{"id":"https://openalex.org/W7138184702","doi":"https://doi.org/10.1609/aaai.v40i18.38539","title":"RGMP: Recurrent Geometric-prior Multimodal Policy for Generalizable Humanoid Robot Manipulation","display_name":"RGMP: Recurrent Geometric-prior Multimodal Policy for Generalizable Humanoid Robot Manipulation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138184702","doi":"https://doi.org/10.1609/aaai.v40i18.38539"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i18.38539","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i18.38539","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i18.38539","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129690230","display_name":"Xuetao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xuetao Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018298375","display_name":"Wenke Huang","orcid":"https://orcid.org/0000-0003-4819-293X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenke Huang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023646996","display_name":"Nengyuan Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nengyuan Pan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109749290","display_name":"Kaiyan Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaiyan Zhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129734273","display_name":"Songhua Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Songhua Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129737998","display_name":"Yiming Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiming Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129648771","display_name":"Mengde Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengde Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129737062","display_name":"Mang Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mang Ye","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129686205","display_name":"Jifeng Xuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jifeng Xuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129749014","display_name":"Miao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miao Li","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5129690230"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.61363636,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"18","first_page":"15153","last_page":"15161"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.5519999861717224,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.5519999861717224,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.1670999974012375,"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"}},{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.0471000000834465,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.7196999788284302},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6269999742507935},{"id":"https://openalex.org/keywords/icub","display_name":"iCub","score":0.5855000019073486},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5748000144958496},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5597000122070312},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5422999858856201},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5022000074386597},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.4471000134944916},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.43950000405311584}],"concepts":[{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.7196999788284302},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.673799991607666},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.666100025177002},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6269999742507935},{"id":"https://openalex.org/C111151474","wikidata":"https://www.wikidata.org/wiki/Q1653368","display_name":"iCub","level":4,"score":0.5855000019073486},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5748000144958496},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5597000122070312},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5422999858856201},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5022000074386597},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.45809999108314514},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.4471000134944916},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.43950000405311584},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4284000098705292},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.40540000796318054},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.39250001311302185},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.39169999957084656},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.36419999599456787},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33799999952316284},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2897000014781952},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2791999876499176},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.27549999952316284},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.2535000145435333},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i18.38539","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i18.38539","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i18.38539","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i18.38539","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6347971558570862,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Humanoid":[0],"robots":[1],"exhibit":[2],"significant":[3,61],"potential":[4],"in":[5,44,59,177],"executing":[6],"diverse":[7],"human-level":[8],"skills.":[9],"However,":[10],"current":[11],"research":[12],"predominantly":[13],"relies":[14],"on":[15,162],"data-driven":[16],"approaches":[17],"that":[18,81,146],"necessitate":[19],"extensive":[20],"training":[21,56,64],"datasets":[22],"to":[23,38],"achieve":[24,123],"robust":[25],"multimodal":[26],"decision-making":[27],"capabilities":[28],"and":[29,47,167,180,203],"generalizable":[30],"visuomotor":[31,88],"control.":[32,89],"These":[33],"methods":[34],"raise":[35],"concerns":[36],"due":[37],"the":[39,48,55,72,95,130,170,187,198],"neglect":[40],"of":[41,51,63,143],"geometric":[42,101],"reasoning":[43,85],"unseen":[45,114],"scenarios":[46],"inefficient":[49],"modeling":[50],"robot-target":[52],"relationships":[53],"within":[54],"data,":[57],"resulting":[58],"a":[60,105,140],"waste":[62],"resources.":[65],"To":[66,122],"address":[67],"these":[68],"limitations,":[69],"we":[70,93,128],"present":[71],"Recurrent":[73],"Geometric-prior":[74,96],"Multimodal":[75],"Policy":[76],"(RGMP),":[77],"an":[78],"end-to-end":[79],"framework":[80,172],"unifies":[82],"geometric-semantic":[83],"skill":[84,111],"with":[86,116],"data-efficient":[87,124,154,204],"For":[90],"perception":[91],"capabilities,":[92],"propose":[94],"Skill":[97],"Selector,":[98],"which":[99,135],"infuses":[100],"inductive":[102],"biases":[103],"into":[104],"vision":[106],"language":[107],"model,":[108],"producing":[109],"adaptive":[110],"sequences":[112],"for":[113,200],"scenes":[115],"minimal":[117],"spatial":[118,150],"common":[119],"sense":[120],"tuning.":[121],"robotic":[125,205],"motion":[126,155],"synthesis,":[127],"introduce":[129],"Adaptive":[131],"Recursive":[132],"Gaussian":[133,144],"Network,":[134],"parameterizes":[136],"robot-object":[137],"interactions":[138],"as":[139],"compact":[141],"hierarchy":[142],"processes":[145],"recursively":[147],"encode":[148],"multi-scale":[149],"relationships,":[151],"yielding":[152],"dexterous,":[153],"synthesis":[156],"even":[157],"from":[158],"sparse":[159],"demonstrations.":[160],"Evaluated":[161],"both":[163],"our":[164],"humanoid":[165],"robot":[166],"desktop":[168],"robot,":[169],"RGMP":[171],"achieves":[173],"87%":[174],"task":[175],"success":[176],"generalization":[178],"tests":[179],"exhibits":[181],"5\u00d7":[182],"greater":[183],"data":[184],"efficiency":[185],"than":[186],"state-of-the-art":[188],"model.":[189],"This":[190],"performance":[191],"underscores":[192],"its":[193],"superior":[194],"cross-domain":[195],"generalization,":[196],"paving":[197],"way":[199],"more":[201],"versatile":[202],"systems.":[206]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}