Adaptive learning-based tracking control for tilted-rotor UAVs under uncertain environments

With the rapid growth of the low-altitude economy, unmanned aerial vehicles (UAVs) are increasingly used in complex environments to perform repetitive tasks, where nonlinear dynamics, disturbances, model uncertainties, and input constraints challenge controller design. This paper proposes an adaptive learning-based trajectory tracking strategy for hexarotor UAVs with fixed tilted rotors. By decoupling the dynamics into translational and rotational subsystems, the control framework is simplified. For the translational subsystem, a novel adaptive iterative learning control (AILC) method is developed to improve tracking across repeated operations, compensating for uncertainties and disturbances through adaptive update laws and an input-dependent auxiliary system. Closed-loop convergence is analyzed using a composite energy function approach. Simulations in MATLAB and SITL environments demonstrate the method's effectiveness, robustness, and application potential.