{"id":"https://openalex.org/W4415524131","doi":"https://doi.org/10.1109/humanoids65713.2025.11203130","title":"Mechanical Intelligence-Aware Curriculum Reinforcement Learning for Humanoids with Parallel Actuation","display_name":"Mechanical Intelligence-Aware Curriculum Reinforcement Learning for Humanoids with Parallel Actuation","publication_year":2025,"publication_date":"2025-09-30","ids":{"openalex":"https://openalex.org/W4415524131","doi":"https://doi.org/10.1109/humanoids65713.2025.11203130"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids65713.2025.11203130","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids65713.2025.11203130","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.00273","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000602137","display_name":"Yusuke Tanaka","orcid":"https://orcid.org/0000-0002-7316-1425"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]},{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yusuke Tanaka","raw_affiliation_strings":["UCLA,Department of Mechanical and Aerospace Engineering,Los Angeles,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLA,Department of Mechanical and Aerospace Engineering,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I2799798094","https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082722944","display_name":"Aibin Zhu","orcid":"https://orcid.org/0000-0002-6346-4932"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]},{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alvin Zhu","raw_affiliation_strings":["UCLA,Department of Mechanical and Aerospace Engineering,Los Angeles,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLA,Department of Mechanical and Aerospace Engineering,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I2799798094","https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045981984","display_name":"Quanyou Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]},{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quanyou Wang","raw_affiliation_strings":["UCLA,Department of Mechanical and Aerospace Engineering,Los Angeles,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLA,Department of Mechanical and Aerospace Engineering,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I2799798094","https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068194893","display_name":"Dennis Hong","orcid":"https://orcid.org/0000-0002-1089-4373"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]},{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dennis Hong","raw_affiliation_strings":["UCLA,Department of Mechanical and Aerospace Engineering,Los Angeles,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLA,Department of Mechanical and Aerospace Engineering,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I2799798094","https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.15346243,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"882","last_page":"889"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9850999712944031,"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":0.9850999712944031,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9585999846458435,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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":0.9545999765396118,"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":0.7590000033378601},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5756999850273132},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.5740000009536743},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.4839000105857849},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.45410001277923584},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4449000060558319},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.42309999465942383},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.41929998993873596}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7590000033378601},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7056000232696533},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5756999850273132},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.5740000009536743},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.4839000105857849},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.45410001277923584},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4449000060558319},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.42309999465942383},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.39910000562667847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39419999718666077},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3425000011920929},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3400999903678894},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C17816587","wikidata":"https://www.wikidata.org/wiki/Q1501872","display_name":"Inverse kinematics","level":3,"score":0.31450000405311584},{"id":"https://openalex.org/C172707124","wikidata":"https://www.wikidata.org/wiki/Q423488","display_name":"Actuator","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C138094506","wikidata":"https://www.wikidata.org/wiki/Q12065277","display_name":"Parallel manipulator","level":3,"score":0.2768000066280365},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.25450000166893005},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/humanoids65713.2025.11203130","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids65713.2025.11203130","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.00273","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.00273","pdf_url":"https://arxiv.org/pdf/2507.00273","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.00273","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.00273","pdf_url":"https://arxiv.org/pdf/2507.00273","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W2210741219","https://openalex.org/W2295130897","https://openalex.org/W2377098276","https://openalex.org/W2415959992","https://openalex.org/W2909643285","https://openalex.org/W2910436940","https://openalex.org/W3011365898","https://openalex.org/W3088310808","https://openalex.org/W3093922502","https://openalex.org/W3130451601","https://openalex.org/W3204523122","https://openalex.org/W3206363598","https://openalex.org/W4283822920","https://openalex.org/W4285102304","https://openalex.org/W4313563143","https://openalex.org/W4389664936","https://openalex.org/W4394674699","https://openalex.org/W4394872716","https://openalex.org/W4401416291","https://openalex.org/W4404953314","https://openalex.org/W4404953378","https://openalex.org/W4405785589","https://openalex.org/W6903228279"],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,12,159],"(RL)":[2],"has":[3],"enabled":[4],"advances":[5],"in":[6,21,28,139,157],"humanoid":[7,93],"robot":[8],"locomotion,":[9],"yet":[10],"most":[11],"frameworks":[13],"do":[14],"not":[15],"account":[16],"for":[17,31,47,61,89,161],"mechanical":[18,117],"intelligence":[19],"embedded":[20],"parallel":[22,65,155,167],"actuation":[23,51],"mechanisms":[24,156],"due":[25],"to":[26,39],"limitations":[27],"simulator":[29],"support":[30],"closed":[32],"kinematic":[33],"chains.":[34],"This":[35,53,143],"omission":[36],"can":[37],"lead":[38],"inaccurate":[40],"motion":[41],"modeling":[42],"and":[43,58,73,77,137,149],"suboptimal":[44],"policies,":[45],"particularly":[46],"robots":[48],"with":[49,166],"high":[50],"complexity.":[52],"paper":[54],"presents":[55],"general":[56],"formulations":[57],"simulation":[59],"methods":[60],"three":[62],"types":[63],"of":[64,152],"mechanisms:":[66,168],"a":[67,70,74,79,91,128],"differential":[68],"pulley,":[69],"five-bar":[71],"linkage,":[72,76],"four-bar":[75],"trains":[78],"parallelmechanism":[80],"aware":[81],"policy":[82],"through":[83],"an":[84],"end-to-end":[85,158],"curriculum":[86],"RL":[87,125],"framework":[88],"BRUCE,":[90],"kid-sized":[92],"robot.":[94],"Unlike":[95],"prior":[96],"approaches":[97,148],"that":[98],"rely":[99],"on":[100],"simplified":[101],"serial":[102],"approximations,":[103],"we":[104],"simulate":[105],"all":[106],"closed-chain":[107],"constraints":[108],"natively":[109],"using":[110],"GPUaccelerated":[111],"MuJoCo":[112],"(MJX),":[113],"preserving":[114],"the":[115,146],"hardware's":[116],"nonlinear":[118],"properties":[119],"during":[120],"training.":[121],"We":[122],"benchmark":[123],"our":[124],"approach":[126],"against":[127],"model":[129],"predictive":[130],"controller":[131],"(MPC),":[132],"demonstrating":[133],"better":[134],"surface":[135],"generalization":[136],"performance":[138,150],"real-world":[140],"zero-shot":[141],"deployment.":[142],"work":[144],"highlights":[145],"computational":[147],"benefits":[151],"fully":[153],"simulating":[154],"pipelines":[160],"legged":[162],"humanoids.":[163],"Project":[164],"codes":[165],"https://github.com/alvister88/og_bruce":[169]},"counts_by_year":[],"updated_date":"2026-07-12T07:33:03.550515","created_date":"2025-10-10T00:00:00"}
