{"id":"https://openalex.org/W4320015882","doi":"https://doi.org/10.1109/tii.2023.3240936","title":"Hierarchical Policy Learning With Demonstration Learning for Robotic Multiple Peg-in-Hole Assembly Tasks","display_name":"Hierarchical Policy Learning With Demonstration Learning for Robotic Multiple Peg-in-Hole Assembly Tasks","publication_year":2023,"publication_date":"2023-01-30","ids":{"openalex":"https://openalex.org/W4320015882","doi":"https://doi.org/10.1109/tii.2023.3240936"},"language":"en","primary_location":{"id":"doi:10.1109/tii.2023.3240936","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2023.3240936","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"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 Industrial Informatics","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/A5026518190","display_name":"Shaohua Yan","orcid":"https://orcid.org/0000-0002-2575-1447"},"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/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaohua Yan","raw_affiliation_strings":["Research Center of Precision Sensing and Control, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2575-1447","affiliations":[{"raw_affiliation_string":"Research Center of Precision Sensing and Control, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016826662","display_name":"De Xu","orcid":"https://orcid.org/0000-0002-7221-1654"},"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/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"De Xu","raw_affiliation_strings":["Research Center of Precision Sensing and Control, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7221-1654","affiliations":[{"raw_affiliation_string":"Research Center of Precision Sensing and Control, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082921939","display_name":"Xian Tao","orcid":"https://orcid.org/0000-0001-5834-5181"},"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/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Tao","raw_affiliation_strings":["Research Center of Precision Sensing and Control, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5834-5181","affiliations":[{"raw_affiliation_string":"Research Center of Precision Sensing and Control, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.7434,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.9556373,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"19","issue":"10","first_page":"10254","last_page":"10264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9984999895095825,"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":0.9984999895095825,"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/T11159","display_name":"Manufacturing Process and Optimization","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T12190","display_name":"Innovations in Concrete and Construction Materials","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/adaptability","display_name":"Adaptability","score":0.6372931599617004},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6340363025665283},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5162243843078613},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5035390257835388},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4997584819793701},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4572429955005646},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42449167370796204},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33183467388153076}],"concepts":[{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.6372931599617004},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6340363025665283},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5162243843078613},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5035390257835388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4997584819793701},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4572429955005646},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42449167370796204},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33183467388153076},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/tii.2023.3240936","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2023.3240936","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"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 Industrial Informatics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7217911764","display_name":null,"funder_award_id":"62273341","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1838334173","https://openalex.org/W2056262117","https://openalex.org/W2116469148","https://openalex.org/W2575705757","https://openalex.org/W2745370328","https://openalex.org/W2787938642","https://openalex.org/W2806263811","https://openalex.org/W2890218953","https://openalex.org/W2909559431","https://openalex.org/W2912019653","https://openalex.org/W2949267040","https://openalex.org/W2959488596","https://openalex.org/W2963262099","https://openalex.org/W2963864421","https://openalex.org/W2968719199","https://openalex.org/W3035866614","https://openalex.org/W3044425366","https://openalex.org/W3081877091","https://openalex.org/W3089337217","https://openalex.org/W3091182627","https://openalex.org/W3109467707","https://openalex.org/W3133076360","https://openalex.org/W3205745479","https://openalex.org/W3215032844","https://openalex.org/W4200220032","https://openalex.org/W4206106108","https://openalex.org/W4210370593","https://openalex.org/W4255661557","https://openalex.org/W4298857966","https://openalex.org/W4300799055","https://openalex.org/W6637967152","https://openalex.org/W6684921986","https://openalex.org/W6703271639","https://openalex.org/W6734215269","https://openalex.org/W6740801417","https://openalex.org/W6748839928"],"related_works":["https://openalex.org/W2357124094","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/W2387293848","https://openalex.org/W3121791438","https://openalex.org/W2250140200"],"abstract_inverted_index":{"The":[0,102,142],"force-based":[1],"control":[2,20,28,40,95],"algorithm":[3,36,41,46,58,96,99,132],"of":[4,15,18,26,85,105,126,148],"robotic":[5],"multiple":[6],"peg-in-hole":[7],"assembly":[8,52,128],"is":[9,47,100,109,118,133],"a":[10,30,62,115],"challenge.":[11],"For":[12],"the":[13,51,55,66,83,122,146,149],"difficulty":[14],"low":[16,23],"adaptability":[17],"model-based":[19],"algorithms":[21,108],"and":[22,42,97,124,139],"learning":[24,34,44],"efficiency":[25],"model-free":[27],"algorithms,":[29],"goal-based":[31,56],"hierarchical":[32],"policy":[33,91],"(HPL)":[35],"that":[37,92],"combines":[38,93],"conventional":[39,94],"demonstration":[43],"(DL)":[45],"proposed":[48,150],"to":[49,65,81,120],"learn":[50],"skill.":[53],"First,":[54],"HPL":[57,112],"adds":[59],"goal":[60],"as":[61,79],"new":[63],"variable":[64],"action":[67],"value":[68],"function.":[69],"Multiple":[70],"states":[71],"reached":[72],"in":[73,136],"each":[74],"episode":[75],"are":[76],"randomly":[77],"selected":[78],"subgoals":[80],"improve":[82],"distribution":[84],"positive":[86],"rewards.":[87],"Second,":[88],"an":[89],"initial":[90],"DL":[98],"designed.":[101],"combined":[103],"coefficient":[104],"these":[106],"two":[107],"learned":[110],"by":[111],"algorithm.":[113],"Finally,":[114],"conical":[116],"surface":[117],"used":[119],"compute":[121],"forces":[123],"moments":[125],"simplified":[127],"simulation":[129,138],"model.":[130],"Our":[131],"well":[134],"implemented":[135],"both":[137],"real-world":[140],"environments.":[141],"experimental":[143],"results":[144],"verify":[145],"effectiveness":[147],"method.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}