Wind speed estimation for rotary-wing vertical take-off and landing (VTOL) UAVs is challenging due to the low accuracy of airspeed sensors, which can be severely affected by the rotor’s down-wash effect. Unlike traditional aerodynamic modeling solutions, in this paper, we present a K Nearest Neighborhood learning-based method which does not require the details of the aerodynamic information. The proposed method includes two stages: an off-line training stage and an on-line wind estimation stage. Only flight data is used for the on-line estimation stage, without direct airspeed measurements. We use Parrot AR.Drone as the testing quadrotor, and a commercial fan is used to generate wind disturbance. Experimental results demonstrate the accuracy and robustness of the developed wind estimation algorithms under hovering conditions.
Generic wind estimation and compensation based on NLGA and RBF-NN