{"id":"https://openalex.org/W4285102270","doi":"https://doi.org/10.1109/icra46639.2022.9811792","title":"Model-driven reinforcement learning and action dimension extension method for efficient asymmetric assembly","display_name":"Model-driven reinforcement learning and action dimension extension method for efficient asymmetric assembly","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W4285102270","doi":"https://doi.org/10.1109/icra46639.2022.9811792"},"language":"en","primary_location":{"id":"doi:10.1109/icra46639.2022.9811792","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811792","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Robotics and Automation (ICRA)","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/A5003430066","display_name":"Yuhang Gai","orcid":"https://orcid.org/0000-0003-4463-602X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuhang Gai","raw_affiliation_strings":["Tsinghua University,Department of Mechanical Engineering,Beijing,China","Department of Mechanical Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Mechanical Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Mechanical Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101711932","display_name":"Jiuming Guo","orcid":"https://orcid.org/0000-0002-5803-7717"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiuming Guo","raw_affiliation_strings":["Tsinghua University,Department of Mechanical Engineering,Beijing,China","Department of Mechanical Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Mechanical Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Mechanical Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061911091","display_name":"Dan Wu","orcid":"https://orcid.org/0000-0002-3856-1087"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Wu","raw_affiliation_strings":["Tsinghua University,Department of Mechanical Engineering,Beijing,China","Department of Mechanical Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Mechanical Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Mechanical Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100420346","display_name":"Ken Chen","orcid":"https://orcid.org/0000-0003-2569-0071"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ken Chen","raw_affiliation_strings":["Tsinghua University,Department of Mechanical Engineering,Beijing,China","Department of Mechanical Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Mechanical Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Mechanical Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003430066"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.2078,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.3887632,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"9867","last_page":"9873"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9980000257492065,"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/T10784","display_name":"Muscle activation and electromyography studies","score":0.9812999963760376,"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":0.8999091386795044},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.7755377292633057},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.7508165836334229},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7233283519744873},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.6790649890899658},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6295379400253296},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5451485514640808},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5298319458961487},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5061783194541931},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.44464531540870667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4294567108154297},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3337877690792084},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18023791909217834},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16286823153495789},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10337337851524353}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8999091386795044},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.7755377292633057},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.7508165836334229},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7233283519744873},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.6790649890899658},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6295379400253296},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5451485514640808},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5298319458961487},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5061783194541931},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.44464531540870667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4294567108154297},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3337877690792084},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18023791909217834},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16286823153495789},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10337337851524353},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra46639.2022.9811792","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811792","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2008731016","https://openalex.org/W2032577978","https://openalex.org/W2280163991","https://openalex.org/W2623491082","https://openalex.org/W2726187156","https://openalex.org/W2736601468","https://openalex.org/W2793035934","https://openalex.org/W2806263811","https://openalex.org/W2889324057","https://openalex.org/W2890218953","https://openalex.org/W2962850167","https://openalex.org/W2963864421","https://openalex.org/W2963940579","https://openalex.org/W2964043796","https://openalex.org/W2967727187","https://openalex.org/W2968268581","https://openalex.org/W3072315125","https://openalex.org/W3130717831","https://openalex.org/W3148025781","https://openalex.org/W3174364619","https://openalex.org/W3206827162","https://openalex.org/W3209862138","https://openalex.org/W4233840023","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6695011786","https://openalex.org/W6739193204","https://openalex.org/W6740222838","https://openalex.org/W6741002519","https://openalex.org/W6749032995","https://openalex.org/W6785871430","https://openalex.org/W6793017453","https://openalex.org/W6802016798"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W2381570729","https://openalex.org/W1976205134","https://openalex.org/W4248336175","https://openalex.org/W2031260042","https://openalex.org/W2391445434","https://openalex.org/W3009369890","https://openalex.org/W4312490297","https://openalex.org/W1641969990"],"abstract_inverted_index":{"Complex":[0],"assembly":[1,91],"tasks":[2],"remain":[3],"huge":[4],"challenge":[5],"for":[6],"robots":[7],"because":[8],"the":[9,25,30,39,49,66,78,98,110],"traditional":[10],"control":[11,31,50,79],"methods":[12],"rely":[13],"on":[14],"complicated":[15],"contact":[16],"state":[17],"analysis.":[18],"Reinforcement":[19],"learning":[20],"(RL)":[21],"becomes":[22],"one":[23],"of":[24,33,41,69,100],"preferred":[26],"embodiments":[27],"to":[28,47,63],"construct":[29,48],"strategy":[32,80],"complex":[34],"tasks.":[35],"In":[36],"this":[37],"paper,":[38],"method":[40,95],"model-driven":[42],"RL":[43,101],"(MDRL)":[44],"is":[45,61],"employed":[46],"strategy.":[51],"Then":[52],"a":[53,88],"completely":[54],"innovative":[55],"action":[56],"dimension":[57],"extension":[58],"(ADE)":[59],"mechanism":[60],"proposed":[62],"further":[64],"accelerate":[65],"training":[67],"process":[68],"RL.":[70],"The":[71],"simulation":[72],"and":[73,85],"experiment":[74],"results":[75],"demonstrate":[76],"that":[77],"obtained":[81],"through":[82],"combining":[83],"MDRL":[84],"ADE":[86,94],"guarantees":[87],"more":[89],"compliant":[90],"process.":[92],"Besides,":[93],"will":[96],"enhance":[97],"data-efficiency":[99],"algorithms":[102],"greatly":[103],"(about":[104],"30%~40%)":[105],"as":[106,108],"well":[107],"increase":[109],"stable":[111],"reward.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}