Date of Award
9-2024
Document Type
Dissertation
Degree Name
Doctor of Philosophy (PhD)
Department
Department of Electrical and Computer Engineering
First Advisor
Scott L. Nykl, PhD
Abstract
AAR is increasingly critical as aircraft autonomy advances, particularly for the Global Strike mission of the USAF, enhancing operational range and endurance. Traditional methods relying on GPS and custom communication links are limited in GPS-denied environments. This dissertation advances a single camera method to estimate object pose across three interconnected studies. The system trains a CNN on synthetic imagery to predict bboxes for object components, Solve-PnP algorithm finds the 6DoF pose, then employs novel pseudo-labeling on real-world images. These findings are pivotal for the AAR community and contribute to robotics, computer vision, and CNN research. By enabling robust GPS-free autonomous systems, this research advances capabilities critical to future autonomous aerospace operations.
AFIT Designator
AFIT-ENG-DS-24-S-016
Recommended Citation
Choate, Jeffrey L., "Advancing Robust Autonomous System Localization: Labeling Optimizations for Convolutional Neural Networks" (2024). Theses and Dissertations. 7994.
https://scholar.afit.edu/etd/7994