{"id":"https://openalex.org/W4407129030","doi":"https://doi.org/10.1109/mra.2025.3527284","title":"I-CTRL: Imitation to Control Humanoid Robots Through Bounded Residual Reinforcement Learning","display_name":"I-CTRL: Imitation to Control Humanoid Robots Through Bounded Residual Reinforcement Learning","publication_year":2025,"publication_date":"2025-02-04","ids":{"openalex":"https://openalex.org/W4407129030","doi":"https://doi.org/10.1109/mra.2025.3527284"},"language":"en","primary_location":{"id":"doi:10.1109/mra.2025.3527284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mra.2025.3527284","pdf_url":null,"source":{"id":"https://openalex.org/S132261465","display_name":"IEEE Robotics & Automation Magazine","issn_l":"1070-9932","issn":["1070-9932","1558-223X"],"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 Robotics &amp; Automation Magazine","raw_type":"journal-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/A5113085979","display_name":"Yashuai Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Yashuai Yan","raw_affiliation_strings":["Autonomous Systems Lab, Technische Universit&#x00E4;t Wien (TU Wien), Vienna, Austria"],"raw_orcid":"https://orcid.org/0009-0005-5489-6273","affiliations":[{"raw_affiliation_string":"Autonomous Systems Lab, Technische Universit&#x00E4;t Wien (TU Wien), Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013385561","display_name":"Esteve Valls Mascaro","orcid":"https://orcid.org/0000-0001-5147-7704"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Esteve Valls Mascaro","raw_affiliation_strings":["Autonomous Systems Lab, Technische Universit&#x00E4;t Wien (TU Wien), Vienna, Austria"],"raw_orcid":"https://orcid.org/0000-0003-4195-8672","affiliations":[{"raw_affiliation_string":"Autonomous Systems Lab, Technische Universit&#x00E4;t Wien (TU Wien), Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045325280","display_name":"Tobias Egle","orcid":"https://orcid.org/0000-0002-4765-2415"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Tobias Egle","raw_affiliation_strings":["Robotics Systems Lab, Technische Universit&#x00E4;t Wien (TU Wien), Vienna, Austria"],"raw_orcid":"https://orcid.org/0000-0002-4765-2415","affiliations":[{"raw_affiliation_string":"Robotics Systems Lab, Technische Universit&#x00E4;t Wien (TU Wien), Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088081800","display_name":"Dongheui Lee","orcid":"https://orcid.org/0000-0003-1897-7664"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Dongheui Lee","raw_affiliation_strings":["Autonomous Systems Lab, Technische Universit&#x00E4;t Wien (TU Wien), Vienna, Austria"],"raw_orcid":"https://orcid.org/0000-0003-1897-7664","affiliations":[{"raw_affiliation_string":"Autonomous Systems Lab, Technische Universit&#x00E4;t Wien (TU Wien), Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145847075"],"apc_list":null,"apc_paid":null,"fwci":8.376,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.97014325,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"32","issue":"1","first_page":"59","last_page":"67"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9836000204086304,"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":0.9836000204086304,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9768000245094299,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.7798365354537964},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.7302297353744507},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7147328853607178},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6420572996139526},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6030578017234802},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5852178335189819},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5579337477684021},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.5425279140472412},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4482753276824951},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3298197388648987},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19149520993232727},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14344024658203125},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10409516096115112}],"concepts":[{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.7798365354537964},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.7302297353744507},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7147328853607178},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6420572996139526},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6030578017234802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5852178335189819},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5579337477684021},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5425279140472412},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4482753276824951},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3298197388648987},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19149520993232727},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14344024658203125},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10409516096115112},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mra.2025.3527284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mra.2025.3527284","pdf_url":null,"source":{"id":"https://openalex.org/S132261465","display_name":"IEEE Robotics & Automation Magazine","issn_l":"1070-9932","issn":["1070-9932","1558-223X"],"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 Robotics &amp; Automation Magazine","raw_type":"journal-article"},{"id":"pmh:oai:elib.dlr.de:221975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/MRA.2025.3527284>.","pdf_url":null,"source":{"id":"https://openalex.org/S4377196266","display_name":"elib (German Aerospace Center)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2898391981","host_organization_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","host_organization_lineage":["https://openalex.org/I2898391981"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G138487048","display_name":"INteractive robots that intuitiVely lEarn to inVErt tasks by ReaSoning about their Execution","funder_award_id":"101136067","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G2012205792","display_name":"European Training Network on  PErsonalized Robotics as SErvice Oriented applications","funder_award_id":"955778","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1994275787","https://openalex.org/W2003013030","https://openalex.org/W2098516422","https://openalex.org/W2138136244","https://openalex.org/W2527952597","https://openalex.org/W2796290181","https://openalex.org/W2964114602","https://openalex.org/W3020839343","https://openalex.org/W3147968035","https://openalex.org/W4249010688","https://openalex.org/W4387005676","https://openalex.org/W4390480930","https://openalex.org/W4390874171","https://openalex.org/W4402354017","https://openalex.org/W4405786155","https://openalex.org/W6741002519","https://openalex.org/W6796772303","https://openalex.org/W6846664724","https://openalex.org/W6870604698"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2745063183"],"abstract_inverted_index":{"Humanoid":[0,86],"robots":[1,69],"have":[2],"the":[3,28,77,154,160],"potential":[4],"to":[5,60,84,129],"mimic":[6],"human":[7,79],"motions":[8,16],"with":[9,110],"high":[10],"visual":[11,33,164],"fidelity,":[12],"yet":[13],"translating":[14],"these":[15,52],"into":[17],"practical":[18,47],"physical":[19,166],"execution":[20],"remains":[21],"a":[22,39,98,137,148],"significant":[23,40],"challenge.":[24],"Existing":[25],"techniques":[26],"in":[27,46,107,152],"graphics":[29],"community":[30],"often":[31],"prioritize":[32],"fidelity":[34],"over":[35,101],"physics-based":[36,62],"feasibility,":[37],"posing":[38],"challenge":[41],"for":[42,168],"deploying":[43],"bipedal":[44,157],"systems":[45],"applications.":[48],"This":[49],"article":[50],"addresses":[51],"issues":[53],"through":[54],"bounded":[55],"residual":[56],"reinforcement":[57],"learning":[58],"(RL)":[59],"produce":[61],"high-quality":[63],"motion":[64,72,95,108,132,170],"imitation":[65,96,109],"onto":[66],"legged":[67],"humanoid":[68],"that":[70,115],"enhance":[71],"resemblance":[73],"while":[74],"successfully":[75],"following":[76],"reference":[78],"trajectory.":[80],"Our":[81],"framework,":[82],"Imitation":[83],"Control":[85],"Robots":[87],"Through":[88],"Bounded":[89],"Residual":[90],"Reinforcement":[91],"Learning":[92],"(I-CTRL),":[93],"reformulates":[94],"as":[97],"constrained":[99],"refinement":[100],"nonphysics-based":[102],"retargeted":[103],"motions.":[104,143],"I-CTRL":[105],"excels":[106],"simple":[111],"and":[112,165],"unique":[113],"rewards":[114],"generalize":[116],"across":[117,141],"five":[118],"robots.":[119],"Moreover,":[120],"our":[121],"framework":[122],"introduces":[123],"an":[124],"automatic":[125],"priority":[126],"scheduler":[127],"(APS)":[128],"manage":[130],"large-scale":[131],"datasets":[133],"when":[134],"efficiently":[135],"training":[136],"unified":[138],"RL":[139],"policy":[140],"diverse":[142],"The":[144],"proposed":[145],"approach":[146],"signifies":[147],"crucial":[149],"step":[150],"forward":[151],"advancing":[153],"control":[155],"of":[156,162],"robots,":[158],"emphasizing":[159],"importance":[161],"aligning":[163],"realism":[167],"successful":[169],"imitation.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-02-05T00:00:00"}
