High Maneuverability and Efficiency Control for Hybrid Quadrotor With All-Moving Wings in SE(3) Based on Deep Reinforcement Learning

This article introduces a novel composite aerial vehicle configuration called hybrid quadrotor with all-moving wings (HQWAW), consisting of a conventional quadrotor combined with two independently all-moving wings. A nonlinear geometric controller in the special Euclidean group SE(3) is proposed as the basic controller for the HQWAW, achieving high maneuverability and energy-efficient flight. Lyapunov stability criterion is used to prove that the proposed control scheme can track the reference trajectory almost globally ultimately uniformly bounded. A deep reinforcement learning compensator, based on the twin delayed deep deterministic policy gradient algorithm, is designed to fine-tune all-moving wing angles, ensuring that wing surfaces remain at optimal angles, thereby maximizing aerodynamic efficiency and reducing rotor consumption. Tracking results for a trajectory involving high-speed dive followed by spiral ascent demonstrate that the proposed algorithm achieves both high maneuverability and improved energy efficiency of the HQWAW.