{"id":"https://openalex.org/W3002817389","doi":"https://doi.org/10.1109/robio49542.2019.8961852","title":"Control of Space Flexible Manipulator Using Soft Actor-Critic and Random Network Distillation","display_name":"Control of Space Flexible Manipulator Using Soft Actor-Critic and Random Network Distillation","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3002817389","doi":"https://doi.org/10.1109/robio49542.2019.8961852","mag":"3002817389"},"language":"en","primary_location":{"id":"doi:10.1109/robio49542.2019.8961852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio49542.2019.8961852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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/A5100759899","display_name":"Chen Yang","orcid":"https://orcid.org/0000-0001-8545-9379"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Yang","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School,Center for Artificial Intelligence and Robotics,Shenzhen,China,518055","Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School,Center for Artificial Intelligence and Robotics,Shenzhen,China,518055","institution_ids":["https://openalex.org/I3131625388"]},{"raw_affiliation_string":"Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101912623","display_name":"Jun Yang","orcid":"https://orcid.org/0000-0002-9386-5825"},"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":"Jun Yang","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China,100084","Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100737125","display_name":"Xueqian Wang","orcid":"https://orcid.org/0000-0003-3542-0593"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqian Wang","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School,Center for Artificial Intelligence and Robotics,Shenzhen,China,518055","Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School,Center for Artificial Intelligence and Robotics,Shenzhen,China,518055","institution_ids":["https://openalex.org/I3131625388"]},{"raw_affiliation_string":"Center for Artificial Intelligence and Robotics, Tsinghua Shenzhen International Graduate School, Shenzhen, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100644630","display_name":"Bin Liang","orcid":"https://orcid.org/0000-0002-8591-8843"},"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":"Bin Liang","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China,100084","Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8747,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.80887724,"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":"3019","last_page":"3024"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9829000234603882,"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":0.9829000234603882,"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/T11701","display_name":"Space Satellite Systems and Control","score":0.958299994468689,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T11406","display_name":"Cerebrospinal fluid and hydrocephalus","score":0.9348000288009644,"subfield":{"id":"https://openalex.org/subfields/2804","display_name":"Cellular and Molecular Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6917849183082581},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6251795887947083},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5124242901802063},{"id":"https://openalex.org/keywords/piecewise","display_name":"Piecewise","score":0.5100293755531311},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4585222601890564},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.45573198795318604},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.35245901346206665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2955103814601898},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2742152810096741},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25380611419677734},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.244902104139328}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6917849183082581},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6251795887947083},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5124242901802063},{"id":"https://openalex.org/C164660894","wikidata":"https://www.wikidata.org/wiki/Q2037833","display_name":"Piecewise","level":2,"score":0.5100293755531311},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4585222601890564},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.45573198795318604},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35245901346206665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2955103814601898},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2742152810096741},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25380611419677734},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.244902104139328},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio49542.2019.8961852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio49542.2019.8961852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"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":29,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W1987370018","https://openalex.org/W1992014302","https://openalex.org/W2153301253","https://openalex.org/W2155007355","https://openalex.org/W2335959470","https://openalex.org/W2594103415","https://openalex.org/W2614839826","https://openalex.org/W2736601468","https://openalex.org/W2781726626","https://openalex.org/W2795456897","https://openalex.org/W2899205164","https://openalex.org/W2921714676","https://openalex.org/W2921924584","https://openalex.org/W2949561945","https://openalex.org/W2963262099","https://openalex.org/W2963523627","https://openalex.org/W2964043796","https://openalex.org/W2964067469","https://openalex.org/W2964161785","https://openalex.org/W6638018090","https://openalex.org/W6682849425","https://openalex.org/W6692846177","https://openalex.org/W6703271639","https://openalex.org/W6734517396","https://openalex.org/W6738087714","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6756303580"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Due":[0],"to":[1,70,81,115,146,150,164,189],"the":[2,8,29,34,57,64,72,78,94,98,108,111,117,121,124,133,142,148,158,165,172,176,185,191,196],"excessive":[3],"degree":[4],"of":[5,7,33,97,123,157,198],"freedom":[6],"space":[9,36,44],"flexible":[10,45],"manipulator,":[11],"we":[12,27,76],"can":[13,183],"hardly":[14],"obtain":[15],"its":[16,21],"accurate":[17],"dynamic":[18],"model":[19,170],"for":[20,107,154],"motion":[22,31],"planning.":[23],"In":[24],"this":[25,162],"work,":[26],"formulate":[28],"precise":[30],"control":[32,184],"free-floating":[35],"piecewise":[37],"constant":[38],"curvature":[39],"(FSPCC)":[40],"continuum":[41,167,187],"manipulator":[42,168,188],"(i.e.":[43],"manipulator)":[46],"as":[47,103,137,139],"a":[48,84,88],"sparse":[49,199],"reward":[50,106],"problem":[51],"in":[52,195],"reinforcement":[53],"learning,":[54],"and":[55,87,120,171],"use":[56,77],"Soft":[58],"Actor-Critic":[59],"(SAC)":[60],"algorithm":[61,113,178],"along":[62],"with":[63,127,180],"Random":[65],"Network":[66],"Distillation":[67],"(RND)":[68],"method":[69,80,163,182],"train":[71,83],"optimal":[73],"policies.":[74],"Firstly,":[75],"RND":[79,181],"jointly":[82],"predictive":[85],"network":[86],"fixed":[89],"network.":[90],"The":[91],"discrepancy":[92],"between":[93],"output":[95],"values":[96],"two":[99],"networks":[100],"is":[101],"served":[102],"an":[104],"internal":[105,143],"environment.":[109],"Secondly,":[110],"SAC":[112,177],"aims":[114],"maximize":[116],"expected":[118],"return":[119],"entropy":[122,129],"policy.":[125],"Policies":[126],"high":[128],"will":[130],"successfully":[131],"complete":[132],"task":[134],"while":[135],"acting":[136],"randomly":[138],"possible.":[140],"Finally,":[141],"rewards":[144],"tend":[145],"incentivize":[147],"agent":[149],"explore":[151],"more":[152],"widely":[153],"faster":[155],"convergence":[156],"algorithm.":[159],"We":[160],"applied":[161],"FSPCC":[166,186],"simulation":[169],"results":[173],"demonstrate":[174],"that":[175],"together":[179],"catch":[190],"target":[192],"quickly,":[193],"even":[194],"presence":[197],"reward.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}