Yazar "Obaid, Amro Ali" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • [ X ]
    Öğe
    Obstacle avoidance in unmanned aerial vehicles using image segmentation and deep learning
    (Altınbaş Üniversitesi / Lisansüstü Eğitim Enstitüsü, 2022) Obaid, Amro Ali; Koyuncu, Hakan
    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.
  • [ X ]
    Öğe
    Obstacle avoidance in unmanned aerial vehicles using image segmentation and deep learning
    (Institute of Electrical and Electronics Engineers Inc., 2022) Obaid, Amro Ali; Koyuncu, Hakan
    Machine learning is a branch of artificial intelligence based on the idea that systems can learn to identify patterns and make decisions with a minimum of human intervention. In this study, demonstration learning will be used, using neural networks in a prototype of a drone built to perform trajectories in controlled environments. To accelerate the training convergence process, a new training data selection approach has been introduced, which picks data from the experience pool based on priority instead of randomness. An autonomous maneuver strategy for dual-UAV olive formation air warfare is provided, which makes use of UAV capabilities such as obstacle avoidance, formation, and confrontation to maximize the effectiveness of the attack.