{"id":"https://openalex.org/W4312568594","doi":"https://doi.org/10.1109/iros47612.2022.9981540","title":"Embedding Koopman Optimal Control in Robot Policy Learning","display_name":"Embedding Koopman Optimal Control in Robot Policy Learning","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4312568594","doi":"https://doi.org/10.1109/iros47612.2022.9981540"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981540","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981540","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 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/A5067144254","display_name":"Hang Yin","orcid":"https://orcid.org/0000-0002-3599-440X"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Hang Yin","raw_affiliation_strings":["CAS/RPL, KTH Royal Institute of Technology,Stockholm,Sweden","CAS/RPL, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"CAS/RPL, KTH Royal Institute of Technology,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"CAS/RPL, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020344044","display_name":"Michael C. Welle","orcid":"https://orcid.org/0000-0003-3827-3824"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Michael C. Welle","raw_affiliation_strings":["CAS/RPL, KTH Royal Institute of Technology,Stockholm,Sweden","CAS/RPL, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"CAS/RPL, KTH Royal Institute of Technology,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"CAS/RPL, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074819656","display_name":"Danica Kragic","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Danica Kragic","raw_affiliation_strings":["CAS/RPL, KTH Royal Institute of Technology,Stockholm,Sweden","CAS/RPL, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"CAS/RPL, KTH Royal Institute of Technology,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"CAS/RPL, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5067144254"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.8745,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70283019,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"13392","last_page":"13399"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9994000196456909,"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":0.9994000196456909,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9954000115394592,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9925000071525574,"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":0.7090305089950562},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6981767416000366},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6571356654167175},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.6561704874038696},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.5855786800384521},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5205491781234741},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5171022415161133},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5067916512489319},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.49858665466308594},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4754880666732788},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.42102938890457153},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"Convex optimization","score":0.4122186303138733},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4071713387966156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36698710918426514},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3455522060394287},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.2796611487865448},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2417263686656952},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22848549485206604}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7090305089950562},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6981767416000366},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6571356654167175},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.6561704874038696},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.5855786800384521},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5205491781234741},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5171022415161133},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5067916512489319},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.49858665466308594},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4754880666732788},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.42102938890457153},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.4122186303138733},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4071713387966156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36698710918426514},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3455522060394287},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.2796611487865448},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2417263686656952},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22848549485206604},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9981540","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981540","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 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/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"},{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1583837637","https://openalex.org/W1997054581","https://openalex.org/W2063741856","https://openalex.org/W2103831616","https://openalex.org/W2133932631","https://openalex.org/W2559655401","https://openalex.org/W2560674852","https://openalex.org/W2561027863","https://openalex.org/W2612690371","https://openalex.org/W2732671178","https://openalex.org/W2736601468","https://openalex.org/W2747329762","https://openalex.org/W2758399700","https://openalex.org/W2777417212","https://openalex.org/W2781726626","https://openalex.org/W2889731659","https://openalex.org/W2963092423","https://openalex.org/W2964119648","https://openalex.org/W2966077329","https://openalex.org/W2973004389","https://openalex.org/W2981603589","https://openalex.org/W3003629310","https://openalex.org/W3009152446","https://openalex.org/W3044718039","https://openalex.org/W3091037773","https://openalex.org/W3098172061","https://openalex.org/W3104183683","https://openalex.org/W3110084462","https://openalex.org/W3126673178","https://openalex.org/W3173693019","https://openalex.org/W3201330981","https://openalex.org/W3205312991","https://openalex.org/W3207133204","https://openalex.org/W4212774754","https://openalex.org/W4226325906","https://openalex.org/W4287121934","https://openalex.org/W4293469469","https://openalex.org/W6617744952","https://openalex.org/W6623316541","https://openalex.org/W6711952718","https://openalex.org/W6734065107","https://openalex.org/W6740792189","https://openalex.org/W6743945476","https://openalex.org/W6747473740","https://openalex.org/W6752217255","https://openalex.org/W6754302822","https://openalex.org/W6758539823","https://openalex.org/W6767977373","https://openalex.org/W6769286903","https://openalex.org/W6771685107","https://openalex.org/W6772521232","https://openalex.org/W6774803112","https://openalex.org/W6777074133","https://openalex.org/W6780559895","https://openalex.org/W6796908064","https://openalex.org/W6801457259","https://openalex.org/W6803702928"],"related_works":["https://openalex.org/W2775112436","https://openalex.org/W3326829","https://openalex.org/W2350013143","https://openalex.org/W3046172785","https://openalex.org/W2136367476","https://openalex.org/W2385948153","https://openalex.org/W2353814909","https://openalex.org/W2203843426","https://openalex.org/W2049369111","https://openalex.org/W34573732"],"abstract_inverted_index":{"Embedding":[0],"an":[1,97],"optimization":[2,20],"process":[3],"has":[4],"been":[5],"explored":[6],"for":[7,30,93,114],"imposing":[8],"efficient":[9,101],"and":[10,33,55,68,100,109,112,117],"flexible":[11],"policy":[12,26,76],"structures.":[13],"Existing":[14],"work":[15],"often":[16],"build":[17],"upon":[18],"nonlinear":[19],"with":[21,43],"explicitly":[22],"iteration":[23],"steps,":[24],"making":[25],"inference":[27],"prohibitively":[28],"expensive":[29],"online":[31],"learning":[32,94],"real-time":[34],"control.":[35],"Our":[36,86],"approach":[37,87],"embeds":[38],"a":[39,44,52,58,64,127],"linear-quadratic-regulator":[40],"(LQR)":[41],"formulation":[42],"Koopman":[45],"representation,":[46],"thus":[47],"exhibiting":[48],"the":[49,75],"tractability":[50],"from":[51,57],"closed-form":[53],"solution":[54],"richness":[56],"non-convex":[59],"neural":[60],"network.":[61],"We":[62,120],"use":[63],"few":[65],"auxiliary":[66],"objectives":[67],"reparameterization":[69],"to":[70,82,90],"enforce":[71],"optimality":[72,98],"conditions":[73],"of":[74],"that":[77],"can":[78],"be":[79,91],"easily":[80],"integrated":[81],"standard":[83],"gradient-based":[84],"learning.":[85],"is":[88],"shown":[89],"effective":[92],"policies":[95],"rendering":[96],"structure":[99],"reinforcement":[102],"learning,":[103],"including":[104],"simulated":[105],"pendulum":[106],"control,":[107],"2D":[108],"3D":[110],"walking,":[111],"manipulation":[113],"both":[115],"rigid":[116],"deformable":[118],"objects.":[119],"also":[121],"demonstrate":[122],"real":[123],"world":[124],"application":[125],"in":[126],"robot":[128],"pivoting":[129],"task.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-08T23:21:52.890332","created_date":"2025-10-10T00:00:00"}