Tilt-rotor quadcopter improves hover control using learned wind compensation
Tilt-Rotor Quadcopter with Learned Residual Control and Mode-Dependent State Estimation
Robotics
Summary
Tilt-rotor quadcopters can fly straight without leaning, but controlling them is tricky because their mechanics are more complex. The authors created a simulation of such a quadcopter that uses careful math modeling and a special sensor fusion method to know exactly where it is and how it’s oriented. They also taught a small neural network to correct steady position errors caused by wind, even though the network never directly senses the wind itself. In their tests, this approach cut static position errors from wind nearly in half compared to standard control.
What this means in practice
- •For drone developers: Implement more accurate hover and translation control on tilt-rotor quadcopters by integrating learned residual wind compensation with mode-dependent state estimation.
- •For aerial robotics engineers: Use the flight stack framework as a foundation for hardware-in-the-loop testing and real-world flight validation of tilt-rotor UAVs under varying wind conditions.
Authors
Ninad Joshi, Prabhat Kumar
Abstract
Tilt-rotor quadcopters redirect thrust for translation without banking, but complicate modeling, state estimation, and disturbance rejection. This paper presents a simulation-based flight stack for a \SI{2.00}{\kilo\gram} tilt-rotor quadcopter. The system uses a six-degree-of-freedom nonlinear model with first-order motor dynamics and two-axis rotor tilt, parameterized using a 3D CAD model. A cascaded PD controller commands forward and lateral tilt angles. A 14-state EKF fuses sensor data across hover, early-transition, and transition modes using a hysteretic (Schmitt-trigger) classifier to prevent covariance discontinuities. Because the proportional position loop leaves a steady-state offset under constant wind, a small bounded neural residual is added on top of the unmodified PD controller. It is trained by behavioral cloning from a teacher with privileged access to the true wind, while the deployed network never observes wind. In simulation, the EKF achieves a post-settling position root mean square error (RMSE) of \SI{0.226}{\metre} (horizontal) and \SI{0.03}{\metre} (vertical) and an attitude RMSE below \SI{0.8}{\degree}, and it estimates a wind velocity of $(\num{2.0}, \num{-1.2})\,\unit{\metre\per\second}$ to within \SI{0.15}{\metre\per\second} per axis. The residual reduces steady-state station-keeping error under wind by approximately \SI{49}{\percent}, from \SI{0.117}{\metre} to \SI{0.060}{\metre} at \SI{1.5}{\metre\per\second} and from \SI{0.319}{\metre} to \SI{0.162}{\metre} at an out-of-distribution \SI{3.9}{\metre\per\second}. The framework provides a basis for hardware-in-the-loop and flight-test studies.