The increasing deployment of CubeSats in space missions necessitates the development of efficient and reliable orbital maneuvering techniques, particularly given the constraints on fuel capacity and computational resources. This paper presents a novel two-level control architecture designed to enhance the accuracy and robustness of CubeSat orbital maneuvers. The proposed method integrates a J₂-optimized sequence at the high level to leverage natural perturbative effects for fuel-efficient orbit corrections, with a gated recurrent unit (GRU)-based low-level controller that dynamically adjusts the maneuver sequence in real-time to account for unmodeled dynamics and external disturbances. A Kalman filter is employed to estimate the pointing accuracy, which represents the uncertainties in the thrust direction, enabling the GRU to compensate for these uncertainties and ensure precise maneuver execution. This integrated approach significantly enhances both the positional accuracy and fuel efficiency of CubeSat maneuvers. Unlike traditional methods, which either rely on extensive pre-mission planning or computationally expensive control algorithms, our architecture efficiently balances fuel consumption with real-time adaptability, making it well-suited for the resource constraints of CubeSat platforms. The effectiveness of the proposed approach is evaluated through a series of simulations, including an orbit correction scenario and a Monte Carlo analysis. The results demonstrate that the integrated J₂-GRU system significantly improves positional accuracy and reduces fuel consumption compared to traditional methods. Even under conditions of high uncertainty, the GRU-based control layer effectively compensates for errors in thrust direction, maintaining a low miss distance throughout the maneuvering period. Additionally, the GRU’s simpler architecture provides computational advantages over more complex models such as long short-term memory (LSTM) networks, making it more suitable for onboard CubeSat implementations.

This paper presents a novel control framework that integrates the stability insights of traditional control with reinforcement learning (RL) to tackle uncertain nonlinear dynamic systems. By embedding an explicit Lyapunov-decrease term in the RL reward and shaping the reward with sliding-mode control concepts, the policy learns stability-aware and robustness-promoting behavior, optimizing tracking accuracy and energy efficiency while promoting practical stability under uncertainty. The method is applied to the underactuated satellite attitude control problem using magnetorquers, where inherent under-actuation and external uncertainties present challenges. Simulations, complemented by hardware-in-the-loop experiments, demonstrate that the proposed RL controller achieves better performance and robustness compared to traditional control strategies. These results underscore the potential of combining robust control theory with data-driven learning techniques to enhance the safety and efficacy of control systems in aerospace and robotic applications.