{"id":"https://openalex.org/W7138432564","doi":"https://doi.org/10.1609/aaai.v40i11.37852","title":"SpatialActor: Exploring Disentangled Spatial Representations for Robust Robotic Manipulation","display_name":"SpatialActor: Exploring Disentangled Spatial Representations for Robust Robotic Manipulation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138432564","doi":"https://doi.org/10.1609/aaai.v40i11.37852"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i11.37852","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37852","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.v40i11.37852","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129752979","display_name":"Hao Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Shi","raw_affiliation_strings":["Department of Automation, BNRist, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Department of Automation, BNRist, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129685055","display_name":"Bin Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091740","display_name":"AbMax AntibodyChina (China)","ror":"https://ror.org/00cqckx82","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091740"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Xie","raw_affiliation_strings":["Dexmal"],"affiliations":[{"raw_affiliation_string":"Dexmal","institution_ids":["https://openalex.org/I4210091740"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102960174","display_name":"Yingfei Liu","orcid":"https://orcid.org/0000-0002-3140-0133"},"institutions":[{"id":"https://openalex.org/I4210091740","display_name":"AbMax AntibodyChina (China)","ror":"https://ror.org/00cqckx82","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091740"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingfei Liu","raw_affiliation_strings":["Dexmal"],"affiliations":[{"raw_affiliation_string":"Dexmal","institution_ids":["https://openalex.org/I4210091740"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129689305","display_name":"Yang Yue","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yue","raw_affiliation_strings":["Department of Automation, BNRist, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Department of Automation, BNRist, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129743654","display_name":"Tiancai Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091740","display_name":"AbMax AntibodyChina (China)","ror":"https://ror.org/00cqckx82","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091740"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiancai Wang","raw_affiliation_strings":["Dexmal"],"affiliations":[{"raw_affiliation_string":"Dexmal","institution_ids":["https://openalex.org/I4210091740"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129683411","display_name":"Haoqiang Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091740","display_name":"AbMax AntibodyChina (China)","ror":"https://ror.org/00cqckx82","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091740"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoqiang Fan","raw_affiliation_strings":["Dexmal"],"affiliations":[{"raw_affiliation_string":"Dexmal","institution_ids":["https://openalex.org/I4210091740"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129665355","display_name":"Xiangyu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109870","display_name":"Vi Technology (United States)","ror":"https://ror.org/016mnbp44","country_code":"US","type":"company","lineage":["https://openalex.org/I4210109870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangyu Zhang","raw_affiliation_strings":["MEGVII Technology\nStepfun"],"affiliations":[{"raw_affiliation_string":"MEGVII Technology\nStepfun","institution_ids":["https://openalex.org/I4210109870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129717357","display_name":"Gao Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao Huang","raw_affiliation_strings":["Department of Automation, BNRist, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Department of Automation, BNRist, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5129752979"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.90839695,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"11","first_page":"8969","last_page":"8977"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.35420000553131104,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.35420000553131104,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.24060000479221344,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.2037999927997589,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6888999938964844},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5716999769210815},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5612999796867371},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.5504000186920166},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.5008000135421753},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.46219998598098755},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.4431999921798706},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42640000581741333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7174000144004822},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6888999938964844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6284000277519226},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5802000164985657},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5716999769210815},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5612999796867371},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.5504000186920166},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.5008000135421753},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.46219998598098755},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42640000581741333},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.35249999165534973},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C2781179811","wikidata":"https://www.wikidata.org/wiki/Q28134081","display_name":"Spatial configuration","level":3,"score":0.2761000096797943},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i11.37852","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37852","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.v40i11.37852","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37852","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Robotic":[0],"manipulation":[1,85],"requires":[2],"precise":[3,74],"spatial":[4,70,114,124,173],"understanding":[5],"to":[6,21,50,150,165],"interact":[7],"with":[8,142],"objects":[9],"in":[10,54],"the":[11,22],"real":[12],"world.":[13],"Point-based":[14],"methods":[15,28,62],"suffer":[16],"from":[17,101],"sparse":[18],"sampling,":[19],"leading":[20],"loss":[23],"of":[24],"fine-grained":[25],"semantics.":[26],"Image-based":[27],"typically":[29],"feed":[30],"RGB":[31],"and":[32,46,90,104,120,132,146,168],"depth":[33,52,103],"into":[34],"2D":[35],"backbones":[36],"pre-trained":[37],"on":[38,64,129,144],"3D":[39],"auxiliary":[40],"tasks,":[41],"but":[42],"their":[43],"entangled":[44],"semantics":[45,89],"geometry":[47,66,100],"are":[48],"sensitive":[49],"inherent":[51],"noise":[53],"real-world":[55,133],"that":[56,86],"disrupts":[57],"semantic":[58],"understanding.":[59],"Moreover,":[60,159],"these":[61],"focus":[63],"high-level":[65],"while":[67],"overlooking":[68],"low-level":[69,113],"cues":[71,115],"essential":[72],"for":[73,82,116],"interaction.":[75],"We":[76,126],"propose":[77],"SpatialActor,":[78],"a":[79,109],"disentangled":[80],"framework":[81],"robust":[83],"robotic":[84],"explicitly":[87],"decouples":[88],"geometry.":[91],"The":[92],"Semantic-guided":[93],"Geometric":[94],"Module":[95],"adaptively":[96],"fuses":[97],"two":[98],"complementary":[99],"noisy":[102,154],"semantic-guided":[105],"expert":[106],"priors.":[107],"Also,":[108],"Spatial":[110],"Transformer":[111],"leverages":[112],"accurate":[117],"2D-3D":[118],"mapping":[119],"enables":[121],"interaction":[122],"among":[123],"features.":[125],"evaluate":[127],"SpatialActor":[128],"multiple":[130],"simulation":[131],"scenarios":[134],"across":[135],"50+":[136],"tasks.":[137],"It":[138],"achieves":[139],"state-of-the-art":[140],"performance":[141],"87.4%":[143],"RLBench":[145],"improves":[147],"by":[148],"13.9%":[149],"19.4%":[151],"under":[152,171],"varying":[153],"conditions,":[155],"showing":[156],"strong":[157],"robustness.":[158],"it":[160],"significantly":[161],"enhances":[162],"few-shot":[163],"generalization":[164],"new":[166],"tasks":[167],"maintains":[169],"robustness":[170],"various":[172],"perturbations.":[174]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}