{"id":"https://openalex.org/W7138311089","doi":"https://doi.org/10.1609/aaai.v40i22.38936","title":"Zero-Shot Robotic Manipulation via 3D Gaussian Splatting-Enhanced Multimodal Retrieval-Augmented Generation","display_name":"Zero-Shot Robotic Manipulation via 3D Gaussian Splatting-Enhanced Multimodal Retrieval-Augmented Generation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138311089","doi":"https://doi.org/10.1609/aaai.v40i22.38936"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i22.38936","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38936","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i22.38936","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084354953","display_name":"Zilong Xie","orcid":"https://orcid.org/0000-0002-6851-7554"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zilong Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074868631","display_name":"Jingyu Gong","orcid":"https://orcid.org/0000-0002-4536-0953"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingyu Gong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129642499","display_name":"Xin Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Tan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129751768","display_name":"Zhizhong Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhizhong Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129643538","display_name":"Yuan Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan Xie","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2195962,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"22","first_page":"18683","last_page":"18691"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.453000009059906,"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":0.453000009059906,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.45260000228881836,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.01810000091791153,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6039999723434448},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.54830002784729},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5192000269889832},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.5170000195503235},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4851999878883362},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46239998936653137},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4577000141143799},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.41909998655319214},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.40450000762939453},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.39480000734329224}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7656000256538391},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.727400004863739},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6327999830245972},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6039999723434448},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.54830002784729},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5192000269889832},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.5170000195503235},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4851999878883362},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46239998936653137},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4577000141143799},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.41909998655319214},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.40450000762939453},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.39480000734329224},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.32339999079704285},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.32089999318122864},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.29899999499320984},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C120515352","wikidata":"https://www.wikidata.org/wiki/Q2564580","display_name":"Image plane","level":3,"score":0.2574999928474426}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i22.38936","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38936","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"},{"id":"pmh:oai:ojs.aaai.org:article/38936","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/38936","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i22.38936","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38936","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":[{"id":"https://metadata.un.org/sdg/1","score":0.4465600848197937,"display_name":"No poverty"}],"awards":[{"id":"https://openalex.org/G2297482413","display_name":null,"funder_award_id":"CSTB2023NSCQ-JQX0007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2713008596","display_name":null,"funder_award_id":"CSTB2023NSCQ-JQX0007","funder_id":"https://openalex.org/F4320323172","funder_display_name":"Natural Science Foundation of Chongqing"},{"id":"https://openalex.org/G3075434960","display_name":null,"funder_award_id":"CSTB2023NSCQ-MSX0137","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G332543946","display_name":null,"funder_award_id":"CSTB2023NSCQ-MSX0137","funder_id":"https://openalex.org/F4320323172","funder_display_name":"Natural Science Foundation of Chongqing"},{"id":"https://openalex.org/G3985214407","display_name":null,"funder_award_id":"62176092","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4427435602","display_name":null,"funder_award_id":"CSTB2023NSCQ","funder_id":"https://openalex.org/F4320323172","funder_display_name":"Natural Science Foundation of Chongqing"},{"id":"https://openalex.org/G5622463821","display_name":null,"funder_award_id":"25ZR1402135","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"},{"id":"https://openalex.org/G5691570638","display_name":null,"funder_award_id":"U23A20343","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6256348062","display_name":null,"funder_award_id":"62502159","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6527433971","display_name":null,"funder_award_id":"23CGA34","funder_id":"https://openalex.org/F4320321881","funder_display_name":"Shanghai Municipal Education Commission"},{"id":"https://openalex.org/G6892761941","display_name":null,"funder_award_id":"CSTB2025NSCQ","funder_id":"https://openalex.org/F4320323172","funder_display_name":"Natural Science Foundation of Chongqing"},{"id":"https://openalex.org/G8017681359","display_name":null,"funder_award_id":"CSTB2025NSCQ-GPX0445","funder_id":"https://openalex.org/F4320323172","funder_display_name":"Natural Science Foundation of Chongqing"},{"id":"https://openalex.org/G8137067846","display_name":null,"funder_award_id":"62302167","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8911208208","display_name":null,"funder_award_id":"62476090","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G91187700","display_name":null,"funder_award_id":"62222602","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321659","display_name":"Shanghai Education Development Foundation","ror":"https://ror.org/02kq92y46"},{"id":"https://openalex.org/F4320321881","display_name":"Shanghai Municipal Education Commission","ror":"https://ror.org/05tewj457"},{"id":"https://openalex.org/F4320322370","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"},{"id":"https://openalex.org/F4320322927","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884"},{"id":"https://openalex.org/F4320323172","display_name":"Natural Science Foundation of Chongqing","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"end-to-end":[1],"approaches":[2],"of":[3,134,165,181],"robotic":[4,60,229],"manipulation":[5,67],"often":[6],"lack":[7],"generalization":[8],"to":[9,15,92,138,158,161,193,206,233],"unseen":[10,234],"objects":[11,235],"or":[12],"tasks":[13],"due":[14],"limited":[16],"data":[17],"and":[18,36,77,108,154,202,224],"poor":[19],"interpretability.":[20],"While":[21],"recent":[22],"Multimodal":[23,53,84],"Large":[24],"Language":[25],"Models":[26],"(MLLMs)":[27],"demonstrate":[28],"strong":[29],"commonsense":[30],"reasoning,":[31],"they":[32],"struggle":[33],"with":[34],"geometric":[35,226],"spatial":[37],"understanding":[38],"required":[39],"for":[40,58],"pose":[41,78,133,168],"prediction.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46],"propose":[47],"RobMRAG,":[48],"a":[49,65,82,116,175],"3D":[50,123,143],"Gaussian":[51,124],"Splatting-Enhanced":[52],"Retrieval-Augmented":[54],"Generation":[55],"(MRAG)":[56],"framework":[57],"zero-shot":[59,196],"manipulation.":[61],"Specifically,":[62],"We":[63,113],"construct":[64],"multi-source":[66],"knowledge":[68],"base":[69],"containing":[70,178],"object":[71,95,137,141],"contact":[72],"frames,":[73,76],"task":[74],"completion":[75],"parameters.":[79,169],"During":[80],"inference,":[81],"Hierarchical":[83],"Retrieval":[85],"module":[86,120],"first":[87],"employs":[88],"hybrid":[89],"semantic":[90,222],"search":[91],"find":[93],"task-relevant":[94],"prototypes,":[96],"then":[97],"selects":[98],"the":[99,127,132,135,139,151,159,163,166,187,194,199,207,218],"geometrically":[100],"closest":[101],"reference":[102,136],"example":[103],"based":[104,121],"on":[105,122,174],"pixel-level":[106],"similarity":[107],"Instance":[109],"Matching":[110],"Distance":[111],"(IMD).":[112],"further":[114],"introduce":[115],"3D-Aware":[117],"Pose":[118],"Refinement":[119],"Splatting":[125],"into":[126],"MRAG":[128],"framework,":[129],"which":[130],"aligns":[131],"target":[140],"in":[142],"space.":[144],"The":[145],"aligned":[146],"results":[147,212],"are":[148],"reprojected":[149],"onto":[150],"image":[152],"plane":[153],"used":[155],"as":[156],"input":[157],"MLLM":[160],"enhance":[162],"generation":[164],"final":[167],"Extensive":[170],"experiments":[171],"show":[172],"that":[173,214,231],"test":[176],"set":[177],"30":[179],"categories":[180],"household":[182],"objects,":[183],"our":[184],"method":[185],"improves":[186],"success":[188],"rate":[189],"by":[190,203],"7.76%":[191],"compared":[192,205],"best-performing":[195],"baseline":[197],"under":[198],"same":[200],"setting,":[201],"6.54%":[204],"state-of-the-art":[208],"supervised":[209],"baseline.":[210],"Our":[211],"validate":[213],"RobMRAG":[215],"effectively":[216],"bridges":[217],"gap":[219],"between":[220],"high-level":[221],"reasoning":[223],"low-level":[225],"execution,":[227],"enabling":[228],"systems":[230],"generalize":[232],"while":[236],"remaining":[237],"inherently":[238],"interpretable.":[239]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-18T00:00:00"}