{"id":"https://openalex.org/W7224869971","doi":"https://doi.org/10.48550/arxiv.2610.39451","title":"Smooth Action Chunking Via Movement-Primitive Representations for Imitation Learning","display_name":"Smooth Action Chunking Via Movement-Primitive Representations for Imitation Learning","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224869971","doi":"https://doi.org/10.48550/arxiv.2610.39451"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.39451","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39451","pdf_url":"https://arxiv.org/pdf/2610.39451","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.39451","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160220365","display_name":"Shota Nomura","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nomura, Shota","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028032706","display_name":"Takayuki Osa","orcid":"https://orcid.org/0000-0002-6895-9088","observed_orcids":["https://orcid.org/0000-0002-6895-9088"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Osa, Takayuki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160172999","display_name":"Yasuhiro Kato","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kato, Yasuhiro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125766273","display_name":"Kazuki Ota","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ota, Kazuki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114983104","display_name":"Naoki Shitanda","orcid":"https://orcid.org/0009-0005-9653-7949","observed_orcids":["https://orcid.org/0009-0005-9653-7949"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shitanda, Naoki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5042711470","display_name":"Tatsuya Harada","orcid":"https://orcid.org/0000-0002-3712-3691","observed_orcids":["https://orcid.org/0000-0002-3712-3691"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harada, Tatsuya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7782999873161316,"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":0.7782999873161316,"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":0.2142000049352646,"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/T10982","display_name":"Motor Control and Adaptation","score":0.0017000000225380063,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/action-chunking","display_name":"action chunking","score":0.9700000286102295},{"id":"https://openalex.org/keywords/movement-primitives","display_name":"motion primitives","score":0.8799999952316284},{"id":"https://openalex.org/keywords/trajectory-smoothing","display_name":"trajectory smoothing","score":0.6420000195503235},{"id":"https://openalex.org/keywords/imitation-learning","display_name":"imitation learning","score":0.8109999895095825},{"id":"https://openalex.org/keywords/vision-based-robot-control","display_name":"vision-based robot control","score":0.7599999904632568},{"id":"https://openalex.org/keywords/diffusion-policy","display_name":"diffusion policy","score":0.6159999966621399},{"id":"https://openalex.org/keywords/vision-language-action-models","display_name":"vision-language-action models","score":0.7080000042915344},{"id":"https://openalex.org/keywords/jerk-reduction","display_name":"jerk reduction","score":0.824999988079071},{"id":"https://openalex.org/keywords/bimanual-manipulation","display_name":"bimanual manipulation","score":0.7390000224113464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7179999947547913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5788000226020813},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5648999810218811},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4871000051498413},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.461899995803833},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.42320001125335693},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.38499999046325684},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3797000050544739},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3659999966621399},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34850001335144043},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29840001463890076},{"id":"https://openalex.org/C181605269","wikidata":"https://www.wikidata.org/wiki/Q497332","display_name":"Jerk","level":3,"score":0.2874999940395355},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27390000224113464},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.25589999556541443},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.39451","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39451","pdf_url":"https://arxiv.org/pdf/2610.39451","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"text"},{"id":"doi:10.48550/arxiv.2610.39451","doi":"https://doi.org/10.48550/arxiv.2610.39451","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.39451","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.39451","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39451","pdf_url":"https://arxiv.org/pdf/2610.39451","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3480867415","display_name":null,"funder_award_id":"JPMJPS2011","funder_id":"https://openalex.org/F4320338247","funder_display_name":"Moonshot Research and Development Program"},{"id":"https://openalex.org/G7360673865","display_name":null,"funder_award_id":"JPMJSP2108","funder_id":"https://openalex.org/F4320338111","funder_display_name":"Precursory Research for Embryonic Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338111","display_name":"Precursory Research for Embryonic Science and Technology","ror":null},{"id":"https://openalex.org/F4320338247","display_name":"Moonshot Research and Development Program","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224869971.pdf","grobid_xml":"https://content.openalex.org/works/W7224869971.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415845527","https://openalex.org/W7170071597","https://openalex.org/W7151957433","https://openalex.org/W7213947776","https://openalex.org/W7160204877","https://openalex.org/W7172258886","https://openalex.org/W7220720189","https://openalex.org/W7129063177","https://openalex.org/W7202139451","https://openalex.org/W7163879634"],"abstract_inverted_index":{"Imitation":[0],"learning":[1],"has":[2,33],"become":[3,34],"a":[4,81,110,118,124,152,174,204,218],"widely":[5],"adopted":[6],"approach":[7],"for":[8,156],"vision-based":[9],"robot":[10],"policies,":[11],"owing":[12],"to":[13,20,54,194],"its":[14,66],"conceptual":[15],"simplicity,":[16],"scalability,":[17],"and":[18,83,95,143,207,212,216,237],"ability":[19],"leverage":[21],"large-scale":[22],"datasets.":[23],"As":[24],"these":[25],"policies":[26,53,195],"have":[27],"grown":[28],"more":[29],"capable,":[30],"action":[31,115],"chunking":[32],"their":[35],"standard":[36],"interface.":[37],"At":[38],"each":[39],"decision":[40],"step":[41],"the":[42,64,100,138,157,164,169,177,234,242,256],"policy":[43,139],"outputs":[44],"several":[45],"future":[46],"actions":[47],"at":[48,176,259],"once.":[49],"Backbones":[50],"from":[51],"diffusion":[52],"large":[55],"vision-language-action":[56],"models":[57],"all":[58],"share":[59],"it.":[60],"Whatever":[61],"backbone":[62,211,236],"produces":[63],"chunk,":[65],"temporal":[67],"structure":[68],"is":[69,76,121],"learned":[70],"only":[71],"implicitly.":[72],"The":[73,147,223,250],"commanded":[74,181],"trajectory":[75,112,119],"therefore":[77],"jerky":[78],"both":[79],"within":[80],"chunk":[82,171],"between":[84],"successive":[85],"chunks.":[86],"On":[87],"real":[88,219],"hardware":[89],"this":[90,106],"appears":[91],"as":[92,96,123],"visible":[93],"vibration":[94],"repeated":[97],"saturation":[98],"of":[99,127,160,231,255],"follower's":[101],"velocity":[102],"limit.":[103],"We":[104,162,200],"address":[105],"issue":[107],"by":[108,134,228,238],"incorporating":[109],"movement-primitive-based":[111],"representation":[113,149,224],"into":[114],"chunking.":[116],"Specifically,":[117],"segment":[120],"represented":[122],"linear":[125],"combination":[126],"smooth":[128,132],"basis":[129],"functions,":[130],"yielding":[131],"trajectories":[133],"construction":[135],"while":[136],"leaving":[137],"architecture,":[140],"training":[141],"objective,":[142],"inference":[144],"procedure":[145],"unchanged.":[146],"same":[148],"also":[150],"yields":[151],"closed-form,":[153],"inference-time":[154],"correction":[155,184],"second":[158],"source":[159],"jerk.":[161],"condition":[163],"predicted":[165],"coefficients":[166],"so":[167],"that":[168],"new":[170],"passes":[172],"through":[173],"via-point":[175],"previous":[178],"chunk's":[179],"last":[180],"action.":[182],"This":[183],"needs":[185],"no":[186],"retraining":[187],"and,":[188],"unlike":[189],"asynchronous":[190],"Real-Time":[191],"Chunking,":[192],"applies":[193],"queried":[196],"in":[197,214],"one":[198],"shot.":[199],"instantiate":[201],"it":[202],"on":[203,217,233,241],"one-shot":[205,235],"(ACT)":[206],"an":[208,229],"iterative":[209,243],"(DiT)":[210],"evaluate":[213],"simulation":[215],"bimanual":[220],"ALOHA":[221],"platform.":[222],"lowers":[225],"within-chunk":[226],"jerk":[227],"order":[230],"magnitude":[232],"2.4":[239],"times":[240],"one,":[244],"with":[245],"task":[246],"success":[247],"statistically":[248],"non-inferior.":[249],"conditioning":[251],"then":[252],"removes":[253],"73-84%":[254],"boundary":[257],"discontinuity,":[258],"negligible":[260],"per-step":[261],"cost.":[262]},"counts_by_year":[],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2026-10-31T00:00:00"}