Wind Estimation in Unmanned Aerial Autos with Causal Machine Learning
Authors: Abdulaziz Alwalan, Miguel Arana-Catania
Abstract: On this work we reveal the chance of estimating the wind ambiance of a UAV with out specialised sensors, using solely the UAV’s trajectory, making use of a causal machine learning technique. We implement the causal curiosity approach which mixes machine learning events sequence classification and clustering with a causal framework. We analyse three distinct wind environments: fastened wind, shear wind, and turbulence, and uncover utterly completely different optimisation strategies for optimum UAV manoeuvres to estimate the wind conditions. The proposed technique will be utilized to design optimum trajectories in tough local weather conditions, and to stay away from specialised sensors that add to the UAV’s weight and compromise its efficiency.
