{"id":{"repo_id":"vt","oai_identifier":"oai:vtechworks.lib.vt.edu:10919/141129"},"canonical_url":"https://search.dev.ndltd.org/etd/vt/oai:vtechworks.lib.vt.edu:10919/141129","repository":{"repo_id":"vt","name":"Virginia Tech","base_url":"https://vtechworks.lib.vt.edu/oai/request"},"display":{"title":"Vision-Based Aerial Navigation Using Satellite Offline Maps","abstract":"While Global Navigation Satellite System (GNSS) technology combined with advanced augmentation techniques provides high accuracy, its reliance on signal integrity leaves safety-critical applications vulnerable to spoofing and jamming. To address this, a lightweight vision-based localization module is proposed as a self-contained GNSS substitute for small Uncrewed Aerial Vehicles (UAVs). It leverages offline satellite maps and an ensemble of Convolutional Neural Network (CNN) models to estimate 2D offsets and associated uncertainty for stable EKF fusion. The system is designed for seamless integration with the PX4 Autopilot and real-time operation on resource-limited platforms. Software In The Loop (SITL) simulations over varied mission scenarios at Virginia Tech's Kentland Farm demonstrate an R95 accuracy of 4.5 m to 5.5 m, with effective drift bounding even in low-texture environments. Remaining challenges include uncertainty calibration, particularly over tree-covered regions, before transitioning to field testing.","abstract_html":"While Global Navigation Satellite System (GNSS) technology combined with advanced augmentation techniques provides high accuracy, its reliance on signal integrity leaves safety-critical applications vulnerable to spoofing and jamming. To address this, a lightweight vision-based localization module is proposed as a self-contained GNSS substitute for small Uncrewed Aerial Vehicles (UAVs). It leverages offline satellite maps and an ensemble of Convolutional Neural Network (CNN) models to estimate 2D offsets and associated uncertainty for stable EKF fusion. The system is designed for seamless integration with the PX4 Autopilot and real-time operation on resource-limited platforms. Software In The Loop (SITL) simulations over varied mission scenarios at Virginia Tech's Kentland Farm demonstrate an R95 accuracy of 4.5 m to 5.5 m, with effective drift bounding even in low-texture environments. Remaining challenges include uncertainty calibration, particularly over tree-covered regions, before transitioning to field testing.","abstract_has_math":false,"creators":["Kempf, Ludwig"],"institution":"Virginia Tech","degree_name":"Master of Science","degree_level":"masters","degree_discipline":"Mechanical Engineering","degree_department":"Mechanical Engineering","school":null,"contributors":[],"advisors":[],"committee_chairs":["Kochersberger, Kevin Bruce"],"committee_members":["Komendera, Erik","Abbott, Amos L."],"year":2026,"date_issued":"2026-02-03","date_published":"2026-02-03","updated_at":"2026-07-22T22:20:34Z","subjects":["GNSS-denied navigation","Vision-based sensing","Cross-view geolocalization"],"languages":["en"],"rights":["In Copyright"],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:45511"],"render_values":[{"text":"vt_gsexam:45511","href":null,"code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/10919/141129","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeechair","label":"Committee Chair","values":["Kochersberger, Kevin Bruce"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Komendera, Erik","Abbott, Amos L."]},{"key":"dc:contributor.department","label":"Department","values":["Mechanical Engineering"]},{"key":"dc:creator","label":"Author","values":["Kempf, Ludwig"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-02-04T09:00:17Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2026-02-04T09:00:17Z"]},{"key":"dc:date.issued","label":"Date","values":["2026-02-03"]},{"key":"dc:publisher","label":"Institution","values":["Virginia Tech"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Mechanical Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Virginia Polytechnic Institute and State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["GNSS-denied navigation","Vision-based sensing","Cross-view geolocalization"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:45511"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10919/141129"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["While Global Navigation Satellite System (GNSS) technology combined with advanced augmentation techniques provides high accuracy, its reliance on signal integrity leaves safety-critical applications vulnerable to spoofing and jamming. To address this, a lightweight vision-based localization module is proposed as a self-contained GNSS substitute for small Uncrewed Aerial Vehicles (UAVs). It leverages offline satellite maps and an ensemble of Convolutional Neural Network (CNN) models to estimate 2D offsets and associated uncertainty for stable EKF fusion. The system is designed for seamless integration with the PX4 Autopilot and real-time operation on resource-limited platforms. Software In The Loop (SITL) simulations over varied mission scenarios at Virginia Tech's Kentland Farm demonstrate an R95 accuracy of 4.5 m to 5.5 m, with effective drift bounding even in low-texture environments. Remaining challenges include uncertainty calibration, particularly over tree-covered regions, before transitioning to field testing."]},{"key":"dc:description.abstractgeneral","label":"General Abstract","values":["Modern drones often rely on satellite navigation, but these signals can be jammed or spoofed, creating risks for safety-critical missions. To reduce this dependence, this work proposes a lightweight, vision-based localization module that can act as a self-contained replacement for satellite navigation on small Uncrewed Aerial Vehicles (UAVs). The system uses pre-downloaded satellite maps and Artificial Intelligence (AI) to estimate how far the UAV has moved and how confident it is in that estimate. This allows the module to integrate smoothly with standard flight-control software like the PX4 Autopilot and run in real time on limited onboard hardware. In simulation tests across varied mission scenarios at Virginia Tech's Kentland Farm, the approach typically keeps the UAV's estimated position within about 4.5 to 5.5 meters. It also limits long-term drift, even when the ground has few visual features. The main remaining challenge is improving how the system measures and reports its own uncertainty, especially over tree-covered areas, before moving from simulation to field testing."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Science"]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["ETD"]},{"key":"dc:title","label":"Title","values":["Vision-Based Aerial Navigation Using Satellite Offline Maps"]}]}],"canonical_facts":{"dc:contributor.committeechair":["Kochersberger, Kevin Bruce"],"dc:contributor.committeemember":["Komendera, Erik","Abbott, Amos L."],"dc:contributor.department":["Mechanical Engineering"],"dc:creator":["Kempf, Ludwig"],"dc:date.accessioned":["2026-02-04T09:00:17Z"],"dc:date.available":["2026-02-04T09:00:17Z"],"dc:date.issued":["2026-02-03"],"dc:description.abstract":["While Global Navigation Satellite System (GNSS) technology combined with advanced augmentation techniques provides high accuracy, its reliance on signal integrity leaves safety-critical applications vulnerable to spoofing and jamming. To address this, a lightweight vision-based localization module is proposed as a self-contained GNSS substitute for small Uncrewed Aerial Vehicles (UAVs). It leverages offline satellite maps and an ensemble of Convolutional Neural Network (CNN) models to estimate 2D offsets and associated uncertainty for stable EKF fusion. The system is designed for seamless integration with the PX4 Autopilot and real-time operation on resource-limited platforms. Software In The Loop (SITL) simulations over varied mission scenarios at Virginia Tech's Kentland Farm demonstrate an R95 accuracy of 4.5 m to 5.5 m, with effective drift bounding even in low-texture environments. Remaining challenges include uncertainty calibration, particularly over tree-covered regions, before transitioning to field testing."],"dc:description.abstractgeneral":["Modern drones often rely on satellite navigation, but these signals can be jammed or spoofed, creating risks for safety-critical missions. To reduce this dependence, this work proposes a lightweight, vision-based localization module that can act as a self-contained replacement for satellite navigation on small Uncrewed Aerial Vehicles (UAVs). The system uses pre-downloaded satellite maps and Artificial Intelligence (AI) to estimate how far the UAV has moved and how confident it is in that estimate. This allows the module to integrate smoothly with standard flight-control software like the PX4 Autopilot and run in real time on limited onboard hardware. In simulation tests across varied mission scenarios at Virginia Tech's Kentland Farm, the approach typically keeps the UAV's estimated position within about 4.5 to 5.5 meters. It also limits long-term drift, even when the ground has few visual features. The main remaining challenge is improving how the system measures and reports its own uncertainty, especially over tree-covered areas, before moving from simulation to field testing."],"dc:description.degree":["Master of Science"],"dc:format.medium":["ETD"],"dc:identifier.other":["vt_gsexam:45511"],"dc:identifier.uri":["https://hdl.handle.net/10919/141129"],"dc:language.iso":["en"],"dc:publisher":["Virginia Tech"],"dc:rights":["In Copyright"],"dc:rights.uri":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["GNSS-denied navigation","Vision-based sensing","Cross-view geolocalization"],"dc:title":["Vision-Based Aerial Navigation Using Satellite Offline Maps"],"dc:type":["Thesis"],"thesis:degree_discipline":["Mechanical Engineering"],"thesis:degree_level":["masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["Virginia Polytechnic Institute and State University"]},"updated_at":"2026-07-22T22:20:34Z"}