Unmanned Aerial Vehicle
Unmanned Aerial Vehicles (UAVs), or drones, are increasingly used for diverse applications, driving research focused on improving their autonomy, safety, and efficiency. Current research emphasizes robust navigation and control in complex environments, employing techniques like nonlinear model predictive control and advanced search algorithms for path planning, often coupled with deep learning models (e.g., YOLO, U-Net) for perception and object detection. These advancements are crucial for expanding UAV capabilities in sectors such as agriculture, search and rescue, and infrastructure monitoring, while also addressing critical concerns like security and reliable operation in challenging conditions (e.g., GPS-denied environments, harsh weather).
Papers
A Reinforcement Learning Approach for Robust Supervisory Control of UAVs Under Disturbances
Ibrahim Ahmed, Marcos Quinones-Grueiro, Gautam Biswas
YOLOv3 with Spatial Pyramid Pooling for Object Detection with Unmanned Aerial Vehicles
Wahyu Pebrianto, Panca Mudjirahardjo, Sholeh Hadi Pramono, Rahmadwati, Raden Arief Setyawan