Two Supervised Machine Learning Approaches for Wind Velocity Estimation Using Multi-Rotor Copter Attitude Measurements

Abstract

In this work we address the adequacy of two machine learning methods to tackle the problem of wind velocity estimation in the lowermost region of the atmosphere using on-board inertial drone data within an outdoor setting. We fed these data, and accompanying wind tower measurements, into a K-nearest neighbor (KNN) algorithm and a long short-term memory (LSTM) neural network to predict future windspeeds, by exploiting the stabilization response of two hovering drones in a wind field. Of the two approaches, we found that LSTM proved to be the most capable supervised learning model during more capricious wind conditions, and made competent windspeed predictions with an average root mean square error of 0.61 m·s−1 averaged across two drones, when trained on at least 20 min of flight data. During calmer conditions, a linear regression model demonstrated acceptable performance, but under more variable wind regimes the LSTM performed considerably better than the linear model, and generally comparable to more sophisticated methods. Our approach departs from other multi-rotor-based windspeed estimation schemes by circumventing the use of complex and specific dynamic models, to instead directly learn the relationship between drone attitude and fluctuating windspeeds. This exhibits utility in a range of otherwise prohibitive environments, like mountainous terrain or off-shore sites.

High-altitude vertical wind profile estimation using multirotor vehicles

“…A number of other approaches to modeling this relationship have been tested with varying degrees of success. Crowe et al (2020) used more data-driven approaches, such as K-nearest neighbors and an LSTM, to build the relationship using similarly gathered data. Marino et al (2015) evaluated multirotors as flying wind sensors for use around tall buildings and proposed another approach by mapping the power consumption of individual rotors to oncoming flow vectors.…”

Wind Pressure Orthogonal Decomposition Anemometer: A Wind Measurement Device for Multi-Rotor UAVs

“…He built three models to obtain wind speeds from the output of the UAV motors, the attack, roll, and pitch angles of the airframe. With the rapid development of various non-linear models, artificial intelligence and machine learning techniques have been used in wind measurement models in recent years [23,24]. They are effective in improving the measurement performance of IMMs.…”