{"id":"https://openalex.org/W3179364417","doi":"https://doi.org/10.1109/robosoft51838.2021.9479340","title":"Model-Free Reinforcement Learning with Ensemble for a Soft Continuum Robot Arm","display_name":"Model-Free Reinforcement Learning with Ensemble for a Soft Continuum Robot Arm","publication_year":2021,"publication_date":"2021-04-12","ids":{"openalex":"https://openalex.org/W3179364417","doi":"https://doi.org/10.1109/robosoft51838.2021.9479340","mag":"3179364417"},"language":"en","primary_location":{"id":"doi:10.1109/robosoft51838.2021.9479340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robosoft51838.2021.9479340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 4th International Conference on Soft Robotics (RoboSoft)","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/A5047078687","display_name":"Ryota Morimoto","orcid":"https://orcid.org/0000-0003-2859-6638"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ryota Morimoto","raw_affiliation_strings":["The University of Tokyo,Graduate School of Information Science and Technology,Tokyo,Japan","Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Graduate School of Information Science and Technology,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058960117","display_name":"Satoshi Nishikawa","orcid":"https://orcid.org/0000-0003-0905-8615"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nishikawa","raw_affiliation_strings":["The University of Tokyo,Graduate School of Information Science and Technology,Tokyo,Japan","Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Graduate School of Information Science and Technology,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059653874","display_name":"Ryuma Niiyama","orcid":"https://orcid.org/0000-0002-9072-8251"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryuma Niiyama","raw_affiliation_strings":["The University of Tokyo,Graduate School of Information Science and Technology,Tokyo,Japan","Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Graduate School of Information Science and Technology,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010543059","display_name":"Yasuo Kuniyoshi","orcid":"https://orcid.org/0000-0001-8443-4161"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasuo Kuniyoshi","raw_affiliation_strings":["The University of Tokyo,Graduate School of Information Science and Technology,Tokyo,Japan","Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Graduate School of Information Science and Technology,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5047078687"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":2.8019,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.90732983,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"141","last_page":"148"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10868","display_name":"Soft Robotics and Applications","score":0.9958999752998352,"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"}},"topics":[{"id":"https://openalex.org/T10868","display_name":"Soft Robotics and Applications","score":0.9958999752998352,"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"}},{"id":"https://openalex.org/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.995199978351593,"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"}},{"id":"https://openalex.org/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.9835000038146973,"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/robot","display_name":"Robot","score":0.8116123080253601},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7580134868621826},{"id":"https://openalex.org/keywords/soft-robotics","display_name":"Soft robotics","score":0.6249989867210388},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5763314962387085},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.574241578578949},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.48606541752815247},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.48426932096481323},{"id":"https://openalex.org/keywords/robotic-arm","display_name":"Robotic arm","score":0.46962976455688477},{"id":"https://openalex.org/keywords/degrees-of-freedom","display_name":"Degrees of freedom (physics and chemistry)","score":0.4405606985092163},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4305293560028076},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4258568286895752},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3948932886123657},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.3498789072036743},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.32156693935394287},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2767995595932007},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.22050076723098755},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09691685438156128}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.8116123080253601},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7580134868621826},{"id":"https://openalex.org/C2776058767","wikidata":"https://www.wikidata.org/wiki/Q24327151","display_name":"Soft robotics","level":3,"score":0.6249989867210388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5763314962387085},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.574241578578949},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.48606541752815247},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.48426932096481323},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.46962976455688477},{"id":"https://openalex.org/C208081375","wikidata":"https://www.wikidata.org/wiki/Q274502","display_name":"Degrees of freedom (physics and chemistry)","level":2,"score":0.4405606985092163},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4305293560028076},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4258568286895752},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3948932886123657},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3498789072036743},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.32156693935394287},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2767995595932007},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.22050076723098755},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09691685438156128},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robosoft51838.2021.9479340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robosoft51838.2021.9479340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 4th International Conference on Soft Robotics (RoboSoft)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1579240551","https://openalex.org/W1982082424","https://openalex.org/W2063797945","https://openalex.org/W2095462685","https://openalex.org/W2101667962","https://openalex.org/W2104733512","https://openalex.org/W2135485145","https://openalex.org/W2158782408","https://openalex.org/W2173248099","https://openalex.org/W2280163991","https://openalex.org/W2416041116","https://openalex.org/W2736601468","https://openalex.org/W2741086304","https://openalex.org/W2742169147","https://openalex.org/W2745494968","https://openalex.org/W2767313115","https://openalex.org/W2775361682","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2793019179","https://openalex.org/W2855298762","https://openalex.org/W2901112449","https://openalex.org/W2904237456","https://openalex.org/W2904246096","https://openalex.org/W2910273746","https://openalex.org/W2921924584","https://openalex.org/W2963864421","https://openalex.org/W2963923407","https://openalex.org/W2963938771","https://openalex.org/W2967427547","https://openalex.org/W2967429195","https://openalex.org/W3002817389","https://openalex.org/W3017367030","https://openalex.org/W3031634197","https://openalex.org/W3035790680","https://openalex.org/W3037785630","https://openalex.org/W3041764008","https://openalex.org/W3048090341","https://openalex.org/W3115226733","https://openalex.org/W3158726102","https://openalex.org/W3172115140","https://openalex.org/W4287759384","https://openalex.org/W4288319859","https://openalex.org/W6675999342","https://openalex.org/W6684921986","https://openalex.org/W6695011786","https://openalex.org/W6741002519","https://openalex.org/W6745497480","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6757592117","https://openalex.org/W6764053384","https://openalex.org/W6768397756","https://openalex.org/W6776026728","https://openalex.org/W6780559895","https://openalex.org/W6780571964"],"related_works":["https://openalex.org/W2326585759","https://openalex.org/W4312473168","https://openalex.org/W4211124276","https://openalex.org/W4312269480","https://openalex.org/W3215005299","https://openalex.org/W2291244835","https://openalex.org/W4388893656","https://openalex.org/W1505290414","https://openalex.org/W2108575589","https://openalex.org/W2605331264"],"abstract_inverted_index":{"Soft":[0],"robots":[1,44,172],"have":[2],"more":[3,168],"passive":[4,202],"degrees":[5],"of":[6,40,47,51,66,185,201,215],"freedom":[7],"(DoFs)":[8],"than":[9,173,183],"rigid-body":[10],"robots,":[11],"which":[12,81],"makes":[13],"controller":[14],"design":[15],"difficult.":[16],"Model-free":[17],"reinforcement":[18,77],"learning":[19,78],"(RL)":[20],"is":[21,61,82,167,181,191,204,208],"a":[22,57,67,87,102,125,158,192],"promising":[23],"tool":[24],"to":[25,42,106,210,212],"resolve":[26],"control":[27,99,148],"problems":[28],"in":[29,115,119,195,218],"soft":[30,43,52,68,220],"robotics":[31],"alongside":[32],"detailed":[33],"and":[34,70,189],"elaborate":[35],"modeling.":[36],"However,":[37],"the":[38,48,94,120,152,178,186,196,199,213],"adaptation":[39],"RL":[41,84,175,217],"requires":[45],"consideration":[46],"unique":[49],"nature":[50],"bodies.":[53],"In":[54],"this":[55],"work,":[56],"continuum":[58,103,128],"robot":[59,104,129,160,221],"arm":[60,105,130],"used":[62,124],"as":[63],"an":[64,73,83],"example":[65],"robot,":[69],"we":[71],"propose":[72],"Ensembled":[74],"Light-weight":[75],"model-Free":[76],"Network":[79],"(ELFNet),":[80],"framework":[85],"with":[86,133],"computationally":[88],"light":[89],"ensemble.":[90],"We":[91,123,162],"demonstrated":[92],"that":[93,131,151,164,184],"proposed":[95],"system":[96],"could":[97],"learn":[98],"policies":[100],"for":[101,170],"reach":[107],"target":[108],"positions":[109],"using":[110,157],"its":[111],"tip":[112],"not":[113],"only":[114],"simulations":[116],"but":[117],"also":[118],"real":[121,159],"world.":[122],"pneumatically":[126],"controlled":[127,144],"operates":[132],"nine":[134],"flexible":[135],"rubber":[136],"artificial":[137,140],"muscles.":[138],"Each":[139],"muscle":[141],"can":[142,154],"be":[143,155],"independently":[145],"by":[146],"pressure":[147],"valves,":[149],"demonstrating":[150],"policy":[153],"learned":[156],"alone.":[161],"found":[163],"our":[165],"method":[166],"suitable":[169],"compliant":[171],"other":[174,187],"methods":[176],"because":[177],"sample":[179],"efficiency":[180],"better":[182],"methods,":[188],"there":[190],"significant":[193],"difference":[194],"performance":[197],"when":[198],"number":[200],"DoFs":[203],"large.":[205],"This":[206],"study":[207],"expected":[209],"lead":[211],"development":[214],"model-free":[216],"future":[219],"control.":[222]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}