{"id":"https://openalex.org/W4416750721","doi":"https://doi.org/10.1109/iros60139.2025.11245998","title":"Offline Reinforcement Learning with Koopman Operators for Control of Soft Robots","display_name":"Offline Reinforcement Learning with Koopman Operators for Control of Soft Robots","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750721","doi":"https://doi.org/10.1109/iros60139.2025.11245998"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11245998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245998","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5010235277","display_name":"Yue Jiang","orcid":"https://orcid.org/0000-0002-0310-2657"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yue Jiang","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100331572","display_name":"Cong Li","orcid":"https://orcid.org/0000-0002-1103-4818"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Li","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051611729","display_name":"Yihe Yang","orcid":"https://orcid.org/0000-0001-6563-3579"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihe Yang","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024579578","display_name":"Wenyu Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyu Cao","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100319792","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0002-0479-6988"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xu","raw_affiliation_strings":["National University of Defense Technology,National Key Laboratory of Equipment State Sensing and Smart Support, College of Intelligence Science and Technology,Changsha,China,410073"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,National Key Laboratory of Equipment State Sensing and Smart Support, College of Intelligence Science and Technology,Changsha,China,410073","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021864206","display_name":"Jinze Liu","orcid":"https://orcid.org/0000-0003-0692-8793"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinze Liu","raw_affiliation_strings":["National University of Defense Technology,Vocational Education Center,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Vocational Education Center,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059828821","display_name":"Wei Jiang","orcid":"https://orcid.org/0000-0002-3719-3710"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Jiang","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101668802","display_name":"Xinglong Zhang","orcid":"https://orcid.org/0000-0002-0587-2487"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinglong Zhang","raw_affiliation_strings":["National University of Defense Technology,National Key Laboratory of Equipment State Sensing and Smart Support, College of Intelligence Science and Technology,Changsha,China,410073"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,National Key Laboratory of Equipment State Sensing and Smart Support, College of Intelligence Science and Technology,Changsha,China,410073","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5010235277"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28730366,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5482","last_page":"5489"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.6686999797821045,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.6686999797821045,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.07320000231266022,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.06759999692440033,"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/interpretability","display_name":"Interpretability","score":0.7688000202178955},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7645999789237976},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6578999757766724},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5638999938964844},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5299000144004822},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5177000164985657},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4724000096321106},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4259999990463257},{"id":"https://openalex.org/keywords/soft-computing","display_name":"Soft computing","score":0.39820000529289246}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7688000202178955},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7645999789237976},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6718999743461609},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6578999757766724},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5638999938964844},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5299000144004822},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5177000164985657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5012999773025513},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4724000096321106},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4259999990463257},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.4075999855995178},{"id":"https://openalex.org/C140073362","wikidata":"https://www.wikidata.org/wiki/Q738759","display_name":"Soft computing","level":3,"score":0.39820000529289246},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C208081375","wikidata":"https://www.wikidata.org/wiki/Q274502","display_name":"Degrees of freedom (physics and chemistry)","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.3382999897003174},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C187523126","wikidata":"https://www.wikidata.org/wiki/Q17098330","display_name":"Inverse dynamics","level":3,"score":0.3176000118255615},{"id":"https://openalex.org/C2776058767","wikidata":"https://www.wikidata.org/wiki/Q24327151","display_name":"Soft robotics","level":3,"score":0.31310001015663147},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.30660000443458557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29100000858306885},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.2750000059604645},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2712000012397766},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.2621000111103058}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11245998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245998","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1515749184","https://openalex.org/W1591018827","https://openalex.org/W1977655452","https://openalex.org/W2561027863","https://openalex.org/W2775361682","https://openalex.org/W2782435507","https://openalex.org/W2884288731","https://openalex.org/W2901112449","https://openalex.org/W2942096073","https://openalex.org/W2947094677","https://openalex.org/W2967427547","https://openalex.org/W3035790680","https://openalex.org/W3110084462","https://openalex.org/W3126673178","https://openalex.org/W3180197665","https://openalex.org/W4205769419","https://openalex.org/W4214644029","https://openalex.org/W4313639260","https://openalex.org/W4383097706","https://openalex.org/W4386280002","https://openalex.org/W4393180309"],"related_works":[],"abstract_inverted_index":{"Soft":[0],"robots":[1,88,110],"are":[2],"promising":[3,42],"to":[4,82,105,111,132],"offer":[5],"flexibility":[6],"in":[7,28,33,64,137,151,175,186,202],"environmental":[8],"interaction":[9],"tasks":[10],"through":[11],"compliant":[12],"deformations.":[13],"However,":[14],"the":[15,49,134,138,147],"infinite":[16],"degrees":[17],"of":[18,23,108,180],"freedom":[19],"and":[20,31,58,204],"high":[21],"nonlinearity":[22],"dynamics":[24,107],"pose":[25],"significant":[26],"challenges":[27],"dynamic":[29],"modeling":[30],"control":[32,84,167,170],"soft":[34,65,87,109,189],"robots.":[35,66],"While":[36],"online":[37],"reinforcement":[38],"learning":[39,52,164],"(RL)":[40],"is":[41,118,130,143,184],"for":[43,86],"designing":[44],"policies":[45,85],"directly":[46],"from":[47,55,146],"data,":[48],"black-box":[50,148],"policy":[51,136,149,163,176],"process":[53],"suffers":[54],"data":[56],"inefficiency":[57],"sim-to-real":[59],"gap,":[60],"limiting":[61],"its":[62],"applications":[63],"To":[67],"address":[68],"these":[69],"challenges,":[70],"we":[71,98],"propose":[72],"a":[73,101,112,127,187],"novel":[74],"offline":[75,123,153],"RL":[76,124,154],"with":[77,126,165],"Koopman":[78,114,158],"operators":[79],"(KORL)":[80],"framework":[81,183],"generate":[83],"without":[89],"using":[90],"physical":[91],"simulators":[92],"or":[93],"real-world":[94,188],"interactions.":[95],"In":[96],"particular,":[97],"first":[99],"utilize":[100],"deep":[102],"neural":[103],"network":[104],"map":[106],"lifted":[113],"observable":[115,140,159],"space,":[116],"which":[117],"inherently":[119],"linear.":[120],"Then,":[121],"an":[122],"algorithm":[125],"control-informed":[128],"actor":[129],"designed":[131,157],"learn":[133],"robotic":[135,190],"linear":[139,166],"space.":[141],"This":[142],"significantly":[144],"different":[145],"design":[150],"existing":[152],"paradigms.":[155],"The":[156,178],"enables":[160],"efficient":[161],"model-free":[162],"theory,":[168],"improving":[169],"performance":[171],"while":[172],"preserving":[173],"interpretability":[174],"learning.":[177],"effectiveness":[179],"our":[181,197],"KORL":[182],"validated":[185],"system.":[191],"Comparative":[192],"experimental":[193],"results":[194],"demonstrate":[195],"that":[196],"method":[198],"outperforms":[199],"state-of-the-art":[200],"methods":[201],"target-reaching":[203],"trajectory-tracking":[205],"tasks.":[206]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}