Document Type
Honors Thesis
Abstract
A major problem with using GPS to navigate an unmanned aerial vehicle is that GPS signals do not accurately work while inside a building. This work presents the usage of the Simultaneous Localization and Mapping library, ORB-SLAM2, in C++ to solve this issue. By using the camera attached to the unmanned aerial vehicle, a map of the area covered by the drone will be created, and landmarks in area will be utilized to navigate throughout the interior of the building without the GPS. Based on previous studies, this navigation method should be viable. Preliminary tests show that this method will efficiently map out the area traversed by an unmanned aerial vehicle and allows for accurate navigation of an environment when GPS is not able to be utilized.
Disciplines
Artificial Intelligence and Robotics
Publication Date
5-2025
Language
English
Faculty Mentor of Honors Project
Chenxi Wang
License
This work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.
Recommended Citation
Pavlik, Joseph R. III, "Navigation of Unmanned Aerial Vehicle Using Computer Vision in Raytheon Drone Competition" (2025). 2025 Spring Honors Capstone Projects. 30.
https://mavmatrix.uta.edu/honors_spring2025/30