702453613,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8202641010284424},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.743198573589325},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.6557449102401733},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6419054269790649},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6024782657623291},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5302179455757141},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4707781970500946},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46426060795783997},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4424659311771393},{"id":"https://openalex.org/keywords/motor-skill","display_name":"Motor skill","score":0.436139315366745},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4234158992767334},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.41305768489837646},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.38161739706993103},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.25931572914123535},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.21980881690979004},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08502647280693054}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8202641010284424},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.743198573589325},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.6557449102401733},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6419054269790649},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6024782657623291},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5302179455757141},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4707781970500946},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46426060795783997},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4424659311771393},{"id":"https://openalex.org/C169976356","wikidata":"https://www.wikidata.org/wiki/Q13208902","display_name":"Motor skill","level":2,"score":0.436139315366745},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4234158992767334},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41305768489837646},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.38161739706993103},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.25931572914123535},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.21980881690979004},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08502647280693054},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2022.3185071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2022.3185071","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1087713857","display_name":null,"funder_award_id":"2020B1515120054","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G1131464226","display_name":null,"funder_award_id":"2018AAA0103001","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3158545095","display_name":null,"funder_award_id":"62173319","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4847400861","display_name":null,"funder_award_id":"JCYJ20200109115610172","funder_id":"https://openalex.org/F4320329791","funder_display_name":"Shenzhen Fundamental Research Program"},{"id":"https://openalex.org/G7645412800","display_name":null,"funder_award_id":"62063006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8394717043","display_name":null,"funder_award_id":"U1813208","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"},{"id":"https://openalex.org/F4320329791","display_name":"Shenzhen Fundamental Research Program","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W130216483","https://openalex.org/W1495727713","https://openalex.org/W1793265611","https://openalex.org/W1885639605","https://openalex.org/W1944024997","https://openalex.org/W1974849157","https://openalex.org/W1975318316","https://openalex.org/W2021004298","https://openalex.org/W2042882799","https://openalex.org/W2074385457","https://openalex.org/W2088901594","https://openalex.org/W2108579172","https://openalex.org/W2110304639","https://openalex.org/W2127107099","https://openalex.org/W2127572219","https://openalex.org/W2128677288","https://openalex.org/W2129515556","https://openalex.org/W2136719407","https://openalex.org/W2149377129","https://openalex.org/W2155307968","https://openalex.org/W2161872510","https://openalex.org/W2166302491","https://openalex.org/W2167117957","https://openalex.org/W2172968643","https://openalex.org/W2409061534","https://openalex.org/W2982838649","https://openalex.org/W3016648415","https://openalex.org/W3080772040","https://openalex.org/W3081938247","https://openalex.org/W3089798071","https://openalex.org/W3131474428","https://openalex.org/W3197895136","https://openalex.org/W3201252281","https://openalex.org/W3209965475","https://openalex.org/W4211008118","https://openalex.org/W6682241156","https://openalex.org/W6803736998"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W4220829754","https://openalex.org/W2351343564","https://openalex.org/W2170052867","https://openalex.org/W2171010636"],"abstract_inverted_index":{"Motor":[0],"skills":[1,78],"are":[2,14,79],"essential":[3],"for":[4,95],"robots":[5,24,49],"to":[6,16,30,69,91,118,129,155,167,189,215],"accomplish":[7],"complicated":[8],"and":[9,42,88,133,184,206],"dexterous":[10],"manipulation":[11,113,151,223],"tasks,":[12],"which":[13],"difficult":[15],"be":[17],"mastered":[18],"through":[19],"traditional":[20],"controller":[21,94],"designs.":[22],"Currently,":[23],"learning":[25,65,85,90,135,142,175,177,211],"from":[26,35,50,86,126,178,203],"demonstrations":[27,87,179],"enable":[28],"them":[29],"learn":[31,92],"control":[32,72,182],"policies":[33],"automatically":[34],"human":[36],"motor":[37,54,77,97],"demonstrations.":[38],"However,":[39],"the":[40,45,53,71,127,139,149,159,165,169,173,181,186,191,198,204,209,218,221],"nonlinearity":[41],"instantaneousness":[43],"of":[44,122],"demonstrated":[46,192],"forces":[47],"prohibit":[48],"fully":[51],"mastering":[52],"skill":[55,141,174],"features":[56],"by":[57],"simply":[58],"exploiting":[59],"force":[60],"examples.":[61],"Therefore,":[62,158],"a":[63,93,110,201],"self-improvement":[64],"scheme":[66],"is":[67,102],"required":[68],"refine":[70],"policy":[73],"further":[74],"until":[75],"satisfactory":[76],"acquired.":[80],"Hence,":[81],"this":[82,123],"paper":[83,124],"combines":[84],"reinforcement":[89,210],"complex":[96],"skills.":[98],"The":[99],"proposed":[100],"method":[101],"validated":[103],"on":[104,148,208],"an":[105,131],"IIWA":[106],"KUKA":[107],"robot,":[108],"performing":[109],"specified":[111],"nonprehensile":[112,150,222],"task.":[114],"<italic":[115],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[116],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Note":[117],"Practitioners</i>":[119],"\u2014The":[120],"motivation":[121],"originates":[125],"requirement":[128],"develop":[130],"efficient":[132],"fast":[134],"algorithm":[136,212],"that":[137],"improves":[138],"robot":[140,160,187,199,219],"efficiency.":[143],"Specifically,":[144],"our":[145],"research":[146],"focuses":[147],"task,":[152],"easily":[153],"subject":[154],"environmental":[156],"changes.":[157],"must":[161],"continuously":[162],"interact":[163],"with":[164],"environment":[166],"master":[168],"skill.":[170,193,224],"To":[171],"accelerate":[172],"process,":[176],"initializes":[180],"policies,":[183],"then":[185],"starts":[188],"practice":[190,196],"After":[194],"each":[195],"round,":[197],"receives":[200],"reward":[202],"environment,":[205],"based":[207],"limited":[213],"up":[214],"100":[216],"trials,":[217],"masters":[220]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}