Obstacle avoidance in unmanned aerial vehicles using image segmentation and deep learning
[ X ]
Tarih
2022
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Altınbaş Üniversitesi / Lisansüstü Eğitim Enstitüsü
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
Computer vision and mobility vehicles have both recently used artificial intelligence algorithms.
Using deep learning in image processing, a wide variety of robotic tasks, including as object
recognition, obstacle avoidance, and control, may be accomplished. There are a limited number
of algorithms designed specifically to process color photographs, which contain a wealth of
data. For this reason, this work investigates the use of numerous deep learning models in an
obstacle avoidance algorithm. We developed a UWP application that allows the UAV to move
from one location to another without clashing with other objects. Deep learning models may be
called the brains of drones since they analyze images taken by the UAV's eye, a monocular
camera. In order to avoid an obstacle, a deep learning model must be able to make the same
judgment as a drone operator. An obstacle avoidance strategy that is similar to a pilot's approach
could emerge when models are trained using the same dataset, and this similarity increases as
training data increases The DRL agent's performance can only be improved by training. Value
functions are part of the agent, which translates the environment's state into a control signal and
provides a measure of how beneficial the chosen control was in that particular state. In the
suggested design, ANNs represent both the control policy and the value function, and they are
trained by making mistakes.This is impractical for UAV control in real-life applications due to external events such as wind
gusts, sudden changes in aerodynamics as a consequence of external hits, and other
unanticipated occurrences. If you're looking for an alternative to typical UAV control methods
for drone landing, it's exciting to look at the possibilities of DL-based approaches.
Açıklama
Anahtar Kelimeler
UAV, ML, DL, LFD
Kaynak
WoS Q Değeri
Scopus Q Değeri
Cilt
Sayı
Künye
Obaid, Amro Ali. (2022). Obstacle avoidance in unmanned aerial vehicles using image segmentation and deep learning. (Yayınlanmamış yüksek lisans tezi). Altınbaş Üniversitesi, Lisansüstü Eğitim Enstitüsü, İstanbul.
