{"id":"https://openalex.org/W4416750124","doi":"https://doi.org/10.1109/iros60139.2025.11246585","title":"MoE-Loco: Mixture of Experts for Multitask Locomotion","display_name":"MoE-Loco: Mixture of Experts for Multitask Locomotion","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750124","doi":"https://doi.org/10.1109/iros60139.2025.11246585"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5005974148","display_name":"Runze Huang","orcid":"https://orcid.org/0000-0001-6640-6271"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Runhan Huang","raw_affiliation_strings":["Tsinghua University,IIIS,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,IIIS,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040608113","display_name":"Shaoting Zhu","orcid":"https://orcid.org/0009-0000-9294-6212"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoting Zhu","raw_affiliation_strings":["Tsinghua University,IIIS,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,IIIS,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041777043","display_name":"Yilun Du","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yilun Du","raw_affiliation_strings":["Massachusetts Institute of Technology,MA,USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,MA,USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085043204","display_name":"Hang Zhao","orcid":"https://orcid.org/0000-0003-2451-3719"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Zhao","raw_affiliation_strings":["Tsinghua University,IIIS,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,IIIS,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005974148"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.7591,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78121844,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"14218","last_page":"14225"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9070000052452087,"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":0.9070000052452087,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.031099999323487282,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.01940000057220459,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6753000020980835},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5665000081062317},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5602999925613403},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.37770000100135803},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.34610000252723694},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.33320000767707825}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6753000020980835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6686999797821045},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5665000081062317},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5602999925613403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.554099977016449},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4146000146865845},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.37770000100135803},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.34610000252723694},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":33,"referenced_works":["https://openalex.org/W2025653905","https://openalex.org/W2117130368","https://openalex.org/W2150884987","https://openalex.org/W2911087563","https://openalex.org/W2913340405","https://openalex.org/W2951360122","https://openalex.org/W2964335674","https://openalex.org/W3085046840","https://openalex.org/W3093922502","https://openalex.org/W3111294788","https://openalex.org/W3175254947","https://openalex.org/W4226143977","https://openalex.org/W4367016688","https://openalex.org/W4380551489","https://openalex.org/W4382365373","https://openalex.org/W4385430486","https://openalex.org/W4385825811","https://openalex.org/W4389665667","https://openalex.org/W4390494915","https://openalex.org/W4390873745","https://openalex.org/W4392763392","https://openalex.org/W4396820856","https://openalex.org/W4401415792","https://openalex.org/W4401416158","https://openalex.org/W4401416847","https://openalex.org/W4402354142","https://openalex.org/W4402449733","https://openalex.org/W4404351541","https://openalex.org/W4405785545","https://openalex.org/W4405786988","https://openalex.org/W4413917587","https://openalex.org/W4413918531","https://openalex.org/W4413945028"],"related_works":[],"abstract_inverted_index":{"We":[0,80],"present":[1],"MoE-Loco,":[2],"a":[3,18],"Mixture":[4],"of":[5],"Experts":[6],"(MoE)":[7],"framework":[8],"for":[9,12,74],"multitask":[10,49],"locomotion":[11,68],"legged":[13],"robots.":[14],"Our":[15,58],"method":[16],"enables":[17],"single":[19],"policy":[20],"to":[21],"handle":[22],"diverse":[23],"terrains,":[24],"including":[25],"bars,":[26],"pits,":[27],"stairs,":[28],"slopes,":[29],"and":[30,35,56,77,88,94],"baffles,":[31],"while":[32],"supporting":[33],"quadrupedal":[34],"bipedal":[36],"gaits.":[37],"Using":[38],"MoE,":[39],"we":[40],"mitigate":[41],"the":[42],"gradient":[43],"conflicts":[44],"that":[45,61],"typically":[46],"arise":[47],"in":[48,66,85],"reinforcement":[50],"learning,":[51],"improving":[52],"both":[53,86],"training":[54],"efficiency":[55],"performance.":[57],"experiments":[59],"demonstrate":[60],"different":[62],"experts":[63],"naturally":[64],"specialize":[65],"distinct":[67],"behaviors,":[69],"which":[70],"can":[71],"be":[72],"leveraged":[73],"task":[75],"migration":[76],"skill":[78],"composition.":[79],"further":[81],"validate":[82],"our":[83],"approach":[84],"simulation":[87],"real-world":[89],"deployment,":[90],"showcasing":[91],"its":[92],"robustness":[93],"adaptability.":[95]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}