{"id":"https://openalex.org/W7158535873","doi":"https://doi.org/10.1126/scirobotics.aea2092","title":"A retrieval-augmented framework enabling VLM spatial awareness for object-centric robot manipulation","display_name":"A retrieval-augmented framework enabling VLM spatial awareness for object-centric robot manipulation","publication_year":2026,"publication_date":"2026-04-29","ids":{"openalex":"https://openalex.org/W7158535873","doi":"https://doi.org/10.1126/scirobotics.aea2092","pmid":"https://pubmed.ncbi.nlm.nih.gov/42054478"},"language":"en","primary_location":{"id":"doi:10.1126/scirobotics.aea2092","is_oa":false,"landing_page_url":"https://doi.org/10.1126/scirobotics.aea2092","pdf_url":null,"source":{"id":"https://openalex.org/S4210213233","display_name":"Science Robotics","issn_l":"2470-9476","issn":["2470-9476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315823","host_organization_name":"American Association for the Advancement of Science","host_organization_lineage":["https://openalex.org/P4310315823"],"host_organization_lineage_names":["American Association for the Advancement of Science"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Science Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5134927454","display_name":"Kai Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["Department of Computer Science and Engineering, Chinese University of Hong Kong, HKSAR, China"],"raw_orcid":"https://orcid.org/0009-0005-1044-2456","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Chinese University of Hong Kong, HKSAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134890439","display_name":"Chengkun Li","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chengkun Li","raw_affiliation_strings":["Department of Computer Science and Engineering, Chinese University of Hong Kong, HKSAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Chinese University of Hong Kong, HKSAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134926336","display_name":"Chang Tu","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chang Tu","raw_affiliation_strings":["Department of Computer Science and Engineering, Chinese University of Hong Kong, HKSAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Chinese University of Hong Kong, HKSAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023225646","display_name":"Jiahui Pan","orcid":"https://orcid.org/0000-0002-7576-6743"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiahui Pan","raw_affiliation_strings":["Department of Computer Science and Engineering, Chinese University of Hong Kong, HKSAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Chinese University of Hong Kong, HKSAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085438856","display_name":"Yiyao Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yiyao Ma","raw_affiliation_strings":["Department of Computer Science and Engineering, Chinese University of Hong Kong, HKSAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Chinese University of Hong Kong, HKSAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134920588","display_name":"Wei Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wei Chen","raw_affiliation_strings":["Department of Mechanical and Automation Engineering, Chinese University of Hong Kong, HKSAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Automation Engineering, Chinese University of Hong Kong, HKSAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010285977","display_name":"Zhongxiang Zhou","orcid":"https://orcid.org/0000-0003-1952-7147"},"institutions":[{"id":"https://openalex.org/I4210163926","display_name":"Zhejiang Medicine (China)","ror":"https://ror.org/05h86nk22","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210163926"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongxiang Zhou","raw_affiliation_strings":["Zhejiang Humanoid Robot Innovation Center Co. Ltd., Ningbo, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-5430-4419","affiliations":[{"raw_affiliation_string":"Zhejiang Humanoid Robot Innovation Center Co. Ltd., Ningbo, Zhejiang, China","institution_ids":["https://openalex.org/I4210163926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080268597","display_name":"Xuecheng Xu","orcid":"https://orcid.org/0000-0002-0762-6714"},"institutions":[{"id":"https://openalex.org/I4210163926","display_name":"Zhejiang Medicine (China)","ror":"https://ror.org/05h86nk22","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210163926"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuecheng Xu","raw_affiliation_strings":["Zhejiang Humanoid Robot Innovation Center Co. Ltd., Ningbo, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-0762-6714","affiliations":[{"raw_affiliation_string":"Zhejiang Humanoid Robot Innovation Center Co. Ltd., Ningbo, Zhejiang, China","institution_ids":["https://openalex.org/I4210163926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134923034","display_name":"Stephen James","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stephen James","raw_affiliation_strings":["Imperial College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134888019","display_name":"Chi-Wing Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chi-Wing Fu","raw_affiliation_strings":["Department of Computer Science and Engineering, Chinese University of Hong Kong, HKSAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Chinese University of Hong Kong, HKSAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134876401","display_name":"Rong Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210163926","display_name":"Zhejiang Medicine (China)","ror":"https://ror.org/05h86nk22","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210163926"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Xiong","raw_affiliation_strings":["College of Control Science and Engineering, Zhejiang University, Hangzhou, Zhejiang, China","Zhejiang Humanoid Robot Innovation Center Co. Ltd., Ningbo, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0001-9318-9014","affiliations":[{"raw_affiliation_string":"College of Control Science and Engineering, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang Humanoid Robot Innovation Center Co. Ltd., Ningbo, Zhejiang, China","institution_ids":["https://openalex.org/I4210163926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129698605","display_name":"Pieter Abbeel","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pieter Abbeel","raw_affiliation_strings":["University of California, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0009-0007-0628-9932","affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134918629","display_name":"Yun-Hui Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yun-Hui Liu","raw_affiliation_strings":["Department of Mechanical and Automation Engineering, Chinese University of Hong Kong, HKSAR, China"],"raw_orcid":"https://orcid.org/0000-0002-3625-6679","affiliations":[{"raw_affiliation_string":"Department of Mechanical and Automation Engineering, Chinese University of Hong Kong, HKSAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134883740","display_name":"Qi Dou","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qi Dou","raw_affiliation_strings":["Department of Computer Science and Engineering, Chinese University of Hong Kong, HKSAR, China"],"raw_orcid":"https://orcid.org/0000-0002-3416-9950","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Chinese University of Hong Kong, HKSAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":14,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.56965395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"113","first_page":"eaea2092","last_page":"eaea2092"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.48100000619888306,"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":0.48100000619888306,"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":0.2766999900341034,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.059300001710653305,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.656499981880188},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.5777999758720398},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5773000121116638},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5564000010490417},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.5360999703407288},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.5303000211715698},{"id":"https://openalex.org/keywords/semantic-mapping","display_name":"Semantic mapping","score":0.4489000141620636},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4480000138282776},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4043999910354614}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6777999997138977},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.656499981880188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6340000033378601},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5777999758720398},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5773000121116638},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5564000010490417},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.5360999703407288},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.5303000211715698},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4814000129699707},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.4489000141620636},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4480000138282776},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4043999910354614},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.36629998683929443},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3578000068664551},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C2775960376","wikidata":"https://www.wikidata.org/wiki/Q1435859","display_name":"Grippers","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C17511633","wikidata":"https://www.wikidata.org/wiki/Q830694","display_name":"SMT placement equipment","level":3,"score":0.3192000091075897},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.27140000462532043},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1126/scirobotics.aea2092","is_oa":false,"landing_page_url":"https://doi.org/10.1126/scirobotics.aea2092","pdf_url":null,"source":{"id":"https://openalex.org/S4210213233","display_name":"Science Robotics","issn_l":"2470-9476","issn":["2470-9476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315823","host_organization_name":"American Association for the Advancement of Science","host_organization_lineage":["https://openalex.org/P4310315823"],"host_organization_lineage_names":["American Association for the Advancement of Science"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Science Robotics","raw_type":"journal-article"},{"id":"pmid:42054478","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42054478","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Science robotics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2103542852","display_name":null,"funder_award_id":"U24A20128","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5576955673","display_name":"Advancing Autonomous Soft Tissue Manipulation via Perception, Modelling, and Control Policy Learning from Human Demonstration Data for Surgical Robotics","funder_award_id":"14208424","funder_id":"https://openalex.org/F4320321592","funder_display_name":"Research Grants Council, University Grants Committee"},{"id":"https://openalex.org/G7517584449","display_name":null,"funder_award_id":"U25A6013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G818396220","display_name":null,"funder_award_id":"62322318","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321592","display_name":"Research Grants Council, University Grants Committee","ror":"https://ror.org/00djwmt25"},{"id":"https://openalex.org/F6246297422","display_name":"Hong Kong Centre for Logistics Robotics","ror":"https://ror.org/04xzpxc31"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2016959837","https://openalex.org/W2085261163","https://openalex.org/W2108182844","https://openalex.org/W2970710335","https://openalex.org/W2982445554","https://openalex.org/W3164862896","https://openalex.org/W3196466825","https://openalex.org/W3202717607","https://openalex.org/W3207832698","https://openalex.org/W4226280394","https://openalex.org/W4312445439","https://openalex.org/W4389519118","https://openalex.org/W4393147129","https://openalex.org/W4401246959","https://openalex.org/W4401415428","https://openalex.org/W4401417048","https://openalex.org/W4401857375","https://openalex.org/W4402354047","https://openalex.org/W4402716288","https://openalex.org/W4402727730","https://openalex.org/W4402774238","https://openalex.org/W4403277629","https://openalex.org/W4403842181","https://openalex.org/W4404307277","https://openalex.org/W4404612908","https://openalex.org/W4405786114","https://openalex.org/W4405786470","https://openalex.org/W4405786528","https://openalex.org/W4407637743","https://openalex.org/W4408555470","https://openalex.org/W4410152941","https://openalex.org/W4413144643","https://openalex.org/W4413145626","https://openalex.org/W4413146238","https://openalex.org/W4413146350","https://openalex.org/W4413147462","https://openalex.org/W4413926275","https://openalex.org/W4415796190","https://openalex.org/W4415798560","https://openalex.org/W4415800665","https://openalex.org/W7133213795"],"related_works":[],"abstract_inverted_index":{"Connecting":[0],"the":[1,9,28,59,68,92,137,161],"semantic":[2,196],"reasoning":[3,61,149],"of":[4,13,103,139],"vision-language":[5],"models":[6,57],"(VLMs)":[7],"to":[8,91,96,126,176,184],"precise":[10,36,105],"geometric":[11,199],"demands":[12],"robotic":[14,213],"manipulation":[15,135],"remains":[16],"a":[17,101,115,119,140,192,203],"fundamental":[18],"challenge.":[19],"Although":[20],"VLMs":[21],"can":[22,122],"interpret":[23],"high-level":[24],"commands,":[25],"they":[26],"lack":[27],"intrinsic":[29],"spatial":[30,60,129],"intelligence":[31],"required":[32],"for":[33,63],"tasks":[34,147],"demanding":[35],"object":[37,154,179],"placement,":[38],"orientation,":[39],"and":[40,106,144,156,181,188,198,211],"physical":[41,151],"reasoning.":[42],"Here,":[43],"we":[44],"introduce":[45],"Retrieval-Augmented":[46],"Manipulation":[47],"(RAM),":[48],"an":[49,76],"object-centric":[50,78],"framework":[51],"that":[52,112,170],"endows":[53],"general-purpose":[54,212],"vision":[55,173],"foundation":[56],"with":[58],"necessary":[62],"robust":[64,183],"manipulation.":[65],"RAM":[66,201],"bridges":[67],"semantic-to-geometric":[69],"gap":[70],"by":[71,148],"grounding":[72],"abstract":[73],"concepts":[74],"into":[75,100],"explicit,":[77],"three-dimensional":[79],"(3D)":[80],"representation.":[81],"This":[82],"grounded":[83],"information":[84],"is":[85,182],"then":[86],"provided":[87],"as":[88],"augmented":[89],"context":[90],"VLM,":[93],"empowering":[94],"it":[95],"decompose":[97],"complex":[98,128],"instructions":[99],"sequence":[102],"spatially":[104,133],"physically":[107,209],"plausible":[108],"subgoals.":[109],"We":[110],"demonstrate":[111],"RAM,":[113],"in":[114,164,186],"zero-shot":[116],"setting":[117],"on":[118,160],"real-world":[120],"robot,":[121],"execute":[123],"these":[124],"subgoals":[125],"fulfill":[127],"language":[130],"instructions,":[131],"complete":[132],"aware":[134],"under":[136],"guidance":[138],"single":[141],"2D":[142],"image,":[143],"adaptively":[145],"replan":[146],"about":[150],"constraints":[152],"like":[153],"size":[155],"collisions.":[157],"Quantitative":[158],"evaluations":[159],"Common":[162],"Object":[163],"3D":[165],"(CO3D)":[166],"dataset":[167],"also":[168],"validated":[169],"RAM's":[171],"core":[172],"module":[174],"generalizes":[175],"previously":[177],"unseen":[178],"categories":[180],"variations":[185],"shape":[187],"occlusions.":[189],"By":[190],"providing":[191],"structured":[193],"bridge":[194],"between":[195],"intent":[197],"execution,":[200],"represents":[202],"critical":[204],"step":[205],"toward":[206],"developing":[207],"more":[208],"intelligent":[210],"systems.":[214]},"counts_by_year":[],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2026-05-01T00:00:00"}