{"id":"https://openalex.org/W2974295111","doi":"https://doi.org/10.1109/coase.2019.8842940","title":"Deep Reinforcement Learning of Robotic Precision Insertion Skill Accelerated by Demonstrations","display_name":"Deep Reinforcement Learning of Robotic Precision Insertion Skill Accelerated by Demonstrations","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W2974295111","doi":"https://doi.org/10.1109/coase.2019.8842940","mag":"2974295111"},"language":"en","primary_location":{"id":"doi:10.1109/coase.2019.8842940","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coase.2019.8842940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)","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/A5048839869","display_name":"Xiapeng Wu","orcid":null},"institutions":[{"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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiapeng Wu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115601773","display_name":"Dapeng Zhang","orcid":"https://orcid.org/0000-0001-7349-8709"},"institutions":[{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dapeng Zhang","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003819876","display_name":"Fangbo Qin","orcid":"https://orcid.org/0000-0002-4085-0857"},"institutions":[{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangbo Qin","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109133403","display_name":"De Xu","orcid":null},"institutions":[{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"De Xu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5048839869"],"corresponding_institution_ids":["https://openalex.org/I4210100255"],"apc_list":null,"apc_paid":null,"fwci":1.9958,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.86897792,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9932000041007996,"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/T10571","display_name":"Robotic Mechanisms and Dynamics","score":0.9923999905586243,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.80238938331604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7670255303382874},{"id":"https://openalex.org/keywords/torque","display_name":"Torque","score":0.5503928661346436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5296534895896912},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5203656554222107},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5167180895805359},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5020864009857178},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.45956188440322876},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4394076466560364},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4384458661079407},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41544508934020996},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.3409882187843323},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10900399088859558}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.80238938331604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7670255303382874},{"id":"https://openalex.org/C144171764","wikidata":"https://www.wikidata.org/wiki/Q48103","display_name":"Torque","level":2,"score":0.5503928661346436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5296534895896912},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5203656554222107},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5167180895805359},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5020864009857178},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.45956188440322876},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4394076466560364},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4384458661079407},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41544508934020996},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3409882187843323},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10900399088859558},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/coase.2019.8842940","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coase.2019.8842940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1522301498","https://openalex.org/W2019875988","https://openalex.org/W2046756261","https://openalex.org/W2056262117","https://openalex.org/W2113486533","https://openalex.org/W2121092017","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2201581102","https://openalex.org/W2244849828","https://openalex.org/W2415726935","https://openalex.org/W2592733455","https://openalex.org/W2788862220","https://openalex.org/W2926550000","https://openalex.org/W2951799221","https://openalex.org/W2962736495","https://openalex.org/W4297686387","https://openalex.org/W6631190155","https://openalex.org/W6677939520","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6690960878","https://openalex.org/W6716193690","https://openalex.org/W6752818329"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W20361778"],"abstract_inverted_index":{"Automatic":[0],"high":[1],"precision":[2,15,39,150],"assembly":[3,16,151],"of":[4,38],"millimeter":[5],"sized":[6],"objects":[7],"is":[8,52,109,131,141],"a":[9,91,149],"challenging":[10],"task.":[11],"Traditional":[12],"methods":[13],"for":[14],"rely":[17],"on":[18,44,83,134,148],"explicit":[19],"programming":[20],"with":[21,143],"real":[22],"robot":[23],"system,":[24],"and":[25,65,73,126],"require":[26],"complex":[27],"parameter-tuning":[28],"work.":[29],"In":[30,119],"this":[31],"paper,":[32],"we":[33],"realize":[34],"deep":[35,47],"reinforcement":[36],"learning":[37,103],"insertion":[40,124,128,146],"skill":[41,88],"learning,":[42],"based":[43,133],"prioritized":[45],"dueling":[46],"Q-network":[48],"(DQN).":[49],"The":[50],"Q-function":[51],"represented":[53],"by":[54],"the":[55,68,74,79,84,87,96,102,105,113,116,123,135,144],"long":[56],"short":[57],"term":[58],"memory":[59],"(LSTM)":[60],"neural":[61],"network,":[62],"whose":[63],"input":[64],"output":[66],"are":[67],"raw":[69],"6D":[70],"force-torque":[71],"feedback":[72],"Q-value,":[75],"respectively.":[76],"According":[77],"to":[78,111,121],"Q":[80],"values":[81],"conditioned":[82],"current":[85],"state,":[86],"model":[89,114],"selects":[90],"6":[92],"degree-of-freedom":[93],"action":[94,98],"from":[95,107],"predefined":[97],"set.":[99],"To":[100],"accelerate":[101],"process,":[104],"data":[106],"demonstrations":[108],"used":[110],"pre-train":[112],"before":[115],"DQN":[117],"starts.":[118],"order":[120],"improve":[122],"efficiency":[125],"safety,":[127],"step":[129],"length":[130],"modulated":[132],"instant":[136],"reward.":[137],"Our":[138],"proposed":[139],"method":[140],"validated":[142],"peg-in-hole":[145],"experiments":[147],"robot.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}