{"id":"https://openalex.org/W4412444679","doi":"https://doi.org/10.1109/lra.2025.3588411","title":"Behavior Cloning Assisted Reinforcement Learning for Cable-Driven Continuum Space Robots in Sparse Reward Environments","display_name":"Behavior Cloning Assisted Reinforcement Learning for Cable-Driven Continuum Space Robots in Sparse Reward Environments","publication_year":2025,"publication_date":"2025-07-15","ids":{"openalex":"https://openalex.org/W4412444679","doi":"https://doi.org/10.1109/lra.2025.3588411"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3588411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3588411","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 and Automation Letters","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/A5111336324","display_name":"Xianru Tian","orcid":"https://orcid.org/0009-0005-9366-5435"},"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"]},{"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":"Xianru Tian","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0005-9366-5435","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072713174","display_name":"Bo Xia","orcid":"https://orcid.org/0009-0003-3507-9732"},"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"]},{"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":"Bo Xia","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004980453","display_name":"Junbo Tan","orcid":"https://orcid.org/0000-0002-8956-5408"},"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"]},{"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":"Junbo Tan","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-8956-5408","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032061647","display_name":"Bo Yuan","orcid":"https://orcid.org/0000-0003-2169-0007"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Bo Yuan","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, The University of Queensland, QLD, Australia"],"raw_orcid":"https://orcid.org/0000-0003-2169-0007","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, The University of Queensland, QLD, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100765837","display_name":"Zhiheng Li","orcid":"https://orcid.org/0000-0002-1523-1114"},"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"]},{"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":"Zhiheng Li","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xueqian Wang","orcid":"https://orcid.org/0009-0003-3507-9732"},"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"]},{"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":"Xueqian Wang","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0003-3507-9732","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5111336324"],"corresponding_institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":4.7878,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.94398051,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"10","issue":"9","first_page":"9232","last_page":"9239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11701","display_name":"Space Satellite Systems and Control","score":0.9702000021934509,"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"}},"topics":[{"id":"https://openalex.org/T11701","display_name":"Space Satellite Systems and Control","score":0.9702000021934509,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8063274621963501},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.5872800946235657},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5843223333358765},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5474366545677185},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.530564546585083},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4884773790836334},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4316403269767761},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.25132763385772705},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.18802371621131897}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8063274621963501},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.5872800946235657},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5843223333358765},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5474366545677185},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.530564546585083},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4884773790836334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4316403269767761},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.25132763385772705},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.18802371621131897},{"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/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/lra.2025.3588411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3588411","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4151766453","display_name":null,"funder_award_id":"2024A1515010003","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2788862220","https://openalex.org/W2963099939","https://openalex.org/W2963411833","https://openalex.org/W2967429195","https://openalex.org/W2973229164","https://openalex.org/W2990747716","https://openalex.org/W2997727809","https://openalex.org/W3002817389","https://openalex.org/W3035790680","https://openalex.org/W3046983221","https://openalex.org/W3130337292","https://openalex.org/W3189250457","https://openalex.org/W3191709555","https://openalex.org/W4317384025","https://openalex.org/W4383069115","https://openalex.org/W4385430582","https://openalex.org/W4402354084","https://openalex.org/W4403741606","https://openalex.org/W6638088447","https://openalex.org/W6640174482","https://openalex.org/W6684338915","https://openalex.org/W6740801417","https://openalex.org/W6742461812","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6789305357","https://openalex.org/W6839241500","https://openalex.org/W6849433528"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2],"(DRL)":[3],"has":[4],"emerged":[5],"as":[6,103],"a":[7,18,81,92,104],"powerful":[8],"tool":[9],"for":[10,198],"controlling":[11,66,173],"cable-driven":[12],"continuum":[13],"space":[14,55],"robots":[15],"(CDCSRs),":[16],"offering":[17],"solution":[19],"that":[20,84],"bypasses":[21],"complex":[22],"system":[23],"modeling.":[24],"However,":[25],"DRL":[26,41],"based":[27,42],"on":[28,43,110],"dense":[29],"reward":[30,38,45],"functions":[31,46],"(DRLDR)":[32],"requires":[33],"meticulous":[34],"tuning":[35],"of":[36,155,170,185,193],"the":[37,54,63,70,100,112,121,126,131,136,149,153,163,168,178,189,194],"structure,":[39],"whereas":[40],"sparse":[44],"(DRLSR)":[47],"exhibits":[48],"limited":[49],"decision-making":[50],"abilities,":[51],"particularly":[52],"in":[53,65,162,172],"environments.":[56],"To":[57],"avoid":[58],"extensive":[59,158],"fine-tuning":[60],"and":[61,142,147,183,191],"enhance":[62],"performance":[64,169],"CDCSRs,":[67],"we":[68],"propose":[69],"behavior":[71,86],"cloning":[72,87],"assisted":[73],"twin":[74],"delayed":[75],"deep":[76],"deterministic":[77],"policy":[78],"gradient":[79],"(BATD3),":[80],"novel":[82],"algorithm":[83,114],"integrates":[85],"(BC)":[88],"with":[89,140,152,188],"DRLSR.":[90],"Firstly,":[91],"DRLSR-based":[93,195],"control":[94,101,196],"framework":[95,197],"is":[96,115],"developed,":[97],"which":[98],"reformulates":[99],"problem":[102],"Markov":[105],"decision":[106],"process":[107],"(MDP).":[108],"Building":[109],"this,":[111],"BATD3":[113,171],"proposed,":[116],"comprising":[117],"two":[118],"training":[119],"phases:":[120],"prior":[122],"phase":[123,133],"to":[124,134,166],"train":[125],"BC":[127],"model":[128,151],"using":[129],"demonstrations;":[130],"formal":[132],"pre-fill":[135],"RL":[137,150],"replay":[138],"buffer":[139],"demonstrations":[141],"successful":[143],"BC-environment":[144],"interaction":[145],"trajectories,":[146],"optimize":[148],"assistance":[154],"BC.":[156],"Finally,":[157],"experiments":[159],"are":[160],"conducted":[161],"MuJoCo":[164],"environment":[165],"assess":[167],"CDCSRs.":[174,199],"The":[175],"results":[176],"highlight":[177],"effectiveness,":[179],"generalization,":[180],"stability,":[181],"robustness":[182],"potential":[184],"BATD3,":[186],"along":[187],"practicality":[190],"feasibility":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}