{"id":"https://openalex.org/W4367663367","doi":"https://doi.org/10.1109/mra.2023.3262461","title":"Mastering the Complex Assembly Task With a Dual-Arm Robot: A Novel Reinforcement Learning Method","display_name":"Mastering the Complex Assembly Task With a Dual-Arm Robot: A Novel Reinforcement Learning Method","publication_year":2023,"publication_date":"2023-05-01","ids":{"openalex":"https://openalex.org/W4367663367","doi":"https://doi.org/10.1109/mra.2023.3262461"},"language":"en","primary_location":{"id":"doi:10.1109/mra.2023.3262461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mra.2023.3262461","pdf_url":null,"source":{"id":"https://openalex.org/S132261465","display_name":"IEEE Robotics & Automation Magazine","issn_l":"1070-9932","issn":["1070-9932","1558-223X"],"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 Robotics & Automation Magazine","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/A5042252206","display_name":"Daqi Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Daqi Jiang","raw_affiliation_strings":["School of Mechanical Engineering and Automation, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0001-6131-2057","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering and Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101974436","display_name":"Hong Wang","orcid":"https://orcid.org/0000-0002-7639-6967"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Wang","raw_affiliation_strings":["School of Mechanical Engineering and Automation, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0002-7639-6967","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering and Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019048736","display_name":"Yanzheng Lu","orcid":"https://orcid.org/0000-0002-1573-5419"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanzheng Lu","raw_affiliation_strings":["School of Mechanical Engineering and Automation, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0002-1573-5419","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering and Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5042252206"],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":5.7215,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.96671431,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"30","issue":"2","first_page":"57","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9968000054359436,"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/T11159","display_name":"Manufacturing Process and Optimization","score":0.9824000000953674,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7955911159515381},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7000997066497803},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6949884295463562},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6649783253669739},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5828187465667725},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5037683844566345},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4836536645889282},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.45692208409309387},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4500763714313507},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4440074563026428},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43657395243644714},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4300861060619354},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.35370808839797974},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1951560080051422}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7955911159515381},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7000997066497803},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6949884295463562},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6649783253669739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5828187465667725},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5037683844566345},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4836536645889282},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.45692208409309387},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4500763714313507},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4440074563026428},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43657395243644714},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4300861060619354},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.35370808839797974},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1951560080051422},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mra.2023.3262461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mra.2023.3262461","pdf_url":null,"source":{"id":"https://openalex.org/S132261465","display_name":"IEEE Robotics & Automation Magazine","issn_l":"1070-9932","issn":["1070-9932","1558-223X"],"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 Robotics & Automation Magazine","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W1665214252","https://openalex.org/W1771410628","https://openalex.org/W2026653933","https://openalex.org/W2736601468","https://openalex.org/W2781726626","https://openalex.org/W2902907165","https://openalex.org/W2911087563","https://openalex.org/W2950069298","https://openalex.org/W2963184939","https://openalex.org/W2963277051","https://openalex.org/W2964043796","https://openalex.org/W3091471537","https://openalex.org/W4205123165","https://openalex.org/W4250666038","https://openalex.org/W4286905708","https://openalex.org/W4287118130","https://openalex.org/W4298857966","https://openalex.org/W6618372016","https://openalex.org/W6637242042","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6692846177","https://openalex.org/W6718092244","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6802188089","https://openalex.org/W6802395018"],"related_works":["https://openalex.org/W4206589974","https://openalex.org/W2087751887","https://openalex.org/W2984863875","https://openalex.org/W3119646977","https://openalex.org/W3009197110","https://openalex.org/W1986600972","https://openalex.org/W2693300019","https://openalex.org/W2072219812","https://openalex.org/W1961973183","https://openalex.org/W1534851618"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,79],"(DRL)":[3],"has":[4],"achieved":[5],"great":[6],"success":[7],"across":[8],"multiple":[9],"fields;":[10],"however,":[11],"in":[12,50,73,103],"the":[13,18,57,60,71,85,88,95,100,104,122,125,132,139,144],"field":[14],"of":[15,20,23,48,106,112,115,124],"robot":[16,97,141],"control,":[17],"acquisition":[19],"large":[21,46,129],"amounts":[22],"motion":[24],"data":[25,49],"from":[26],"real":[27,61,89,140],"robots":[28],"is":[29,36,67,81],"challenging.":[30],"In":[31,127],"this":[32],"work,":[33],"an":[34],"algorithm":[35,92,134],"proposed":[37,133],"to":[38,59,69,83,87,98,120],"train":[39,70],"a":[40,45,51,128],"neural":[41],"network":[42],"model":[43,58,86],"with":[44],"amount":[47],"simulated":[52],"environment":[53],"and":[54,75,138,151],"then":[55],"transfer":[56,84],"environment.":[62],"Proximal":[63],"policy":[64],"optimization":[65],"(PPO)":[66],"used":[68],"agent":[72],"simulator,":[74],"generative":[76],"adversarial":[77],"imitation":[78],"(GAIL)":[80],"specified":[82],"world.":[90],"The":[91],"can":[93],"guide":[94],"two-armed":[96],"complete":[99],"task":[101,146],"well":[102],"face":[105],"complex":[107],"assembly":[108,145],"tasks.":[109],"A":[110],"total":[111],"three":[113],"tasks":[114],"different":[116],"difficulties":[117],"were":[118],"set":[119],"test":[121],"performance":[123],"algorithm.":[126],"experimental":[130],"study,":[131],"outperforms":[135],"other":[136],"algorithms,":[137],"arm":[142],"completes":[143],"significantly":[147],"faster":[148],"than":[149],"script":[150],"keyboard":[152],"operations.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}