Reinforcement Learning-Based Fixed-Time Synchronized Control for Spacecraft Attitude Stabilization

This paper presents a fixed-time synchronized reinforcement learning-based control (pFxT-SRLC) framework for spacecraft attitude systems that simultaneously addresses four critical challenges: predetermined convergence time guarantees, synchronized multi-axis coordination, energy optimization, and practical constraint handling. Our integrated framework combines a fixed-time super-twisting observer with adaptive switching strategy, a practical fixed-time synchronized controller with singularity avoidance, and an actor-critic reinforcement learning structure for near-optimal energy performance. The proposed method ensures all state variables converge to desired neighborhoods simultaneously within predetermined time bounds independent of initial conditions, while the constrained learning algorithm maintains stability throughout the optimization process. A second-order command filter handles input saturation constraints and reduces control chattering for practical implementation. Theoretical analysis proves fixed-time synchronized stability with explicit convergence time bounds, and establishes energy optimality through Hamilton-Jacobi-Bellman approximation. Simulation results demonstrate that the proposed pFxT-SRLC achieves comparable tracking accuracy to conventional fixed-time methods while reducing energy consumption and generating significantly smoother control signals.