[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-128810-105":59,"doc-detail-128810-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","real-time-athlete-localization-with-uwb-and-machine-learning-masters-thesis","Real-Time Athlete Localization with UWB and Machine Learning - Master’s Thesis","","Accurate real-time athlete localization is critical for performance analysis, tactical assessment, and injury prevention, yet GNSS and optical tracking often fail due to limited indoor applicability, high infrastructure cost, and insufficient precision. This thesis develops a real-time localization system using Ultra-Wideband (UWB) combined with Machine Learning (ML), targeting dynamic sports scenarios. The Time Difference of Arrival (TDoA) method localizes wearable tags with low device computation. Contributions include a complete data acquisition system for real-time visualization, improved TDoA algorithm design and mathematics, and ML-based position estimation models. Additional hardware and communication enhancements improve scalability, reduce packet loss, and support indoor and outdoor deployments. Experimental results confirm reliable real-time performance and accurate localization in complex settings.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/real-time-athlete-localization-with-uwb-and-machine-learning-masters-thesis/128810/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/real-time-athlete-localization-with-uwb-and-machine-learning-masters-thesis/128810.png","ImageObject",300,407,{"name":92,"@type":93},"Violet","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-09-19","2026-08-06",true,{"@type":102,"interactionType":103,"userInteractionCount":52},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why are GNSS solutions insufficient for real-time athlete tracking in sports?","Question",{"text":112,"@type":113},"GNSS positional accuracy is typically only meters-level and update rates cannot capture rapid, high-intensity movement and directional changes. In addition, GNSS signals often cannot penetrate building structures, limiting indoor or covered-stadium use.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does UWB support accurate indoor localization for RTLS?",{"text":117,"@type":113},"UWB uses very large signal bandwidths to create nanosecond-scale pulses, enabling fine time-of-flight distance measurements with centimeter-level resolution. Its broad spectrum and time resolution make it robust to multipath and suitable for precise ranging.",{"name":119,"@type":110,"acceptedAnswer":120},"What role do Machine Learning techniques play in this thesis?",{"text":121,"@type":113},"Machine Learning models are used to estimate tag positions and to compensate for systematic errors and non-line-of-sight effects that can degrade UWB localization accuracy in complex environments.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},128810,1786003620,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":52,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":144},1099523885336,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Real-Time Athlete Localization with UWB and Machine Learning  \nTesi di Laurea Magistrale in  \nComputer Science and Engineering-Ingegneria Informatica  \nStefano Staffolani, 10632170  \nAdvisor:  \nProf. Manuel Roveri  \nCo-advisors:  \nPierpaolo Lento Gabriele Viscardi  \nAcademic year:  \n2024-2025  \nAbstract: Accurate real-time localization of athletes is increasingly essential for performance analysis, tactical assessment, and injury prevention in modern sports environments. Although Global Navigation Satellite Systems (GNSS) and optical tracking solutions are widely adopted, they present significant limitations in terms of positioning accuracy, infrastructure cost, and indoor applicability.  \nThis thesis investigates the use of Ultra-Wideband (UWB) radio technology, in combination with Machine Learning (ML) techniques, to develop a real-time localization system (RTLS) optimized for dynamic sports scenarios. Specifically, the Time Difference of Arrival (TDoA) method is employed to enable accurate localization of wearable devices (tags) with minimal computational load on the devices themselves.  \nThe main contributions of this work include the design and implementation of a complete data acquisition system featuring an intuitive interface for real-time visualization of athlete positions; the enhancement of a traditional TDoA-based localization algorithm through architectural and mathematical improvements; and the proposal and evaluation of ML-based models capable of estimating tag positions. Additionally, several hardware and communication improvements have been introduced to enhance system scalability, reduce packet loss, and support both indoor and outdoor deployments.  \nExperimental results show that the proposed approach enables reliable real-time performance and good localization accuracy, even in complex sports scenarios.  \nKey-words: Ultra-Wideband (UWB), Real-Time Locating System (RTLS), Time Difference of Arrival (TDoA), Athlete Tracking, Machine Learning, Localization System Design  \n1. Introduction  \nReal-time localization of athletes and equipment has become a pivotal component of performance analysis in professional sports. By tracking players’ positions, speeds, and movement patterns during training and competition, coaches and sports scientists can quantify external workload and gain tactical insights for injury prevention and strategy development [6] . Traditionally, outdoor team sports have relied on Global Navigation Satellite Systems (GNSS), such as GPS, with wearable sensors to monitor distance covered and velocities. While GNSS-based devices are generally considered valid and reliable for capturing overall running distance and speed in outdoor environments [6], they suffer important limitations. Their positional accuracy (often on the order of several meters) and update rates are insufficient to capture the rapid, high-intensity movements and directional changes characteristic of many sports. Moreover, GNSS signals cannot penetrate most building structures, rendering GPS tracking ineffective for indoor sports or covered stadiums [1] . Alternative optical tracking systems (e.g. multi-camera video or infrared motion capture) can provide high accuracy and full-field coverage, but these systems are expensive, infrastructure-heavy, and limited to specific instrumented venues. This creates a clear need for a portable, accurate, and Real-Time Locating System (RTLS) that can operate in both indoor and outdoor sport settings.  \nUltra-Wideband (UWB) radio technology has emerged in the last two decades as a promising solution for precise indoor localization. UWB-based RTLS offers several advantages over conventional technologies. By utilizing very large signal bandwidths (typically ≥500 MHz) in the 3.1–10.6 GHz spectrum, UWB signals produce nanosecond-scale pulses, which enable time-of-flight distance measurements with fine resolution on the order of a few centimeters [12] . In 2002, regulatory agencies such as the U.S. F","cbCaiqG0SjTS1KcD","https://ap.wps.com/l/cbCaiqG0SjTS1KcD","pdf",11799051,34,"English","# Introduction\n## Motivation and limitations of GNSS and optical tracking\n## Why UWB for sports RTLS\n## Challenges motivating ML-enhanced solutions","[{\"question\":\"Why are GNSS solutions insufficient for real-time athlete tracking in sports?\",\"answer\":\"GNSS positional accuracy is typically only meters-level and update rates cannot capture rapid, high-intensity movement and directional changes. In addition, GNSS signals often cannot penetrate building structures, limiting indoor or covered-stadium use.\"},{\"question\":\"How does UWB support accurate indoor localization for RTLS?\",\"answer\":\"UWB uses very large signal bandwidths to create nanosecond-scale pulses, enabling fine time-of-flight distance measurements with centimeter-level resolution. Its broad spectrum and time resolution make it robust to multipath and suitable for precise ranging.\"},{\"question\":\"What role do Machine Learning techniques play in this thesis?\",\"answer\":\"Machine Learning models are used to estimate tag positions and to compensate for systematic errors and non-line-of-sight effects that can degrade UWB localization accuracy in complex environments.\"}]","Real-Time Athlete Localization with UWB and Machine Learning - Master’s Thesis | PDF",86]