{"id":"https://openalex.org/W4396853395","doi":"https://doi.org/10.1109/robosoft60065.2024.10522003","title":"Reinforcement Learning Controllers for Soft Robots Using Learned Environments","display_name":"Reinforcement Learning Controllers for Soft Robots Using Learned Environments","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4396853395","doi":"https://doi.org/10.1109/robosoft60065.2024.10522003"},"language":"en","primary_location":{"id":"doi:10.1109/robosoft60065.2024.10522003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robosoft60065.2024.10522003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 7th International Conference on Soft Robotics (RoboSoft)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.18519","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004730335","display_name":"Uljad Berdica","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Uljad Berdica","raw_affiliation_strings":["University of Oxford"],"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012459953","display_name":"Matthew Jackson","orcid":"https://orcid.org/0000-0002-7891-6217"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Matthew Jackson","raw_affiliation_strings":["University of Oxford"],"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097955701","display_name":"Niccol\u00f2 Enrico Veronese","orcid":null},"institutions":[{"id":"https://openalex.org/I122534668","display_name":"Marche Polytechnic University","ror":"https://ror.org/00x69rs40","country_code":"IT","type":"education","lineage":["https://openalex.org/I122534668"]},{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Niccol\u00f2 Enrico Veronese","raw_affiliation_strings":["Polytechnic University of Milan,Italy","Polytechnic University of Milan, Italy"],"affiliations":[{"raw_affiliation_string":"Polytechnic University of Milan,Italy","institution_ids":["https://openalex.org/I122534668"]},{"raw_affiliation_string":"Polytechnic University of Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059094093","display_name":"Jakob Foerster","orcid":"https://orcid.org/0000-0001-9688-2498"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jakob Foerster","raw_affiliation_strings":["University of Oxford"],"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054789141","display_name":"Perla Maiolino","orcid":"https://orcid.org/0000-0002-7588-9567"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Perla Maiolino","raw_affiliation_strings":["University of Oxford"],"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5004730335"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":0.9058,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.70314152,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"933","last_page":"939"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10868","display_name":"Soft Robotics and Applications","score":0.9993000030517578,"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":0.9993000030517578,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.993399977684021,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9929999709129333,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8228065967559814},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6816211938858032},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.6562924385070801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6022733449935913},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5672725439071655},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5370793342590332},{"id":"https://openalex.org/keywords/randomness","display_name":"Randomness","score":0.5354959964752197},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5289611220359802},{"id":"https://openalex.org/keywords/soft-robotics","display_name":"Soft robotics","score":0.4575691521167755},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4386546313762665},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3960834741592407},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3944697380065918},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17994898557662964},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09311637282371521}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8228065967559814},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6816211938858032},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.6562924385070801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6022733449935913},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5672725439071655},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5370793342590332},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.5354959964752197},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5289611220359802},{"id":"https://openalex.org/C2776058767","wikidata":"https://www.wikidata.org/wiki/Q24327151","display_name":"Soft robotics","level":3,"score":0.4575691521167755},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4386546313762665},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3960834741592407},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3944697380065918},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17994898557662964},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09311637282371521},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/robosoft60065.2024.10522003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robosoft60065.2024.10522003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 7th International Conference on Soft Robotics (RoboSoft)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.18519","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.18519","pdf_url":"https://arxiv.org/pdf/2410.18519","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.18519","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.18519","pdf_url":"https://arxiv.org/pdf/2410.18519","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3105706333","display_name":null,"funder_award_id":"EP/V000748/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5670947113","display_name":"EPSRC Centre for Doctoral Training in Autonomous Intelligent Machines and Systems","funder_award_id":"EP/S024050/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6198381055","display_name":"From Sensing to Collaboration: Engineering, Exploring and Exploiting the Building Blocks of Embodied Intelligence - An EPSRC Programme Grant","funder_award_id":"EP/V000748/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396853395.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W755046805","https://openalex.org/W2064675550","https://openalex.org/W2116086091","https://openalex.org/W2151471214","https://openalex.org/W2560730116","https://openalex.org/W2605807134","https://openalex.org/W2735708297","https://openalex.org/W2736601468","https://openalex.org/W2741086304","https://openalex.org/W2775361682","https://openalex.org/W2782435507","https://openalex.org/W2843252114","https://openalex.org/W2901112449","https://openalex.org/W2967429195","https://openalex.org/W2973229164","https://openalex.org/W3153278392","https://openalex.org/W4226256030","https://openalex.org/W4250720744","https://openalex.org/W4280571816","https://openalex.org/W4305038385","https://openalex.org/W4376605634","https://openalex.org/W4378192004","https://openalex.org/W6846337460"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2326585759","https://openalex.org/W4312473168","https://openalex.org/W4211124276","https://openalex.org/W4312269480"],"abstract_inverted_index":{"Soft":[0],"robotic":[1,52],"manipulators":[2],"offer":[3],"operational":[4],"advantage":[5],"due":[6],"to":[7,41,50,106],"their":[8,14],"compliant":[9],"and":[10,36,79,146],"deformable":[11],"structures.":[12],"However,":[13],"inherently":[15],"nonlinear":[16],"dynamics":[17,86],"presents":[18],"substantial":[19],"challenges.":[20],"Traditional":[21],"analytical":[22],"methods":[23,58],"often":[24],"depend":[25],"on":[26],"simplifying":[27],"assumptions,":[28],"while":[29],"learning-based":[30],"techniques":[31],"can":[32],"be":[33],"computationally":[34],"demanding":[35],"limit":[37],"the":[38,108,135,141,148],"control":[39,119],"policies":[40],"existing":[42],"data.":[43,65],"This":[44,132],"paper":[45],"introduces":[46],"a":[47,69,92,96,113,151],"novel":[48],"approach":[49,116,133],"soft":[51,156],"control,":[53],"leveraging":[54],"state-of-the-art":[55,121],"policy":[56],"gradient":[57],"within":[59],"parallelizable":[60],"synthetic":[61],"environments":[62],"learned":[63,89],"from":[64,95],"We":[66,111],"also":[67],"propose":[68],"safety":[70],"oriented":[71],"actuation":[72,104],"space":[73,105],"exploration":[74],"protocol":[75],"via":[76],"cascaded":[77],"updates":[78],"weighted":[80],"randomness.":[81],"Specifically,":[82],"our":[83],"recurrent":[84],"forward":[85],"model":[87],"is":[88],"by":[90],"generating":[91],"training":[93],"dataset":[94],"physically":[97],"safe":[98],"mean":[99],"reverting":[100],"random":[101],"walk":[102],"in":[103,155],"explore":[107],"partially-observed":[109],"state-space.":[110],"demonstrate":[112],"reinforcement":[114],"learning":[115],"towards":[117],"closed-loop":[118],"through":[120],"actor-critic":[122],"methods,":[123],"which":[124],"efficiently":[125],"learn":[126],"high-performance":[127],"behaviour":[128],"over":[129],"long":[130],"horizons.":[131],"removes":[134],"need":[136],"for":[137,150],"any":[138],"knowledge":[139],"regarding":[140],"robot's":[142],"operations":[143],"/":[144],"capabilities":[145],"sets":[147],"stage":[149],"comprehensive":[152],"benchmarking":[153],"tool":[154],"robotics":[157],"control.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}