{"id":"https://openalex.org/W2901112449","doi":"https://doi.org/10.1109/tro.2018.2878318","title":"Model-Based Reinforcement Learning for Closed-Loop Dynamic Control of Soft Robotic Manipulators","display_name":"Model-Based Reinforcement Learning for Closed-Loop Dynamic Control of Soft Robotic Manipulators","publication_year":2018,"publication_date":"2018-11-12","ids":{"openalex":"https://openalex.org/W2901112449","doi":"https://doi.org/10.1109/tro.2018.2878318","mag":"2901112449"},"language":"en","primary_location":{"id":"doi:10.1109/tro.2018.2878318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tro.2018.2878318","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1941-0468"],"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 Transactions on Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/3759636","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037510570","display_name":"Thomas George Thuruthel","orcid":"https://orcid.org/0000-0003-0571-1672"},"institutions":[{"id":"https://openalex.org/I162290304","display_name":"Scuola Superiore Sant'Anna","ror":"https://ror.org/025602r80","country_code":"IT","type":"education","lineage":["https://openalex.org/I162290304"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Thomas George Thuruthel","raw_affiliation_strings":["BioRobotics Institute, Scuola Superiore Sant\u2019Anna, Pisa, Italy","BioRobotics Institute, Scuola Superiore Sant'Anna, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"BioRobotics Institute, Scuola Superiore Sant\u2019Anna, Pisa, Italy","institution_ids":["https://openalex.org/I162290304"]},{"raw_affiliation_string":"BioRobotics Institute, Scuola Superiore Sant'Anna, Pisa, Italy","institution_ids":["https://openalex.org/I162290304"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033570527","display_name":"Egidio Falotico","orcid":"https://orcid.org/0000-0001-8060-8080"},"institutions":[{"id":"https://openalex.org/I162290304","display_name":"Scuola Superiore Sant'Anna","ror":"https://ror.org/025602r80","country_code":"IT","type":"education","lineage":["https://openalex.org/I162290304"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Egidio Falotico","raw_affiliation_strings":["BioRobotics Institute, Scuola Superiore Sant\u2019Anna, Pisa, Italy","BioRobotics Institute, Scuola Superiore Sant'Anna, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"BioRobotics Institute, Scuola Superiore Sant\u2019Anna, Pisa, Italy","institution_ids":["https://openalex.org/I162290304"]},{"raw_affiliation_string":"BioRobotics Institute, Scuola Superiore Sant'Anna, Pisa, Italy","institution_ids":["https://openalex.org/I162290304"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043823023","display_name":"Federico Renda","orcid":"https://orcid.org/0000-0002-1833-9809"},"institutions":[{"id":"https://openalex.org/I176601375","display_name":"Khalifa University of Science and Technology","ror":"https://ror.org/05hffr360","country_code":"AE","type":"education","lineage":["https://openalex.org/I176601375"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Federico Renda","raw_affiliation_strings":["Department of Mechanical Engineering and the Center for Autonomous Robotics Systems, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering and the Center for Autonomous Robotics Systems, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I176601375"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045065209","display_name":"Cecilia Laschi","orcid":"https://orcid.org/0000-0001-5248-1043"},"institutions":[{"id":"https://openalex.org/I162290304","display_name":"Scuola Superiore Sant'Anna","ror":"https://ror.org/025602r80","country_code":"IT","type":"education","lineage":["https://openalex.org/I162290304"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Cecilia Laschi","raw_affiliation_strings":["BioRobotics Institute, Scuola Superiore Sant\u2019Anna, Pisa, Italy","BioRobotics Institute, Scuola Superiore Sant'Anna, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"BioRobotics Institute, Scuola Superiore Sant\u2019Anna, Pisa, Italy","institution_ids":["https://openalex.org/I162290304"]},{"raw_affiliation_string":"BioRobotics Institute, Scuola Superiore Sant'Anna, Pisa, Italy","institution_ids":["https://openalex.org/I162290304"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5037510570"],"corresponding_institution_ids":["https://openalex.org/I162290304"],"apc_list":null,"apc_paid":null,"fwci":10.1384,"has_fulltext":false,"cited_by_count":388,"citation_normalized_percentile":{"value":0.98921054,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"35","issue":"1","first_page":"124","last_page":"134"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10868","display_name":"Soft Robotics and Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T14011","display_name":"Elevator Systems and Control","score":0.9811999797821045,"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/T10618","display_name":"Aortic Disease and Treatment Approaches","score":0.9718999862670898,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.7273147106170654},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.610109806060791},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6035455465316772},{"id":"https://openalex.org/keywords/soft-robotics","display_name":"Soft robotics","score":0.6014403700828552},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.520984947681427},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.515819251537323},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.5048940777778625},{"id":"https://openalex.org/keywords/piecewise","display_name":"Piecewise","score":0.4692012667655945},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44624632596969604},{"id":"https://openalex.org/keywords/robot-manipulator","display_name":"Robot manipulator","score":0.4173371195793152},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3950580656528473},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.3491707444190979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33435189723968506},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2408384084701538},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1297711431980133}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7273147106170654},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.610109806060791},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6035455465316772},{"id":"https://openalex.org/C2776058767","wikidata":"https://www.wikidata.org/wiki/Q24327151","display_name":"Soft robotics","level":3,"score":0.6014403700828552},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.520984947681427},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.515819251537323},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.5048940777778625},{"id":"https://openalex.org/C164660894","wikidata":"https://www.wikidata.org/wiki/Q2037833","display_name":"Piecewise","level":2,"score":0.4692012667655945},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44624632596969604},{"id":"https://openalex.org/C2985527887","wikidata":"https://www.wikidata.org/wiki/Q1587588","display_name":"Robot manipulator","level":3,"score":0.4173371195793152},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3950580656528473},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3491707444190979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33435189723968506},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2408384084701538},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1297711431980133},{"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/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tro.2018.2878318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tro.2018.2878318","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1941-0468"],"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 Transactions on Robotics","raw_type":"journal-article"},{"id":"pmh:oai:www.iris.sssup.it:11382/530001","is_oa":false,"landing_page_url":"http://hdl.handle.net/11382/530001","pdf_url":null,"source":{"id":"https://openalex.org/S4377196376","display_name":"CINECA IRIS Institutional Research Information System (Sant'Anna School of Advanced Studies)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I162290304","host_organization_name":"Scuola Superiore Sant'Anna","host_organization_lineage":["https://openalex.org/I162290304"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:zenodo.org:3759636","is_oa":true,"landing_page_url":"https://zenodo.org/record/3759636","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:3759636","is_oa":true,"landing_page_url":"https://zenodo.org/record/3759636","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W134451811","https://openalex.org/W1520597402","https://openalex.org/W1923344279","https://openalex.org/W1925606516","https://openalex.org/W1967429206","https://openalex.org/W2013290215","https://openalex.org/W2065682774","https://openalex.org/W2073677587","https://openalex.org/W2097854201","https://openalex.org/W2104733512","https://openalex.org/W2117629901","https://openalex.org/W2121103318","https://openalex.org/W2125612430","https://openalex.org/W2221677593","https://openalex.org/W2271075069","https://openalex.org/W2295431040","https://openalex.org/W2337157527","https://openalex.org/W2416041116","https://openalex.org/W2495535193","https://openalex.org/W2511924737","https://openalex.org/W2512635237","https://openalex.org/W2520982900","https://openalex.org/W2560730116","https://openalex.org/W2605807134","https://openalex.org/W2607883703","https://openalex.org/W2615167078","https://openalex.org/W2621077460","https://openalex.org/W2621263557","https://openalex.org/W2724857106","https://openalex.org/W2741086304","https://openalex.org/W2782435507","https://openalex.org/W2786905609","https://openalex.org/W2870735678","https://openalex.org/W2897782084","https://openalex.org/W6675999342","https://openalex.org/W6678367057","https://openalex.org/W6693787782","https://openalex.org/W6980998118"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W4323768008","https://openalex.org/W3131574667","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778"],"abstract_inverted_index":{"Dynamic":[0],"control":[1,68,127,137],"of":[2,18,22,51,69,108],"soft":[3,23,71,113,121],"robotic":[4,24,72],"manipulators":[5,25],"is":[6,78,88,98],"an":[7],"open":[8],"problem":[9],"yet":[10],"to":[11],"be":[12,130],"well":[13],"explored":[14],"and":[15,93,138],"analyzed.":[16],"Most":[17],"the":[19,38,48],"current":[20],"applications":[21],"utilize":[26],"static":[27],"or":[28,35],"quasi-dynamic":[29],"controllers":[30],"based":[31],"on":[32,101,119],"kinematic":[33],"models":[34],"linearity":[36],"in":[37],"joint":[39],"space.":[40],"However,":[41],"such":[42],"approaches":[43],"are":[44],"not":[45],"truly":[46],"exploiting":[47],"rich":[49],"dynamics":[50],"a":[52,60,70,81,102,109,120],"soft-bodied":[53],"system.":[54],"In":[55],"this":[56],"paper,":[57],"we":[58,116],"present":[59],"model-based":[61],"policy":[62,87],"learning":[63],"algorithm":[64],"for":[65],"closed-loop":[66,86,126],"predictive":[67],"manipulator.":[73,114],"The":[74,85,96],"forward":[75],"dynamic":[76],"model":[77,107],"represented":[79],"using":[80,90],"recurrent":[82],"neural":[83],"network.":[84],"derived":[89,131],"trajectory":[91],"optimization":[92],"supervised":[94],"learning.":[95],"approach":[97],"verified":[99],"first":[100],"simulated":[103],"piecewise":[104],"constant":[105],"strain":[106],"cable":[110],"driven":[111],"under-actuated":[112],"Furthermore,":[115],"experimentally":[117],"demonstrate":[118],"pneumatically":[122],"actuated":[123],"manipulator":[124],"how":[125],"policies":[128],"can":[129,133],"that":[132],"accommodate":[134],"variable":[135],"frequency":[136],"unmodeled":[139],"external":[140],"loads.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":72},{"year":2024,"cited_by_count":64},{"year":2023,"cited_by_count":87},{"year":2022,"cited_by_count":65},{"year":2021,"cited_by_count":42},{"year":2020,"cited_by_count":37},{"year":2019,"cited_by_count":12}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
