{"id":"https://openalex.org/W7138268695","doi":"https://doi.org/10.1609/aaai.v40i22.38889","title":"Learning Diffusion Policy from Primitive Skills for Robot Manipulation","display_name":"Learning Diffusion Policy from Primitive Skills for Robot Manipulation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138268695","doi":"https://doi.org/10.1609/aaai.v40i22.38889"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i22.38889","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38889","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.v40i22.38889","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023573700","display_name":"Zhihao Gu","orcid":"https://orcid.org/0009-0002-2000-6955"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Zhihao Gu","raw_affiliation_strings":["Department of Computer Science, School of Computing and Data Science, The University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, School of Computing and Data Science, The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129721501","display_name":"Ming Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Yang","raw_affiliation_strings":["School of Software, Beihang University"],"affiliations":[{"raw_affiliation_string":"School of Software, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129692703","display_name":"Difan Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Difan Zou","raw_affiliation_strings":["Department of Computer Science, School of Computing and Data Science, The University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, School of Computing and Data Science, The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129734276","display_name":"Dong Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dong Xu","raw_affiliation_strings":["Department of Computer Science, School of Computing and Data Science, The University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, School of Computing and Data Science, The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023573700"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48179872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"22","first_page":"18262","last_page":"18270"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4731999933719635,"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":0.4731999933719635,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.34139999747276306,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.13079999387264252,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6783000230789185},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6236000061035156},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.548799991607666},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.43720000982284546},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.37540000677108765},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.374099999666214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7269999980926514},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6783000230789185},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6236000061035156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.571399986743927},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.548799991607666},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.43720000982284546},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4174000024795532},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.36489999294281006},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3646000027656555},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.34279999136924744},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.32850000262260437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28110000491142273},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.2750999927520752}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i22.38889","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38889","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.v40i22.38889","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38889","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.47802630066871643}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diffusion":[0],"policies":[1],"have":[2],"recently":[3],"shown":[4],"great":[5],"promise":[6],"for":[7,61,123,182],"generating":[8],"actions":[9],"in":[10,29,31],"robotic":[11],"manipulation.":[12],"However,":[13],"existing":[14],"approaches":[15],"often":[16],"rely":[17],"on":[18,108,162],"global":[19],"instructions":[20],"to":[21,41,97,117,132],"produce":[22],"short-term":[23],"control":[24],"signals,":[25],"which":[26,126],"can":[27],"result":[28],"misalignment":[30],"action":[32,82],"generation.":[33],"We":[34],"conjecture":[35],"that":[36,75,172],"the":[37,52,109,151],"primitive":[38,88,121,144],"skills,":[39],"referred":[40],"as":[42,47],"fine-grained,":[43],"short-horizon":[44],"manipulations,":[45],"such":[46],"\"move":[48],"up\"":[49],"and":[50,58,92,104,146,167],"\"open":[51],"gripper\",":[53],"provide":[54],"a":[55,71,94,111,119,129,141,148,179],"more":[56],"intuitive":[57],"effective":[59],"interface":[60],"robot":[62,169,184],"learning.":[63],"To":[64],"bridge":[65],"this":[66],"gap,":[67],"we":[68],"propose":[69],"SDP,":[70],"skill-conditioned":[72],"diffusion":[73,187],"policy":[74,131],"integrates":[76],"interpretable":[77],"skill":[78,122],"learning":[79,185],"with":[80,186],"conditional":[81],"planning.":[83],"SDP":[84,153,173],"abstracts":[85],"eight":[86],"reusable":[87],"skills":[89,145],"across":[90,157],"tasks":[91,139],"employs":[93],"vision-language":[95],"model":[96],"extract":[98],"discrete":[99],"representations":[100],"from":[101],"visual":[102],"observations":[103],"language":[105],"instructions.":[106],"Based":[107],"representations,":[110],"lightweight":[112],"router":[113],"network":[114],"is":[115],"designed":[116],"assign":[118],"desired":[120],"each":[124],"state,":[125],"helps":[127],"construct":[128],"single-skill":[130,149],"generate":[133],"skill-aligned":[134],"actions.":[135],"By":[136],"decomposing":[137],"complex":[138],"into":[140],"sequence":[142],"of":[143],"selecting":[147],"policy,":[150],"proposed":[152],"ensures":[154],"skill-consistent":[155],"behavior":[156],"diverse":[158],"tasks.":[159],"Extensive":[160],"experiments":[161],"two":[163],"challenging":[164],"simulation":[165],"benchmarks":[166],"real-world":[168],"deployments":[170],"demonstrate":[171],"consistently":[174],"outperforms":[175],"state-of-the-art":[176],"methods,":[177],"providing":[178],"new":[180],"paradigm":[181],"skill-based":[183],"policies.":[188]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}