Implementation of a Neural Network for Nonlinearities Estimation in a Tail-Sitter Aircraft

A tail-sitter aircraft’s control is a challenging task, especially during transition maneuvers where the lift and drag forces are highly non-linear. In this work, we implement a neural network (NN) capable to estimate such nonlinearities. Once they are estimated, one can propose a control scheme where these forces can correctly feed-forwarded. Our NN implementation has been programmed in C++ within the PX4 Autopilot, an open-source autopilot for drones. To ensure that this implementation does not considerably affect the autopilot’s performance, the coded NN must imply light computational load. To test our approach, we have carried out a series of realistic simulations in the Software in The Loop (SITL) using the PX4 Autopilot firmware. These experiments demonstrate that the implemented NN can be used to estimate the tail-sitter aerodynamic forces to improve the control algorithms during all the flight phases of the tail-sitter aircraft: hover, cruise flight, and transition.