Owing to the large communication delay in deep space exploration missions, trajectory maneuvers prior to the flyby of small celestial bodies generally need to be scheduled in advance. However, the lack of prior data and the presence of environmental uncertainties in deep space are significant challenges for maneuver scheduling. To solve this problem, in this study, robust maneuver scheduling networks based on proximal policy optimization were proposed. A reward function that considers the terminal state accuracy of the spacecraft after maneuvering and the total velocity impulse cost was designed for the maneuver scheduling networks. An additional constant was added to the variance of the actor network to improve the performance of the generated maneuvering strategy. Compared with the actor–critic algorithm and genetic algorithm, the maneuvering strategy generated by the maneuver scheduling networks demonstrated the best performance in most simulation scenarios and maintained a better balance between the terminal state accuracy and the total velocity impulse cost. The robustness of the maneuver strategy against uncertain perturbations in the environment and uncertain initial state deviations of the spacecraft was validated in several maneuver scenarios in the simulation. In addition, the generated maneuvering strategy exhibited excellent real-time performance. The time cost to make a decision was still better than 0.7 s in the worst case, testing on Raspberry Pi 4B with a memory of 4 GB and a limited CPU frequency of 800 MHz. The robustness against uncertainties and real-time capability of the proposed method revealed its potential onboard application to future deep space exploration missions.

The coordination of multiple Earth-observing satellites presents a significant scheduling challenge. This paper introduces a fully distributed autonomous scheduling solution that utilizes a learning-based mechanism through an independent proximal policy optimization (IPPO) algorithm. Each satellite independently makes decisions regarding tasks, such as imaging, desaturation, and charging, while adapting to dynamic environmental changes to enhance its real-time constellation scheduling performance. The proposed fully distributed strategy enables individual satellites to update their policies based solely on their observations. The only requirement is the unidirectional broadcast of a completion flag upon target observation. This approach distinguishes itself from traditional centralized methods, thus enhancing the overall robustness and security of the system. In simulations, our strategy exhibited effective observational mission planning results for major cities worldwide. The results show that the proposed method addresses both autonomous scheduling and significantly improves constellation performance and reliability.

This paper investigates the configuration design associated with boundary-constrained swarm flying. An analytic swarm configuration is identified to ensure the passive safety between each pair of spacecraft in the radial-cross-track plane. For the first time, this work derives the explicit configurable spacecraft amount to clarify the configuration’s accommodation capacity while considering the maximum inter-spacecraft separation constraint. For larger-scale design problem that involves hundreds of spacecraft, this paper proposes an optimization framework that integrates a Relative Orbit Element (ROE) affine transformation operation and successional convex optimization. The framework establishes a multi-subcluster swarm structure, allowing decoupling the maintenance issues of each subcluster. Compared with previous design methods, it ensures that the computational cost for constraints verification only scales linearly with the swarm size, while also preserving the configuration optimization capacities. Numerical simulations demonstrate that the proposed analytic configuration strictly meets the design constraints. It is also shown that the proposed framework reduces the handled constraint amount by two orders compared with direct optimization, while achieving a remarkable swarm safety enhancement based on the existing analytic configuration.