{"id":"https://openalex.org/W4226030739","doi":"https://doi.org/10.1109/icra46639.2022.9812023","title":"Real-Robot Deep Reinforcement Learning: Improving Trajectory Tracking of Flexible-Joint Manipulator with Reference Correction","display_name":"Real-Robot Deep Reinforcement Learning: Improving Trajectory Tracking of Flexible-Joint Manipulator with Reference Correction","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W4226030739","doi":"https://doi.org/10.1109/icra46639.2022.9812023"},"language":"en","primary_location":{"id":"doi:10.1109/icra46639.2022.9812023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9812023","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":"conference-paper","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/A5077737512","display_name":"Dmytro Pavlichenko","orcid":"https://orcid.org/0000-0003-0904-9524"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dmytro Pavlichenko","raw_affiliation_strings":["University of Bonn,Autonomous Intelligent Systems (AIS) Group, Computer Science Institute VI,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bonn,Autonomous Intelligent Systems (AIS) Group, Computer Science Institute VI,Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027761977","display_name":"Sven Behnke","orcid":"https://orcid.org/0000-0002-5040-7525"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sven Behnke","raw_affiliation_strings":["University of Bonn,Autonomous Intelligent Systems (AIS) Group, Computer Science Institute VI,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bonn,Autonomous Intelligent Systems (AIS) Group, Computer Science Institute VI,Germany","institution_ids":["https://openalex.org/I135140700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I135140700"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2671","last_page":"2677"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5078999996185303,"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":0.5078999996185303,"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":0.18719999492168427,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.10599999874830246,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7609014511108398},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.7041394710540771},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6666232943534851},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6275222301483154},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5970615148544312},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5876669883728027},{"id":"https://openalex.org/keywords/payload","display_name":"Payload (computing)","score":0.5657762885093689},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5326119661331177},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5183180570602417},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.49712827801704407},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4536064565181732},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4242992401123047},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.36990082263946533},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.24079099297523499},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19144073128700256},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.129774272441864}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7609014511108398},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7041394710540771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6666232943534851},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6275222301483154},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5970615148544312},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5876669883728027},{"id":"https://openalex.org/C134066672","wikidata":"https://www.wikidata.org/wiki/Q1424639","display_name":"Payload (computing)","level":3,"score":0.5657762885093689},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5326119661331177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5183180570602417},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.49712827801704407},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4536064565181732},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4242992401123047},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.36990082263946533},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.24079099297523499},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19144073128700256},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.129774272441864},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra46639.2022.9812023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9812023","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":[{"id":"https://openalex.org/G5287504387","display_name":null,"funder_award_id":"BE 2556/16-2","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W40338364","https://openalex.org/W1975517766","https://openalex.org/W2001123678","https://openalex.org/W2017932718","https://openalex.org/W2040871222","https://openalex.org/W2041242313","https://openalex.org/W2097520388","https://openalex.org/W2169462064","https://openalex.org/W2207061578","https://openalex.org/W2782876516","https://openalex.org/W2797655438","https://openalex.org/W2895632869","https://openalex.org/W2904526301","https://openalex.org/W2911087563","https://openalex.org/W2911426134","https://openalex.org/W2963713397","https://openalex.org/W3091444023","https://openalex.org/W3126321819","https://openalex.org/W3165182604","https://openalex.org/W3168511769","https://openalex.org/W3206620955","https://openalex.org/W4285336281","https://openalex.org/W6638018090","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6734517396","https://openalex.org/W6741471465","https://openalex.org/W6747473740","https://openalex.org/W6780404908"],"related_works":["https://openalex.org/W1323832","https://openalex.org/W14655851","https://openalex.org/W8692371","https://openalex.org/W3011641","https://openalex.org/W9859545","https://openalex.org/W7002317","https://openalex.org/W11452874","https://openalex.org/W8327028","https://openalex.org/W6177293","https://openalex.org/W15687067"],"abstract_inverted_index":{"Flexible-joint":[0],"manipulators":[1],"are":[2],"governed":[3],"by":[4,35],"complex":[5],"nonlinear":[6],"dynamics,":[7],"defining":[8],"a":[9,36,61,80,93,120],"challenging":[10],"control":[11],"problem.":[12],"In":[13,66],"this":[14],"work,":[15],"we":[16],"propose":[17],"an":[18,22,68,137],"approach":[19,86],"to":[20,131,136],"learn":[21],"outer-loop":[23],"joint":[24],"trajectory":[25,126],"tracking":[26,127],"controller":[27,33],"with":[28],"deep":[29],"reinforcement":[30],"learning.":[31],"The":[32],"represented":[34],"stochastic":[37],"policy":[38,70,121],"is":[39,51,72,77,102],"learned":[40,81],"in":[41,79,129],"under":[42],"two":[43],"hours":[44],"directly":[45,112],"on":[46,87,113],"the":[47,75,88,99,114,125,132],"real":[48,115],"robot.":[49,95,116],"This":[50],"achieved":[52],"through":[53],"bounded":[54],"reference":[55],"correction":[56],"actions":[57],"and":[58],"use":[59],"of":[60,92,104],"model-free":[62],"off-policy":[63],"learning":[64,106],"method.":[65],"addition,":[67],"informed":[69],"initialization":[71],"proposed,":[73],"where":[74],"agent":[76],"pre-trained":[78],"simulation.":[82],"We":[83,96],"test":[84],"our":[85],"7":[89],"DOF":[90],"manipulator":[91],"Baxter":[94],"demonstrate":[97],"that":[98],"proposed":[100],"method":[101,118],"capable":[103],"consistent":[105],"across":[107],"multiple":[108],"runs":[109],"when":[110],"applied":[111],"Our":[117],"yields":[119],"which":[122],"significantly":[123],"improves":[124],"accuracy":[128],"comparison":[130],"vendor-provided":[133],"controller,":[134],"generalizing":[135],"unseen":[138],"payload.":[139]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-05-05T00:00:00"}