Physics-Informed Neural Networks for UAV System Estimation

The dynamic nature of quadrotor flight introduces significant uncertainty in system parameters, such as thrust and drag factor. Consequently, operators grapple with escalating challenges in implementing real-time control actions. This study delves into an approach for estimating the model of quadrotor Unmanned Aerial Vehicles using Physics-Informed Neural Networks (PINNs) when you have a limited amount of data available. PINNs offer the potential to tackle issues like heightened non-linearities in low-inertia systems, elevated measurement noise, and constraints on data availability. The effectiveness of the estimator is showcased in a simulation environment with real data and juxtaposed with a state-of-the-art technique, such as the Extended Kalman Filter (EKF).