MPC for underactuated spacecraft control with a Lyapunov supervised physics-informed neural network correction layer
For underactuated spacecraft control, this work addresses the challenge of combining learning-based disturbance estimation with stability guarantees, though the approach is incremental as it builds on existing NMPC and PINN methods.
The paper presents a hierarchical control architecture combining NMPC, a physics-informed neural network for disturbance estimation, and a Lyapunov-based safety layer for underactuated spacecraft attitude control. Monte Carlo simulations show statistically significant reductions in steady-state attitude error compared to standalone NMPC while maintaining robustness under uncertainty.
Underactuated spacecraft faces controllability limitations and heightened sensitivity to environmental disturbances, complicating attitude maneuvering and stabilization. Due to the lack of control authority along the underactuated axis, conventional controllers cannot directly stabilize all attitude components and therefore require reference planning strategies. Furthermore, MPC approaches remain sensitive to inertia uncertainty and unmodeled dynamic couplings, resulting in degraded tracking performance under mismatch. To address these issues, we consider a hierarchical architecture integrating three layers: (i) a nonlinear model predictive controller (NMPC) for constraint and underactuation-aware maneuver planning and nominal closed-loop stability under actuator limits; (ii) a physics-informed neural network (PINN) trained offline on simulation data to estimate residual disturbance torques, with loss terms that enforce consistency with rigid-body rotational dynamics; (iii) a Lyapunov-based supervisory safety mechanism that evaluates the learned correction online and bounds or suppresses its influence to preserve the stability properties of the baseline controller. The architecture is evaluated in a high-fidelity simulation environment modelling reaction wheel dynamics, actuator saturation, and environmental disturbances. Monte Carlo studies show statistically significant reductions in steady-state attitude error relative to standalone NMPC while maintaining robust behavior under uncertainty. The supervisory layer ensures graceful degradation to purely model-based control when the learning-based augmentation is unreliable.