{"id":"https://openalex.org/W2083456681","doi":"https://doi.org/10.1109/humanoids.2013.7030010","title":"Trajectory-model-based reinforcement learning: Application to bimanual humanoid motor learning with a closed-chain constraint","display_name":"Trajectory-model-based reinforcement learning: Application to bimanual humanoid motor learning with a closed-chain constraint","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W2083456681","doi":"https://doi.org/10.1109/humanoids.2013.7030010","mag":"2083456681"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids.2013.7030010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2013.7030010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids)","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/A5067055140","display_name":"Norikazu Sugimoto","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Norikazu Sugimoto","raw_affiliation_strings":["Department of Brain Machine Interface, National Institute of Information and Communications Technology, Suita, Osaka, Japan","Department of Brain Machine Interface, Center for Information and Neural Networks, National Institute of Information and Communications Technology, 1-4 Yamadaoka, Suita, Osaka, 565-0871, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Brain Machine Interface, National Institute of Information and Communications Technology, Suita, Osaka, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Department of Brain Machine Interface, Center for Information and Neural Networks, National Institute of Information and Communications Technology, 1-4 Yamadaoka, Suita, Osaka, 565-0871, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025458882","display_name":"Jun Morimoto","orcid":"https://orcid.org/0000-0002-4115-1919"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Morimoto","raw_affiliation_strings":["Department of Brain Robot Interface, ATR Computational Neuroscience Laboratories, Kyoto, Japan","Department of Brain Robot Interface, ATR Computational Neuroscience Laboratories, 2-2-2 Seika, Hikaridai, Souraku, Kyoto, 619-0237, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Brain Robot Interface, ATR Computational Neuroscience Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I4210104143"]},{"raw_affiliation_string":"Department of Brain Robot Interface, ATR Computational Neuroscience Laboratories, 2-2-2 Seika, Hikaridai, Souraku, Kyoto, 619-0237, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5067055140"],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":0.9992,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.76611254,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"429","last_page":"434"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T10784","display_name":"Muscle activation and electromyography studies","score":0.996999979019165,"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"}},{"id":"https://openalex.org/T10982","display_name":"Motor Control and Adaptation","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8508542776107788},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.7620095610618591},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7419288158416748},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.7059093713760376},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6130458116531372},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5905439853668213},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5528855919837952},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5442581176757812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4848374128341675},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4526769816875458},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.43033087253570557},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.41124826669692993},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.2705318331718445},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12187808752059937}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8508542776107788},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.7620095610618591},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7419288158416748},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7059093713760376},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6130458116531372},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5905439853668213},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5528855919837952},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5442581176757812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4848374128341675},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4526769816875458},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.43033087253570557},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.41124826669692993},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2705318331718445},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12187808752059937},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/humanoids.2013.7030010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2013.7030010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W658381347","https://openalex.org/W1925816294","https://openalex.org/W1970890515","https://openalex.org/W2025752438","https://openalex.org/W2026659355","https://openalex.org/W2039091159","https://openalex.org/W2042929944","https://openalex.org/W2099768828","https://openalex.org/W2113501460","https://openalex.org/W2120742447","https://openalex.org/W2140135625","https://openalex.org/W2155027007","https://openalex.org/W3005581722","https://openalex.org/W4295133295","https://openalex.org/W6640290305","https://openalex.org/W6674989108","https://openalex.org/W6680657880","https://openalex.org/W6683204974"],"related_works":["https://openalex.org/W2152087638","https://openalex.org/W2626492911","https://openalex.org/W3138568041","https://openalex.org/W3117414450","https://openalex.org/W2751969933","https://openalex.org/W3185319788","https://openalex.org/W2102384057","https://openalex.org/W3014662868","https://openalex.org/W4316041871","https://openalex.org/W2097364276"],"abstract_inverted_index":{"We":[0,50,113],"propose":[1],"a":[2,11,61,66,73,97,110,116,125,137],"reinforcement":[3],"learning":[4,26,101],"(RL)":[5],"framework":[6],"to":[7,33,43,56,96,107,123,127],"improve":[8,34,57],"policies":[9],"for":[10],"high-dimensional":[12],"system":[13],"through":[14],"fewer":[15],"interactions":[16,135],"with":[17,38],"real":[18,118,138],"environments":[19],"than":[20],"standard":[21],"RL":[22,69],"methods.":[23],"In":[24,88],"our":[25,93],"framework,":[27,70],"we":[28,91,105],"first":[29],"use":[30,52],"off-line":[31],"simulations":[32],"the":[35,53,58,76,80,86],"controller":[36],"parameters":[37],"an":[39],"approximated":[40,54],"environment":[41],"model":[42],"generate":[44],"samples":[45],"along":[46],"locally":[47],"optimized":[48],"trajectories.":[49],"then":[51],"dynamics":[55],"performance":[59],"of":[60,79],"tool":[62],"manipulation":[63],"task":[64,102],"in":[65,103,136],"path":[67],"integral":[68],"which":[71,104],"updates":[72],"policy":[74],"from":[75],"sampled":[77],"trajectories":[78],"state":[81],"and":[82,85],"action":[83],"vectors":[84],"cost.":[87],"this":[89],"study,":[90],"apply":[92],"proposed":[94],"method":[95],"bimanual":[98],"humanoid":[99,119],"motor":[100],"need":[106],"explicitly":[108],"consider":[109],"closed-chain":[111],"constraint.":[112],"show":[114],"that":[115],"51-DOF":[117],"robot":[120],"can":[121],"learn":[122],"manipulate":[124],"rod":[126],"hit":[128],"via-points":[129],"using":[130],"both":[131],"arms":[132],"within":[133],"36":[134],"environment.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}