{"id":"https://openalex.org/W7128808322","doi":"https://doi.org/10.1109/lra.2026.3664620","title":"PALM: Enhanced Generalizability for Local Visuomotor Policies via Perception Alignment","display_name":"PALM: Enhanced Generalizability for Local Visuomotor Policies via Perception Alignment","publication_year":2026,"publication_date":"2026-02-13","ids":{"openalex":"https://openalex.org/W7128808322","doi":"https://doi.org/10.1109/lra.2026.3664620"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3664620","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2026.3664620","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/lra.2026.3664620","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126015727","display_name":"Ruiyu Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Ruiyu Wang","raw_affiliation_strings":["Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":"https://orcid.org/0009-0008-7672-970X","affiliations":[{"raw_affiliation_string":"Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102427121","display_name":"Zheyu Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Zheyu Zhuang","raw_affiliation_strings":["Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":"https://orcid.org/0000-0002-6632-3342","affiliations":[{"raw_affiliation_string":"Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023792180","display_name":"Danica Kragi\u0107","orcid":"https://orcid.org/0000-0003-2965-2953"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Danica Kragic","raw_affiliation_strings":["Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-2965-2953","affiliations":[{"raw_affiliation_string":"Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018027629","display_name":"Florian T. Pokorny","orcid":"https://orcid.org/0000-0003-1114-6040"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Florian T. Pokorny","raw_affiliation_strings":["Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-1114-6040","affiliations":[{"raw_affiliation_string":"Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5126015727"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30178746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"4","first_page":"4865","last_page":"4872"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11685","display_name":"Zebrafish Biomedical Research Applications","score":0.2741999924182892,"subfield":{"id":"https://openalex.org/subfields/1307","display_name":"Cell Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11685","display_name":"Zebrafish Biomedical Research Applications","score":0.2741999924182892,"subfield":{"id":"https://openalex.org/subfields/1307","display_name":"Cell Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.16539999842643738,"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":0.1137000024318695,"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/generalizability-theory","display_name":"Generalizability theory","score":0.6072999835014343},{"id":"https://openalex.org/keywords/workspace","display_name":"Workspace","score":0.5670999884605408},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5440999865531921},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.524399995803833},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.45339998602867126},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4260999858379364}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.6072999835014343},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5824000239372253},{"id":"https://openalex.org/C58581272","wikidata":"https://www.wikidata.org/wiki/Q12741163","display_name":"Workspace","level":3,"score":0.5670999884605408},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5440999865531921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5246999859809875},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.524399995803833},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.45339998602867126},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4260999858379364},{"id":"https://openalex.org/C87335442","wikidata":"https://www.wikidata.org/wiki/Q2494345","display_name":"Local binary patterns","level":4,"score":0.39660000801086426},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.39480000734329224},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34150001406669617},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.32760000228881836},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32010000944137573},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.29660001397132874},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2671000063419342},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2628999948501587},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.26109999418258667}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2026.3664620","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2026.3664620","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/lra.2026.3664620","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2026.3664620","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5415501594543457,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2417041764","https://openalex.org/W3007769740","https://openalex.org/W3192335307","https://openalex.org/W3207359859","https://openalex.org/W4308233968","https://openalex.org/W4312297897","https://openalex.org/W4385430538","https://openalex.org/W4386076088","https://openalex.org/W4390578009","https://openalex.org/W4401417065","https://openalex.org/W4402354041","https://openalex.org/W4402354047","https://openalex.org/W4402354111","https://openalex.org/W4402354121","https://openalex.org/W4402354166","https://openalex.org/W4403982072","https://openalex.org/W4414079207","https://openalex.org/W7129096717"],"related_works":[],"abstract_inverted_index":{"Generalizing":[0],"beyond":[1],"the":[2,48,77,93,101,115,140],"training":[3],"domain":[4],"in":[5,30,135,139],"image-based":[6],"behavior":[7],"cloning":[8],"remains":[9],"challenging.":[10],"Existing":[11],"methods":[12],"address":[13,61],"individual":[14],"axes":[15],"of":[16,50],"generalization,":[17],"workspace":[18],"shifts,":[19],"viewpoint":[20],"changes,":[21,71],"and":[22,32,57,84,97,110,137,146],"cross-embodiment":[23],"transfer,":[24],"yet":[25],"they":[26],"are":[27],"typically":[28],"developed":[29],"isolation":[31],"often":[33],"rely":[34],"on":[35],"complex":[36],"pipelines.":[37],"We":[38,91],"introduce":[39],"PALM":[40,75,128],"(Perception":[41],"Alignment":[42],"for":[43,88,148],"Local":[44],"Manipulation),":[45],"which":[46],"leverages":[47],"invariance":[49],"local":[51,86,102,107,120],"action":[52],"distributions":[53],"between":[54,95],"out-of-distribution":[55],"(OOD)":[56],"demonstrated":[58],"domains":[59],"to":[60,117,133,144],"these":[62],"OOD":[63,98,123,130],"shifts":[64],"concurrently,":[65],"without":[66],"additional":[67],"input":[68],"modalities,":[69],"model":[70],"or":[72],"data":[73],"collection.":[74],"modularizes":[76],"manipulation":[78],"policy":[79,87,103,116],"into":[80],"coarse":[81],"global":[82],"components":[83],"a":[85],"fine-grained":[89],"actions.":[90],"reduce":[92],"discrepancy":[94],"in-domain":[96],"inputs":[99],"at":[100],"level":[104],"by":[105],"enforcing":[106],"visual":[108],"focus":[109],"consistent":[111],"proprioceptive":[112],"representation,":[113],"allowing":[114],"retrieve":[118],"invariant":[119],"actions":[121],"under":[122],"conditions.":[124],"Experiments":[125],"show":[126],"that":[127],"limits":[129],"performance":[131],"drops":[132],"8%":[134],"simulation":[136],"24%":[138],"real":[141],"world,":[142],"compared":[143],"45%":[145],"77%":[147],"baselines.":[149]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-02-02T00:00:00"}