Reinforcement learning robust optimal control for spacecraft attitude stabilization

The problem of optimal attitude stabilization control of rigid spacecraft despite external disturbances is investigated. An online reinforcement learning-based intelligent and robust control approach is presented via the adaptive dynamic programming technique. In this approach, a critic-only neural network is developed to learn the optimal control policy of the spacecraft attitude system with external disturbance. A new estimation law is synthesized to estimate the weights of that network online. The learned controller can achieve near-optimal control performance. Then, a robust control effort is designed and added into the learned controller to formulate an intelligent and robust controller. It is proven that the closed-loop attitude system obtained from the proposed controller is uniformly ultimately bounded and that the weight estimation error of the Critic NN is convergent by Lyapunov theory. Comparison with the traditional actor-critical neural network-based control schemes shows that with less computation complexity and great robustness to external disturbances, the proposed control approach is less dependent of the persistent excitation condition. Simulation results verify the superior control performance of the proposed approach.