Fast Model-Free Learning for Controlling a Quadrotor UAV With Designed Error Trajectory

Traditional model-based control methods typically require accurate system dynamics. However, when controlling a complex non-linear system such as a quadrotor unmanned aerial vehicle (QUAV), the dynamics are unknown and it is challenging to tune the control parameters manually. This paper proposes a novel model-free learning method that combines the advantages of a model-based method, i.e., sliding mode control (SMC), with the iterative learning control (ILC) method. Specifically, we selected a designed sliding surface to obtain the expected tracking error trajectory as the learning objective, and the system tracking errors of the angles of the QUAV constitute the state space. Then, the policy of converging to the sliding surface is learned by an ILC algorithm. We have provided theoretical proof of the convergence, and validated the proposed method with real-world experiments where the sine wave signals of roll and pitch angles were tracked. The results have demonstrated the effectiveness of the method with less tracking errors as well as faster learning speed compared with a baseline PID controller and a sliding mode controller.