20 September 2023 in IEEE Transactions on Aerospace and Electronic Systems
Real-time emergency event processing for mega-constellation management requires an approach that can quickly obtain a satisfactory satellite range rescheduling scheme. In this paper, a deep reinforcement learning (DRL) approach is proposed for rapid rescheduling on the basis of established satellite range scheduling schemes. Three rescheduling principles with different impacts on established scheduling schemes are first analyzed. A mathematical model for both maximizing the completion profits of dynamic missions and minimizing their impacts on scheduled missions is formulated. An efficient DRL-based approach to satellite range rescheduling is then developed. A mask processing mechanism is integrated into the reinforcement learning framework to effectively eliminate the conflicts accurately expressed by the conflict space, and a modified pointer network (Ptr-Net) based on the mask processing mechanism is employed to approximate the action-value function for optimal decision-making. Experimental results show that the proposed approach significantly outperforms the rule-based heuristic and another DRL-based method in terms of computational efficiency and optimization performance, and the total time spent during the training and testing phases of the proposed approach is approximately 13% of the total running time required by the search-based methods.
31 December 2020 in IEEE Transactions on Aerospace and Electronic Systems
The design of multitarget rendezvous missions requires a method to quickly and accurately approximate the optimal transfer between any two rendezvous targets. In this paper, an artificial neural network-based method is proposed for the rapid approximation of optimal perturbed long-duration impulsive transfers. The relationship between the optimal transfer velocity increments and the initial right ascension of the ascending node difference between the departure body and the rendezvous target is analyzed, and the result suggests that the perturbed long-duration impulsive transfers should be divided into three types. An efficient database generation method is developed. Three regression multilayer perceptrons are trained individually and applied to approximate the corresponding types of transfers. The simulation results show that the well-trained multilayer perceptrons are capable of quickly estimating the optimal velocity increments with a relative error of less than 3% for all three types of transfers. Additional tests of the debris chains with total velocity increments of several thousand m/s show that the estimation results are very close to the optimized results, with a final estimation error of less than 10 m/s.
1 February 2025 in Astrodynamics
1 July 2024 in Journal of Guidance, Control, and Dynamics
16 September 2025 in IEEE Transactions on Aerospace and Electronic Systems
Global trajectory optimization of multitarget successive rendezvous missions is studied. A learning-based method is proposed to train a neural network offline, which can directly generate the near-optimal rendezvous sequence online. A neural network structure based on the attention mechanism is developed to extract combinatorial features among multiple on-orbit bodies. Physical equations and neural networks are integrated to generate solutions in a recurrent manner. The sequence generator can be trained and applied in cases with diverse values and sizes. A local refinement approach is applied to the generator to enhance the final solution quality. A reinforcement parallel learning algorithm is specifically designed for efficient model training. Numerical simulations are conducted on general random cases and global trajectory optimization competition (GTOC) problems. The well-trained solver can efficiently produce a sequence that is equivalent to the solution obtained via traditional advanced heuristics. When the trained sequence generator is applied to multispacecraft rendezvous sequence planning, the target assignment optimization process clearly accelerates due to fast sequence generation. The sequence and time of the GTOC winner's solution is reoptimized and better results were obtained, indicating that the proposed model performs significantly well in terms of solution quality.