{"id":"https://openalex.org/W4415524605","doi":"https://doi.org/10.1109/humanoids65713.2025.11203058","title":"Gait-Conditioned Reinforcement Learning with Multi-Phase Curriculum for Humanoid Locomotion","display_name":"Gait-Conditioned Reinforcement Learning with Multi-Phase Curriculum for Humanoid Locomotion","publication_year":2025,"publication_date":"2025-09-30","ids":{"openalex":"https://openalex.org/W4415524605","doi":"https://doi.org/10.1109/humanoids65713.2025.11203058"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids65713.2025.11203058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids65713.2025.11203058","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":"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/A5109710738","display_name":"Tianhu Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tianhu Peng","raw_affiliation_strings":["University College London,Department of Computer Science,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London,Department of Computer Science,UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114155254","display_name":"Lingfan Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lingfan Bao","raw_affiliation_strings":["University College London,Department of Computer Science,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London,Department of Computer Science,UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026845307","display_name":"Chengxu Zhou","orcid":"https://orcid.org/0000-0002-6677-0855"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chengxu Zhou","raw_affiliation_strings":["University College London,Department of Computer Science,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London,Department of Computer Science,UK","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4858,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.6776322,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9980000257492065,"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":0.9980000257492065,"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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.9488000273704529,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9002000093460083,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.7889000177383423},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7656000256538391},{"id":"https://openalex.org/keywords/gait","display_name":"Gait","score":0.5231999754905701},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5101000070571899},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.44190001487731934},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.4187999963760376},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.40220001339912415},{"id":"https://openalex.org/keywords/motion-control","display_name":"Motion control","score":0.3935999870300293}],"concepts":[{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.7889000177383423},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7656000256538391},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5559999942779541},{"id":"https://openalex.org/C151800584","wikidata":"https://www.wikidata.org/wiki/Q2370000","display_name":"Gait","level":2,"score":0.5231999754905701},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5101000070571899},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.44190001487731934},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43459999561309814},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4187999963760376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4058000147342682},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.40220001339912415},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.3935999870300293},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.34209999442100525},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.3156999945640564},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.3107999861240387},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3012000024318695},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2858000099658966},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/humanoids65713.2025.11203058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids65713.2025.11203058","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:eprints.ucl.ac.uk.OAI2:10219246","is_oa":false,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10219246/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"In:  2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids).  (pp. pp. 1087-1093).  IEEE: Seoul, Korea, Republic of. (2025)","raw_type":"Proceedings paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2528243200","display_name":null,"funder_award_id":"RG\\R2\\232409","funder_id":"https://openalex.org/F4320320006","funder_display_name":"Royal Society"}],"funders":[{"id":"https://openalex.org/F4320320006","display_name":"Royal Society","ror":"https://ror.org/03wnrjx87"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2018444584","https://openalex.org/W2064675550","https://openalex.org/W2082677043","https://openalex.org/W2090190159","https://openalex.org/W2146469560","https://openalex.org/W2784449021","https://openalex.org/W2796290181","https://openalex.org/W2911087563","https://openalex.org/W2951360122","https://openalex.org/W2990747716","https://openalex.org/W3108412994","https://openalex.org/W3147968035","https://openalex.org/W3176539729","https://openalex.org/W3206620955","https://openalex.org/W3206762371","https://openalex.org/W4229081732","https://openalex.org/W4312606126","https://openalex.org/W4312900898","https://openalex.org/W4390874171","https://openalex.org/W4394872716","https://openalex.org/W4400362143","https://openalex.org/W4405785208","https://openalex.org/W4405873188","https://openalex.org/W4412192314"],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,21,36,116],"unified":[3],"gait-conditioned":[4],"reinforcement":[5],"learning":[6],"framework":[7],"that":[8],"enables":[9],"humanoid":[10,124],"robots":[11],"to":[12],"perform":[13],"standing,":[14,89,103],"walking,":[15,90,104],"running,":[16,91],"and":[17,43,59,75,92,105,110,122,129],"smooth":[18],"transitions":[19],"within":[20],"single":[22],"recurrent":[23],"policy.":[24],"A":[25,68],"compact":[26],"reward":[27,41,49],"routing":[28],"mechanism":[29],"dynamically":[30],"activates":[31],"gait-specific":[32],"objectives":[33],"based":[34],"on":[35],"one-hot":[37],"gait":[38,73,93],"ID,":[39],"mitigating":[40],"interference":[42],"supporting":[44],"stable":[45,109],"multi-gait":[46],"learning.":[47],"Human-inspired":[48],"terms":[50],"promote":[51],"biomechanically":[52],"natural":[53],"motions,":[54],"such":[55],"as":[56],"straight-knee":[57],"stance":[58],"coordinated":[60,111],"arm-leg":[61],"swing,":[62],"without":[63],"requiring":[64],"motion":[65],"capture":[66],"data.":[67],"structured":[69],"curriculum":[70],"progressively":[71],"introduces":[72],"complexity":[74],"expands":[76],"command":[77],"space":[78],"over":[79],"multiple":[80],"phases.":[81],"In":[82],"simulation,":[83],"the":[84,96],"policy":[85],"successfully":[86],"achieves":[87],"robust":[88],"transitions.":[94],"On":[95],"real":[97],"Unitree":[98],"G1":[99],"humanoid,":[100],"we":[101],"validate":[102],"walk-to-stand":[106],"transitions,":[107],"demonstrating":[108],"locomotion.":[112],"This":[113],"work":[114],"provides":[115],"scalable,":[117],"reference-free":[118],"solution":[119],"toward":[120],"versatile":[121],"naturalistic":[123],"control":[125],"across":[126],"diverse":[127],"modes":[128],"environments.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-13T07:54:00.901334","created_date":"2025-10-24T00:00:00"}
