Sequential-synchronized optimized tracking control for a stratospheric airship with reinforcement learning

To improve the safety and efficiency of stratospheric airships in trajectory tracking missions, this paper proposes a sequential-synchronized optimized control (SSOC) scheme that enables the system states to converge in a predefined sequence, accommodating the inherent fast-slow dynamics between the airship's attitude and position states. Specifically, the synchronized convergence of attitude states is achieved first, followed by the synchronized convergence of the position states. Meanwhile, considering the energy consumption limitations of the airships, the proposed control scheme combines the reinforcement learning algorithm with optimal control theory to minimize energy consumption without compromising tracking performance. Rigorous theoretical proofs are provided for the proposed sequential-synchronized convergence. The overall stability of the system is analyzed theoretically and the effectiveness of the proposed control strategy is verified via comparative simulations.