{"id":"https://openalex.org/W4416676831","doi":"https://doi.org/10.1109/sbr/wre66973.2025.11249656","title":"Residual Reinforcement Learning to Generate a Closed-Loop Policy from a Keyframe Kick Motion","display_name":"Residual Reinforcement Learning to Generate a Closed-Loop Policy from a Keyframe Kick Motion","publication_year":2025,"publication_date":"2025-10-13","ids":{"openalex":"https://openalex.org/W4416676831","doi":"https://doi.org/10.1109/sbr/wre66973.2025.11249656"},"language":null,"primary_location":{"id":"doi:10.1109/sbr/wre66973.2025.11249656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sbr/wre66973.2025.11249656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Brazilian Symposium on Robotics (SBR) and 2025 Workshop on Robotics in Education (WRE)","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/A5120665582","display_name":"Marcos Vin\u00edcius S. Passamani","orcid":null},"institutions":[{"id":"https://openalex.org/I107428990","display_name":"Instituto Tecnol\u00f3gico de Aeron\u00e1utica","ror":"https://ror.org/05vh67662","country_code":"BR","type":"education","lineage":["https://openalex.org/I107428990"]},{"id":"https://openalex.org/I4210123805","display_name":"Instituto de Aeron\u00e1utica e Espa\u00e7o","ror":"https://ror.org/025n1fp68","country_code":"BR","type":"other","lineage":["https://openalex.org/I4210123805"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Marcos Vin\u00edcius S. Passamani","raw_affiliation_strings":["Aeronautics Institute of Technology,São José dos Campos,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aeronautics Institute of Technology,São José dos Campos,Brazil","institution_ids":["https://openalex.org/I4210123805","https://openalex.org/I107428990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019218502","display_name":"Marcos R. O. A. M\u00e1ximo","orcid":"https://orcid.org/0000-0003-2944-4476"},"institutions":[{"id":"https://openalex.org/I4210123805","display_name":"Instituto de Aeron\u00e1utica e Espa\u00e7o","ror":"https://ror.org/025n1fp68","country_code":"BR","type":"other","lineage":["https://openalex.org/I4210123805"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Marcos R. O. A. Maximo","raw_affiliation_strings":["Institute of Technology,Computer Science Division Aeronautics,São José dos Campos,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Technology,Computer Science Division Aeronautics,São José dos Campos,Brazil","institution_ids":["https://openalex.org/I4210123805"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064656646","display_name":"Luckeciano C. Melo","orcid":"https://orcid.org/0000-0003-2599-6265"},"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"]},{"id":"https://openalex.org/I4210146410","display_name":"Science Oxford","ror":"https://ror.org/04j8yhy50","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210146410"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Luckeciano C. Melo","raw_affiliation_strings":["University of Oxford and AKCIT,Oxford,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford and AKCIT,Oxford,UK","institution_ids":["https://openalex.org/I4210146410","https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.17306454,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"147","last_page":"151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7037000060081482,"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":0.7037000060081482,"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":0.17100000381469727,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.039400000125169754,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7020000219345093},{"id":"https://openalex.org/keywords/football","display_name":"Football","score":0.6782000064849854},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5557000041007996},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.5110999941825867},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.4560999870300293},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.40700000524520874}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7020000219345093},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.682699978351593},{"id":"https://openalex.org/C2778444522","wikidata":"https://www.wikidata.org/wiki/Q1081491","display_name":"Football","level":2,"score":0.6782000064849854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6460999846458435},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5557000041007996},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.5110999941825867},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4560999870300293},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.40700000524520874},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3896999955177307},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3831000030040741},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.3747999966144562},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C2780465443","wikidata":"https://www.wikidata.org/wiki/Q852061","display_name":"Champion","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.301800012588501},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.28630000352859497},{"id":"https://openalex.org/C17816587","wikidata":"https://www.wikidata.org/wiki/Q1501872","display_name":"Inverse kinematics","level":3,"score":0.25870001316070557}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sbr/wre66973.2025.11249656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sbr/wre66973.2025.11249656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Brazilian Symposium on Robotics (SBR) and 2025 Workshop on Robotics in Education (WRE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315144","display_name":"MathWorks","ror":"https://ror.org/01n8qtk87"},{"id":"https://openalex.org/F4320322569","display_name":"STMicroelectronics","ror":"https://ror.org/00wm3b005"},{"id":"https://openalex.org/F4320330107","display_name":"Empresa Brasileira de Pesquisa e Inova\u00e7\u00e3o Industrial","ror":null},{"id":"https://openalex.org/F8956940760","display_name":"Enhancing Diversity in Graduate Education Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W277265366","https://openalex.org/W2565085884","https://openalex.org/W2925173345","https://openalex.org/W3095980510","https://openalex.org/W3160597453","https://openalex.org/W3163161787","https://openalex.org/W3167879406","https://openalex.org/W4224941573","https://openalex.org/W4393194491","https://openalex.org/W4409377352"],"related_works":[],"abstract_inverted_index":{"The":[0,157],"RoboCup":[1,42],"is":[2,43,68,92],"an":[3],"international":[4],"robot":[5],"football":[6,56],"competition":[7],"that":[8,102],"aims":[9],"to":[10,19,115,131,151],"push":[11],"the":[12,38,44,84,100,108,112,145,162,165],"boundaries":[13],"of":[14,25,37,41,51,55,97,164],"robotics":[15],"and":[16,121,175],"artificial":[17],"intelligence":[18],"a":[20,23,30,52,59,69,129,142,153],"point":[21],"where":[22],"team":[24],"robotic":[26],"players":[27],"could":[28],"beat":[29],"human":[31],"World":[32],"Cup":[33],"champion":[34],"team.":[35],"One":[36],"major":[39],"categories":[40],"3D":[45],"Soccer":[46],"Simulation":[47],"League,":[48],"which":[49,110,139],"consists":[50],"full":[53],"game":[54],"executed":[57],"in":[58,99,119,138],"physically":[60],"simulated":[61],"environment.":[62],"In":[63],"this":[64,90],"league,":[65],"keyframe":[66,133,154],"interpolation":[67],"very":[70],"common":[71],"practice":[72],"for":[73],"executing":[74],"specific":[75],"tasks":[76],"such":[77],"as":[78],"getting":[79],"up,":[80],"diving,":[81],"or":[82,117],"kicking":[83],"ball.":[85],"A":[86],"primary":[87],"problem":[88],"with":[89],"method":[91],"its":[93,170],"open-loop":[94],"kinematic":[95],"description":[96],"movement,":[98],"sense":[101],"it":[103],"lacks":[104],"feedback":[105],"information":[106],"from":[107],"world,":[109],"makes":[111],"behavior":[113],"prone":[114],"underperformance":[116],"failure":[118],"complex":[120],"noisy":[122],"environments.":[123],"This":[124],"work":[125],"contributes":[126],"by":[127],"providing":[128],"methodology":[130],"enhance":[132],"movements":[134],"using":[135,144],"residual":[136],"learning,":[137],"we":[140],"train":[141],"policy":[143],"Proximal":[146],"Policy":[147],"Optimization":[148],"(PPO)":[149],"algorithm":[150],"improve":[152],"kick":[155,166],"motion.":[156],"approach":[158],"not":[159],"only":[160],"improved":[161],"reliability":[163],"but":[167],"also":[168],"enhanced":[169],"performance":[171],"metrics,":[172],"including":[173],"distance":[174],"precision.":[176]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-25T00:00:00"}