UAV Adaptive Trajectory for Detection of Xylella Fastidiosa Disease in Olive Trees

This paper presents an adaptive trajectory generation for drones that inspect trees to diagnose the Xylella Fastidiosa disease. In particular, a simulation environment has been developed within the ROS (Robot Operating System) framework, including Gazebo, Rviz, and MoveIt platforms. Then, a suitable algorithm is proposed for efficient detection and exploration of the selected area. The inspection process involves a simulated drone which is driven by a workstation performing all the necessary computations. A communication protocol is agreed upon with four codes used by the drone to forward requests to the workstation, which will respond to the ROS topics created specifically. The algorithm consists of the following steps. Firstly, the drone takes off and reaches the centre of the area to be monitored. Then, it identifies the position of the trees by processing the aerial images and autonomously plans the main trajectory to visit them all. Each time a tree is reached, its canopy is fully inspected in order to collect an adequate number of images to detect the presence of the Xylella disease by a post-processing analysis using neural networks. Simulation results show the effectiveness of the proposed approach.