{"id":"https://openalex.org/W4401416961","doi":"https://doi.org/10.1109/icra57147.2024.10611491","title":"EquivAct: SIM(3)-Equivariant Visuomotor Policies beyond Rigid Object Manipulation","display_name":"EquivAct: SIM(3)-Equivariant Visuomotor Policies beyond Rigid Object Manipulation","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401416961","doi":"https://doi.org/10.1109/icra57147.2024.10611491"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611491","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101861092","display_name":"Jingyun Yang","orcid":"https://orcid.org/0000-0001-7506-9895"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jingyun Yang","raw_affiliation_strings":["Stanford University,Department of Computer Science"],"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Computer Science","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050560702","display_name":"Congyue Deng","orcid":"https://orcid.org/0000-0002-0177-218X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Congyue Deng","raw_affiliation_strings":["Stanford University,Department of Computer Science"],"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Computer Science","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056420488","display_name":"Jimmy Wu","orcid":"https://orcid.org/0000-0001-6388-9116"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jimmy Wu","raw_affiliation_strings":["Princeton University,Department of Computer Science"],"affiliations":[{"raw_affiliation_string":"Princeton University,Department of Computer Science","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009099496","display_name":"Rika Antonova","orcid":"https://orcid.org/0000-0002-3018-2445"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rika Antonova","raw_affiliation_strings":["Stanford University,Department of Computer Science"],"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Computer Science","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112461556","display_name":"Leonidas Guibas","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leonidas Guibas","raw_affiliation_strings":["Stanford University,Department of Computer Science"],"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Computer Science","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021676288","display_name":"Jeannette Bohg","orcid":"https://orcid.org/0000-0002-4921-7193"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeannette Bohg","raw_affiliation_strings":["Stanford University,Department of Computer Science"],"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Computer Science","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101861092"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":6.2418,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.97109011,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9249","last_page":"9255"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9954000115394592,"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":0.9954000115394592,"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.9807000160217285,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10427","display_name":"Visual perception and processing mechanisms","score":0.9779999852180481,"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/equivariant-map","display_name":"Equivariant map","score":0.8077464699745178},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6021813154220581},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.584896445274353},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4239104986190796},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4216776490211487},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36291253566741943},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2021065056324005},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.13452720642089844}],"concepts":[{"id":"https://openalex.org/C171036898","wikidata":"https://www.wikidata.org/wiki/Q256355","display_name":"Equivariant map","level":2,"score":0.8077464699745178},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6021813154220581},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.584896445274353},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4239104986190796},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4216776490211487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36291253566741943},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2021065056324005},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.13452720642089844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10611491","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4000000059604645}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W2073924944","https://openalex.org/W2788775653","https://openalex.org/W2963390419","https://openalex.org/W3021708257","https://openalex.org/W3036737467","https://openalex.org/W3116959466","https://openalex.org/W3158545781","https://openalex.org/W3163187545","https://openalex.org/W3176751833","https://openalex.org/W3177826989","https://openalex.org/W3205321526","https://openalex.org/W3212066820","https://openalex.org/W4229002925","https://openalex.org/W4229927528","https://openalex.org/W4236965008","https://openalex.org/W4281877847","https://openalex.org/W4283067636","https://openalex.org/W4285102336","https://openalex.org/W4287121275","https://openalex.org/W4297805934","https://openalex.org/W4312799694","https://openalex.org/W4313172691","https://openalex.org/W4322759826","https://openalex.org/W4378505295","https://openalex.org/W4383108224","https://openalex.org/W4383108463","https://openalex.org/W4383108699","https://openalex.org/W4385430538","https://openalex.org/W4386076348","https://openalex.org/W4390874575","https://openalex.org/W6748579715","https://openalex.org/W6749031613","https://openalex.org/W6755816839","https://openalex.org/W6761443123","https://openalex.org/W6763422710","https://openalex.org/W6774314701","https://openalex.org/W6776867236","https://openalex.org/W6779789776","https://openalex.org/W6795508825","https://openalex.org/W6797371470","https://openalex.org/W6803239650","https://openalex.org/W6803569764","https://openalex.org/W6839117414","https://openalex.org/W6839214563","https://openalex.org/W6839443173","https://openalex.org/W6846496272","https://openalex.org/W6850081569","https://openalex.org/W6852754536"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"If":[0],"a":[1,5,15,80,92,97,168,175,180],"robot":[2,159],"masters":[3],"folding":[4,14],"kitchen":[6],"towel,":[7],"we":[8,90],"would":[9],"expect":[10],"it":[11],"to":[12,37,40,112,174],"master":[13],"large":[16],"beach":[17],"towel.":[18],"However,":[19],"existing":[20],"policy":[21,47,95,109],"learning":[22],"methods":[23],"that":[24,57,106,114,186],"rely":[25],"on":[26,84],"data":[27],"augmentation":[28],"still":[29],"don\u2019t":[30],"guarantee":[31,58],"such":[32],"generalization.":[33],"Our":[34],"insight":[35],"is":[36,72],"add":[38],"equivariance":[39],"both":[41,151],"the":[42,107],"visual":[43,82],"object":[44,63,141],"representation":[45,83],"and":[46,67,122,134,154,171,191],"architecture.":[48],"We":[49,77,104,124,148],"propose":[50],"EquivAct":[51,71],"which":[52],"utilizes":[53],"SIM(3)-equivariant":[54,81,93],"network":[55],"structures":[56],"generalization":[59],"across":[60],"all":[61],"possible":[62],"translations,":[64],"3D":[65],"rotations,":[66],"scales":[68],"by":[69],"construction.":[70],"trained":[73],"in":[74,119,128,145,152,155,179],"two":[75],"phases.":[76],"first":[78],"pre-train":[79],"simulated":[85],"scene":[86],"point":[87],"clouds.":[88],"Then,":[89],"learn":[91],"visuomotor":[94],"using":[96],"small":[98],"amount":[99],"of":[100,167],"source":[101],"task":[102,170,178],"demonstrations.":[103],"show":[105],"learned":[108],"directly":[110],"transfers":[111,172],"objects":[113],"substantially":[115],"differ":[116],"from":[117],"demonstrations":[118,166],"scale,":[120],"position,":[121],"orientation.":[123],"evaluate":[125],"our":[126,161,187],"method":[127,162],"three":[129],"manipulation":[130,142,177],"tasks":[131,143],"involving":[132],"deformable":[133],"articulated":[135],"objects,":[136],"going":[137],"beyond":[138],"typical":[139],"rigid":[140],"considered":[144],"prior":[146,198],"work.":[147,199],"conduct":[149],"experiments":[150],"simulation":[153],"reality.":[156],"For":[157],"real":[158],"experiments,":[160],"uses":[163],"20":[164],"human":[165],"tabletop":[169],"zero-shot":[173],"mobile":[176],"much":[181],"larger":[182],"setup.":[183],"Experiments":[184],"confirm":[185],"contrastive":[188],"pre-training":[189],"procedure":[190],"equivariant":[192],"architecture":[193],"offer":[194],"significant":[195],"improvements":[196],"over":[197],"Project":[200],"website:":[201],"equivact.github.io":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":5}],"updated_date":"2026-03-01T08:55:55.761014","created_date":"2025-10-10T00:00:00"}