{"id":"https://openalex.org/W4415971176","doi":"https://doi.org/10.1109/tro.2025.3629819","title":"Improving Robustness to Out-of-Distribution States in Imitation Learning via Deep Koopman-Boosted Diffusion Policy","display_name":"Improving Robustness to Out-of-Distribution States in Imitation Learning via Deep Koopman-Boosted Diffusion Policy","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415971176","doi":"https://doi.org/10.1109/tro.2025.3629819"},"language":"en","primary_location":{"id":"doi:10.1109/tro.2025.3629819","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tro.2025.3629819","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1546-1904","1941-0468"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tro.2025.3629819","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102782165","display_name":"Dianye Huang","orcid":"https://orcid.org/0000-0001-7719-6505"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dianye Huang","raw_affiliation_strings":["Chair for Computer Aided Medical Procedures and Augmented Reality, Technical University of Munich, Garching bei München, Germany","Chair for Computer Aided Medical Procedures and Augmented Reality (CAMP), Technical University of Munich (TUM), Boltzmannstr. 3, Garching bei München, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7719-6505","affiliations":[{"raw_affiliation_string":"Chair for Computer Aided Medical Procedures and Augmented Reality, Technical University of Munich, Garching bei München, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Chair for Computer Aided Medical Procedures and Augmented Reality (CAMP), Technical University of Munich (TUM), Boltzmannstr. 3, Garching bei München, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046896448","display_name":"Nassir Navab","orcid":"https://orcid.org/0000-0002-6032-5611"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nassir Navab","raw_affiliation_strings":["Chair for Computer Aided Medical Procedures and Augmented Reality, Technical University of Munich, Garching bei München, Germany","Chair for Computer Aided Medical Procedures and Augmented Reality (CAMP), Technical University of Munich (TUM), Boltzmannstr. 3, Garching bei München, Germany"],"raw_orcid":"https://orcid.org/0000-0002-6032-5611","affiliations":[{"raw_affiliation_string":"Chair for Computer Aided Medical Procedures and Augmented Reality, Technical University of Munich, Garching bei München, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Chair for Computer Aided Medical Procedures and Augmented Reality (CAMP), Technical University of Munich (TUM), Boltzmannstr. 3, Garching bei München, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045257827","display_name":"Zhongliang Jiang","orcid":"https://orcid.org/0000-0001-7461-2200"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zhongliang Jiang","raw_affiliation_strings":["Chair for Computer Aided Medical Procedures and Augmented Reality, Technical University of Munich, Garching bei München, Germany","Chair for Computer Aided Medical Procedures and Augmented Reality (CAMP), Technical University of Munich (TUM), Boltzmannstr. 3, Garching bei München, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7461-2200","affiliations":[{"raw_affiliation_string":"Chair for Computer Aided Medical Procedures and Augmented Reality, Technical University of Munich, Garching bei München, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Chair for Computer Aided Medical Procedures and Augmented Reality (CAMP), Technical University of Munich (TUM), Boltzmannstr. 3, Garching bei München, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":{"value":2645,"currency":"USD","value_usd":2645},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26820047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"41","issue":null,"first_page":"6680","last_page":"6692"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.7817999720573425,"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":0.7817999720573425,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.08590000122785568,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0632999986410141,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5052000284194946},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4390000104904175},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4228000044822693},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3693999946117401},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.36419999599456787},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.36070001125335693},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3573000133037567},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3402000069618225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7692999839782715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6855999827384949},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5052000284194946},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4390000104904175},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4228000044822693},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.36070001125335693},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3573000133037567},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3248000144958496},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3018999993801117},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28859999775886536},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28200000524520874},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.26600000262260437},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.25609999895095825},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tro.2025.3629819","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tro.2025.3629819","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1546-1904","1941-0468"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"},{"id":"pmh:oai:hub.hku.hk:10722/367051","is_oa":true,"landing_page_url":"http://hdl.handle.net/10722/367051","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1109/tro.2025.3629819","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tro.2025.3629819","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1546-1904","1941-0468"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2093730316","https://openalex.org/W2777417212","https://openalex.org/W2965273749","https://openalex.org/W3007769740","https://openalex.org/W3016970897","https://openalex.org/W3128707967","https://openalex.org/W4225912419","https://openalex.org/W4312573894","https://openalex.org/W4366371396","https://openalex.org/W4385245566","https://openalex.org/W4385403811","https://openalex.org/W4385430674","https://openalex.org/W4400646793","https://openalex.org/W4401417065","https://openalex.org/W4402354007","https://openalex.org/W4402354093","https://openalex.org/W4404809951","https://openalex.org/W4413926035","https://openalex.org/W4413926164","https://openalex.org/W4414050443","https://openalex.org/W4414050712"],"related_works":[],"abstract_inverted_index":{"Integrating":[0],"generative":[1,187],"models":[2],"with":[3],"action":[4,138,202],"chunking":[5],"has":[6],"shown":[7],"significant":[8],"promise":[9],"in":[10],"imitation":[11],"learning":[12],"for":[13,111],"robotic":[14,233],"manipulation.":[15,113],"However,":[16],"the":[17,44,51,55,60,68,83,94,102,118,131,142,155,182,186,195,198,206,221],"existing":[18],"diffusion-based":[19],"paradigm":[20],"often":[21],"struggles":[22],"to":[23,40,47,81,97,121,136,147,193],"capture":[24],"strong":[25],"temporal":[26,173],"dependencies":[27],"across":[28,214],"multiple":[29],"steps,":[30],"particularly":[31],"when":[32,117],"incorporating":[33],"proprioceptive":[34,48,109],"input.":[35],"This":[36],"limitation":[37],"can":[38,133],"lead":[39],"task":[41,99],"failures,":[42],"where":[43],"policy":[45,132,209,224],"overfits":[46],"cues":[49],"at":[50],"expense":[52],"of":[53,59,85,154,185,197,208,228],"capturing":[54],"visually":[56],"derived":[57],"features":[58],"task.":[61,156],"To":[62,157],"overcome":[63],"this":[64,115],"challenge,":[65],"we":[66,163,180],"propose":[67],"Deep":[69,166],"Koopman-boosted":[70],"Dual-branch":[71],"Diffusion":[72],"Policy":[73],"(D3P)":[74],"algorithm.":[75],"D3P":[76,219],"introduces":[77],"a":[78,128,165,190,238],"dual-branch":[79],"architecture":[80],"decouple":[82],"roles":[84],"different":[86],"sensory":[87],"modality":[88],"combinations.":[89],"The":[90],"visual":[91,95,107,143,160,176],"branch":[92,104],"encodes":[93],"observations":[96],"indicate":[98],"progression,":[100],"while":[101],"fused":[103],"integrates":[105],"both":[106],"and":[108,151],"inputs":[110],"precise":[112],"Within":[114],"architecture,":[116],"robot":[119],"fails":[120],"accomplish":[122],"intermediate":[123],"goals,":[124],"such":[125],"as":[126,189],"grasping":[127],"drawer":[129],"handle,":[130],"dynamically":[134],"switch":[135],"execute":[137],"chunks":[139],"generated":[140],"by":[141,225],"branch,":[144],"allowing":[145],"recovery":[146],"previously":[148],"observed":[149],"states":[150],"facilitating":[152],"retrial":[153],"further":[158],"enhance":[159],"representation":[161],"learning,":[162],"incorporate":[164],"Koopman":[167],"Operator":[168],"module":[169],"that":[170],"captures":[171],"structured":[172],"dynamics":[174],"from":[175],"inputs.":[177],"During":[178],"inference,":[179],"use":[181],"test-time":[183],"loss":[184],"model":[188],"confidence":[191],"signal":[192],"guide":[194],"aggregation":[196],"temporally":[199],"overlapping":[200],"predicted":[201],"chunks,":[203],"thereby":[204],"enhancing":[205],"reliability":[207],"execution.":[210],"In":[211],"simulation":[212],"experiments":[213],"six":[215],"RLBench":[216],"tabletop":[217],"tasks,":[218,235],"outperforms":[220],"state-of-the-art":[222],"diffusion":[223],"an":[226],"average":[227],"14.6%.":[229],"On":[230],"three":[231],"real-world":[232],"manipulation":[234],"it":[236],"achieves":[237],"15.0%":[239],"improvement.":[240],"Code:https://github.com/dianyeHuang/D3P.":[241]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-11-06T00:00:00"}