Institutional Repository
Technical University of Crete
Technical University of Crete
EN
|
EL
| URI: | http://purl.tuc.gr/dl/dias/86A9EBB8-7FA6-42AB-AE7D-9DD10A61BA1F | ||
| Year | 2023 | ||
| Type of Item | Diploma Work | ||
| License |
|
||
| Bibliographic Citation | Georgios Loukopoulos-Chatzigiosis, "Embedded system for real-time detection of escape openings towards unmanned aerial vehicle navigation", Diploma Work, School of Electrical and Computer Engineering, Technical University of Crete, Chania, Greece, 2023 https://doi.org/10.26233/heallink.tuc.95104 | ||
| Appears in Collections |
Unmanned aerial vehicles (UAVs), also known as drones, have emerged as versatile tools for various applications, including surveillance, inspection, delivery, and search and rescue missions. The increasing popularity of UAVs has led to a growing demand for advanced autonomous navigation systems to enable them to perform complex tasks independently. Autonomous navigation refers to the ability of UAVs to navigate and maneuver without human intervention, relying on onboard sensors, algorithms, and decision-making processes. Two of the critical tasks in UAV autonomous navigation is localization, which refers to determining the drone's position and orientation relative to its environment, and mapping which is the ability of the drone to build a map of its surroundings. Another important aspect is the detection of escape openings, which are critical in emergency situations, allowing the UAV to navigate through narrow or complex environments. In this work, we present an approach that addresses the challenges of localization, mapping, and escape opening detection in UAV autonomous navigation, while minimizing cost, energy consumption, and resource usage. Our solution leverages the power of Computer Vision algorithms and sensors, enabling accurate and robust localization and mapping, as well as an efficient escape opening detection.
Copyright © DIAS 2013
