[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86049-en":3,"doc-seo-86049-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},86049,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","Graph Neural Networks for RFID-Based Spatial Geometry Inference in Spatial AI Systems","Indoor spatial understanding remains a key challenge for intelligent systems in physical environments. Traditional RFID localization estimates tag positions from signal strength but overlooks higher-order spatial relationships among objects and infrastructure. A graph-based learning framework is proposed using Graph Neural Networks to infer spatial geometry from RFID observations. The method models relationships between RFID readings, antennas, and indoor floorplan structures as a graph, integrating signal strength, floorplan semantics, and spatial constraints. Nodes represent RFID observations and edges encode proximity and contextual relations.","arXiv :2607 . 10822v 1 [ cs .LG] 12 Jul 2026  \nGraph Neural Networks for RFID-Based Spatial Geometry Inference in Spatial AI Systems  \nCurtis L. Shull 1*, Merrick Green2 and Roy Rucker3  \n1* College of Computer Science, Engineering, and Technology, Valdosta  \nState University, Valdosta, GA, 31698, USA.  \n2 College of Computer Science, Engineering, and Technology, Colorado Technical University, Colorado Springs, CO, 80907, USA.  \n3 College of Management and Human Potential, Walden University, Minneapolis, MN, 55401, USA.  \n*Corresponding author(s). E-mail(s): [cshull@valdosta.edu](cshull@valdosta.edu) ; Contributing [authors: merrick.green@coloradotech.edu](authors: merrick.green@coloradotech.edu);  \n[roy.rucker@example.com](roy.rucker@example.com) ;  \nAbstract  \nIndoor spatial understanding remains a fundamental challenge for intelligent systems operating in physical environments. Traditional RFID localization techniques typically estimate positions of tags using signal strength measurements but fail to capture higher-order spatial relationships between objects and infrastructure. Recent work on RFID and wireless indoor localization has increasingly emphasized robust learning under noisy propagation, while recent graph-based localization methods demonstrate the value of relational modeling over isolated samples [1–3] . This paper introduces a graph-based learning framework that leverages Graph Neural Networks (GNNs) to infer spatial geometry from RFID observations. Rather than predicting isolated coordinates, the proposed system models relationships between RFID readings, antennas, and physical structures within an indoor floorplan. This framing is aligned with recent graph-based indoor positioning and graph construction literature, where topology is a first-class source of information for downstream inference [3–5] . The approach integrates signal strength data, floorplan semantics, and spatial constraints into a graph representation where nodes correspond to RFID observations and edges encode proximity and contextual relationships. A GNN is then trained to predict geometric patterns such as linear trajectories, rectangular bounding regions, and movement paths of objects in space. Experiments on RFID data collected in a controlled laboratory environment are used to evaluate the proposed framework  \n1  \nand to examine whether graph-based learning can recover meaningful spatial geometries from noisy signal observations. The results illustrate the potential of graph-based spatial reasoning as a foundation for next-generation spatial AI systems, especially when combined with recent floorplan reconstruction and interoperable indoor modeling standards such as IndoorGML 2.0 [6–8] . Recent surveys of graph-based wireless localization further support this direction by showing that relational models are increasingly effective when indoor measurements are sparse, noisy, or infrastructure-dependent [9, 10] .  \nKeywords: RFID, graph neural networks, spatial AI, indoor localization, graph  \nlearning, smart environments, wireless sensing  \n1 Introduction  \nSpatial intelligence is essential for robotics, automation systems, and smart environments. Indoor sensing systems must interpret noisy sensor measurements to infer meaningful spatial structure. Recent reviews of RFID indoor localization note that robustness to multipath, occlusion, and environmental variability remains a central limitation of pointwise approaches [2, 11] .  \nRFID technology is widely used for tracking assets in indoor environments. Traditional RFID localization methods rely on signal strength measurements to estimate tag positions. However, these approaches treat sensor readings independently and ignore structural information about the environment [2] .  \nIndoor environments contain meaningful spatial relationships including rooms, corridors, equipment locations, and storage containers. Ignoring these relationships limits the ability of sensing systems to reason about sp","cbCaij1gzrpL13GL","https://ap.wps.com/l/cbCaij1gzrpL13GL","pdf",11667665,1,38,"English","en",105,"# Abstract\n# Keywords\n# Introduction\n# Related Work","[{\"question\":\"How does the proposed method differ from traditional RFID localization?\",\"answer\":\"Traditional RFID localization predicts independent tag positions from signal strength. The proposed framework performs relational spatial geometry inference by modeling relationships among RFID readings, antennas, and floorplan structures using a graph representation.\"},{\"question\":\"What inputs and graph structure are used in the GNN approach?\",\"answer\":\"The system integrates signal strength data, floorplan semantics, and spatial constraints into a graph. Nodes correspond to RFID observations, while edges encode proximity and contextual relationships.\"},{\"question\":\"What spatial geometry patterns are the GNN trained to predict?\",\"answer\":\"The GNN is trained to predict geometric patterns such as linear trajectories, rectangular bounding regions, and movement paths of objects in space.\"}]",1784208078,96,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"graph-neural-networks-for-rfid-based-spatial-geometry-inference-in-spatial-ai-systems","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/graph-neural-networks-for-rfid-based-spatial-geometry-inference-in-spatial-ai-systems/86049/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"How does the proposed method differ from traditional RFID localization?","Question",{"text":75,"@type":76},"Traditional RFID localization predicts independent tag positions from signal strength. The proposed framework performs relational spatial geometry inference by modeling relationships among RFID readings, antennas, and floorplan structures using a graph representation.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What inputs and graph structure are used in the GNN approach?",{"text":80,"@type":76},"The system integrates signal strength data, floorplan semantics, and spatial constraints into a graph. Nodes correspond to RFID observations, while edges encode proximity and contextual relationships.",{"name":82,"@type":73,"acceptedAnswer":83},"What spatial geometry patterns are the GNN trained to predict?",{"text":84,"@type":76},"The GNN is trained to predict geometric patterns such as linear trajectories, rectangular bounding regions, and movement paths of objects in space.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]