{"id":"https://openalex.org/W7225296580","doi":"https://doi.org/10.5302/j.icros.2026.26.0215","title":"Optimization-based Imitation Learning for Stable Action Generation","display_name":"Optimization-based Imitation Learning for Stable Action Generation","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7225296580","doi":"https://doi.org/10.5302/j.icros.2026.26.0215"},"language":"en","primary_location":{"id":"doi:10.5302/j.icros.2026.26.0215","doi":"https://doi.org/10.5302/j.icros.2026.26.0215","is_oa":false,"landing_page_url":"https://doi.org/10.5302/j.icros.2026.26.0215","pdf_url":null,"source":{"id":"https://openalex.org/S4210183236","display_name":"Journal of Institute of Control Robotics and Systems","issn_l":"1976-5622","issn":["1976-5622","2233-4335"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["kci-registered","poland-40","russia-white-list-2"],"host_organization":"https://openalex.org/P4323366859","host_organization_name":"Institute of Control, Robotics and Systems","host_organization_lineage":["https://openalex.org/P4323366859"],"host_organization_lineage_names":["Institute of Control, Robotics and Systems"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Institute of Control, Robotics and Systems","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"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/A5148098625","display_name":"Euichan Heo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Euichan Heo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076219237","display_name":"\ud669\ucc2c\uc2dd","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chansik Hwang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088814754","display_name":"Jaehoon An","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaehoon An","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5160800897","display_name":"Inho Lee","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Inho Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"11","first_page":"1494","last_page":"1502"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8574000000953674,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8574000000953674,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.14149999618530273,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/imitation-learning","display_name":"imitation learning","score":0.8880000114440918},{"id":"https://openalex.org/keywords/robotic-manipulation","display_name":"robotic manipulation","score":0.6579999923706055},{"id":"https://openalex.org/keywords/action-refinement","display_name":"action refinement","score":0.4779999852180481},{"id":"https://openalex.org/keywords/peg-in-hole-task","display_name":"peg-in-hole task","score":0.8949999809265137},{"id":"https://openalex.org/keywords/behavioral-cloning","display_name":"behavior cloning","score":0.6340000033378601},{"id":"https://openalex.org/keywords/expert-demonstrations","display_name":"expert demonstrations","score":0.453000009059906},{"id":"https://openalex.org/keywords/mujoco","display_name":"MuJoCo","score":0.5789999961853027}],"concepts":[{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.633400022983551},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6134999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48969998955726624},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.42500001192092896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42500001192092896},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.382999986410141},{"id":"https://openalex.org/C183759332","wikidata":"https://www.wikidata.org/wiki/Q343680","display_name":"Action learning","level":4,"score":0.36329999566078186},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3513000011444092},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3052999973297119}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5302/j.icros.2026.26.0215","doi":"https://doi.org/10.5302/j.icros.2026.26.0215","is_oa":false,"landing_page_url":"https://doi.org/10.5302/j.icros.2026.26.0215","pdf_url":null,"source":{"id":"https://openalex.org/S4210183236","display_name":"Journal of Institute of Control Robotics and Systems","issn_l":"1976-5622","issn":["1976-5622","2233-4335"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["kci-registered","poland-40","russia-white-list-2"],"host_organization":"https://openalex.org/P4323366859","host_organization_name":"Institute of Control, Robotics and Systems","host_organization_lineage":["https://openalex.org/P4323366859"],"host_organization_lineage_names":["Institute of Control, Robotics and Systems"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Institute of Control, Robotics and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3045788060","https://openalex.org/W3196712826","https://openalex.org/W2762476664","https://openalex.org/W2911383979","https://openalex.org/W2969383898","https://openalex.org/W4313139794","https://openalex.org/W6941794198","https://openalex.org/W3004929771","https://openalex.org/W7167488900","https://openalex.org/W7221624962"],"abstract_inverted_index":{"Imitation":[0,65],"learning":[1],"is":[2,88,130,153,163],"widely":[3],"used":[4,131],"to":[5,49,97,204,223,228],"learn":[6],"robotic":[7],"manipulation":[8,225],"behaviors":[9],"from":[10,91,122,142],"expert":[11,92],"demonstrations,":[12],"but":[13],"conventional":[14],"behavior":[15],"cloning":[16],"primarily":[17],"minimizes":[18],"the":[19,40,59,99,106,123,135,143,150,156,160,167,174,201,210,213,217],"discrepancy":[20],"between":[21],"demonstrated":[22],"and":[23,31,43,79,94,159,199],"predicted":[24],"actions.":[25],"As":[26],"a":[27,70,74,110,116,179,184],"result,":[28],"task-oriented":[29],"objectives":[30],"execution":[32],"constraints":[33],"may":[34,47],"not":[35],"be":[36,229],"explicitly":[37],"reflected":[38],"in":[39,52],"learned":[41,100,151],"policy,":[42,73],"small":[44],"prediction":[45,77,137],"errors":[46],"lead":[48],"task":[50,101,117],"failure":[51],"states":[53],"that":[54,114],"are":[55],"insufficiently":[56],"covered":[57],"by":[58],"demonstrations.":[60],"This":[61],"paper":[62],"proposes":[63],"Optimization-Based":[64],"Learning":[66],"(OB-IL),":[67],"which":[68,139],"combines":[69],"pretrained":[71],"nominal":[72,85,175],"lightweight":[75],"residual":[76,80,107,118,128,136,152,168],"head,":[78,138],"quadratic":[81],"programming":[82],"(QP).":[83],"The":[84,126],"ACT":[86,145,157,176],"policy":[87,104,177],"initially":[89],"trained":[90],"demonstrations":[93],"then":[95],"frozen":[96,144],"preserve":[98],"behavior.":[102],"During":[103,148],"rollouts,":[105],"QP":[108],"computes":[109],"bounded":[111],"corrective":[112],"action":[113,162],"reduces":[115],"while":[119],"limiting":[120],"deviations":[121],"reference":[124],"action.":[125],"QP-generated":[127],"correction":[129],"as":[132],"supervision":[133],"for":[134,216],"predicts":[140],"corrections":[141],"feature":[146],"representation.":[147],"inference,":[149],"combined":[154],"with":[155,183],"output":[158],"resulting":[161],"further":[164],"refined":[165],"using":[166],"QP.":[169],"In":[170],"MuJoCo":[171],"peg-in-hole":[172],"experiments,":[173],"achieved":[178,194],"9.0%":[180],"success":[181,197],"rate":[182,198],"median":[185,202],"lateral":[186],"alignment":[187],"error":[188,203],"of":[189,212],"6.43":[190],"mm,":[191],"whereas":[192],"OB-IL":[193],"an":[195],"89.0%":[196],"reduced":[200],"0.85":[205],"mm.":[206],"These":[207],"results":[208],"support":[209],"effectiveness":[211],"proposed":[214],"approach":[215],"evaluated":[218],"precision":[219],"insertion":[220],"task;":[221],"extension":[222],"other":[224],"tasks":[226],"remains":[227],"validated":[230],"experimentally.":[231]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-11-06T00:00:00"}