{"id":"https://openalex.org/W2980348817","doi":"https://doi.org/10.1109/aim.2019.8868579","title":"Manipulation Skill Acquisition for Robotic Assembly using Deep Reinforcement Learning","display_name":"Manipulation Skill Acquisition for Robotic Assembly using Deep Reinforcement Learning","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2980348817","doi":"https://doi.org/10.1109/aim.2019.8868579","mag":"2980348817"},"language":"en","primary_location":{"id":"doi:10.1109/aim.2019.8868579","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aim.2019.8868579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)","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/A5075777899","display_name":"Fengming Li","orcid":"https://orcid.org/0000-0003-2263-1957"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fengming Li","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003790606","display_name":"Qi Jiang","orcid":"https://orcid.org/0000-0003-3180-5701"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Jiang","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036159136","display_name":"Wei Quan","orcid":"https://orcid.org/0000-0001-7454-0905"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Quan","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113852285","display_name":"Rui Song","orcid":"https://orcid.org/0000-0002-4119-4433"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Song","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100724411","display_name":"Yibin Li","orcid":"https://orcid.org/0000-0002-5906-5074"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibin Li","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5075777899"],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":1.3305,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.81415448,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"13","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9977999925613403,"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":0.9811999797821045,"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":0.8703231811523438},{"id":"https://openalex.org/keywords/workspace","display_name":"Workspace","score":0.802911639213562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6832793354988098},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6074159741401672},{"id":"https://openalex.org/keywords/torque","display_name":"Torque","score":0.60341477394104},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.535241961479187},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5301849246025085},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5293365716934204},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5157216191291809},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48325115442276},{"id":"https://openalex.org/keywords/robotic-arm","display_name":"Robotic arm","score":0.4766586422920227},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3571266531944275},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2115539312362671}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8703231811523438},{"id":"https://openalex.org/C58581272","wikidata":"https://www.wikidata.org/wiki/Q12741163","display_name":"Workspace","level":3,"score":0.802911639213562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6832793354988098},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6074159741401672},{"id":"https://openalex.org/C144171764","wikidata":"https://www.wikidata.org/wiki/Q48103","display_name":"Torque","level":2,"score":0.60341477394104},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.535241961479187},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5301849246025085},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5293365716934204},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5157216191291809},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48325115442276},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.4766586422920227},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3571266531944275},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2115539312362671},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aim.2019.8868579","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aim.2019.8868579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1499669280","https://openalex.org/W1500357294","https://openalex.org/W1570903953","https://openalex.org/W1967097499","https://openalex.org/W1977655452","https://openalex.org/W2000407777","https://openalex.org/W2017957151","https://openalex.org/W2100235553","https://openalex.org/W2125612430","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2174644224","https://openalex.org/W2341171179","https://openalex.org/W2575705757","https://openalex.org/W2601066903","https://openalex.org/W2766578458","https://openalex.org/W2782231176","https://openalex.org/W2786658381","https://openalex.org/W2810785043","https://openalex.org/W2912997088","https://openalex.org/W2913938871","https://openalex.org/W2938360536","https://openalex.org/W2962887844","https://openalex.org/W2963864421","https://openalex.org/W2963940579","https://openalex.org/W4293864724","https://openalex.org/W4298857966","https://openalex.org/W4302570325","https://openalex.org/W6629910019","https://openalex.org/W6637967152","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6735544697","https://openalex.org/W6737327832","https://openalex.org/W6745360853","https://openalex.org/W6753243525"],"related_works":["https://openalex.org/W1992503747","https://openalex.org/W2371519816","https://openalex.org/W2043154226","https://openalex.org/W2369529107","https://openalex.org/W2329043542","https://openalex.org/W2109948066","https://openalex.org/W1678858522","https://openalex.org/W3195090107","https://openalex.org/W38056103","https://openalex.org/W1999333556"],"abstract_inverted_index":{"Nowadays":[0],"mobile":[1,53],"manipulators":[2],"are":[3],"commonly":[4],"used":[5,112],"in":[6,52,113],"assembly":[7,32,69,115,155],"tasks,":[8],"which":[9,109],"can":[10,43,80],"reach":[11],"greater":[12],"workspace":[13],"but":[14],"also":[15],"cause":[16],"more":[17],"uncertainties.":[18],"Uncertainty":[19],"is":[20,65,103],"one":[21],"of":[22,31,36,48,94],"the":[23,27,50,92,137,151],"main":[24],"factors":[25],"affecting":[26],"quality":[28],"and":[29,99],"efficiency":[30],"tasks.":[33,85,116],"The":[34,71,86,97,117,147],"framework":[35],"skill":[37],"acquisition":[38],"based":[39,60,77],"on":[40,61,78,127,136],"machine":[41],"learning":[42,64,107],"make":[44],"a":[45,58,128],"good":[46],"job":[47],"solving":[49],"uncertainties":[51],"manipulation.":[54],"In":[55],"this":[56],"paper,":[57],"method":[59],"deep":[62,118],"reinforcement":[63],"proposed":[66],"to":[67,82,91,105],"learn":[68,154],"skills.":[70],"Deep":[72],"Deterministic":[73],"Policy":[74],"Gradient":[75],"algorithm":[76],"off-policy":[79],"scale":[81],"complex":[83],"manipulation":[84],"safety":[87],"constraint":[88],"was":[89,134],"set":[90],"torque":[93],"each":[95],"joint.":[96],"positive":[98],"negative":[100],"reward":[101],"function":[102],"designed":[104],"improve":[106],"efficiency,":[108],"could":[110,122,153],"be":[111,123],"different":[114],"neural":[119],"network":[120],"policies":[121],"trained":[124],"out":[125],"efficiently":[126],"real":[129],"robot":[130,140,152],"platform.":[131],"This":[132],"approach":[133],"performed":[135],"KUKA":[138],"iiwa":[139],"arm":[141],"equipped":[142],"with":[143,158],"7-dof":[144],"force/torque":[145],"sensors.":[146],"results":[148],"show":[149],"that":[150],"skills":[156],"properly":[157],"no":[159],"prior":[160],"knowledge.":[161]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}