1. Swarm-to-swarm orbital pursuit method under delta-v maneuver for space pursuit-evasion.
- Author
-
Luo, Yuelong, Jiang, Xiuqiang, Zhou, Chuang, Zhong, Suchuan, Ji, Yuandong, and Li, Shuang
- Subjects
- *
DEEP reinforcement learning , *REINFORCEMENT learning , *ORBITS (Astronomy) , *SPACE vehicles , *ALGORITHMS - Abstract
This paper investigates the orbital pursuit strategy for spacecraft swarms, where both pursuers and evaders possess limited delta-v maneuvering capabilities. Given that swarms can consist of numerous members, ranging from dozens to thousands, the swarm-to-swarm problem has significant coupling effects that cannot be solved by merely superimposing one-to-one or few-to-few problems. Otherwise, one would cause a dimension explosion in decision-making space. To avoid this issue, the swarm orbital pursuit problem is divided into two coupled problems: swarm target allocation and orbital maneuver. First, considering the relative orbit state between pursuers and evaders and estimated orbital maneuver costs of pursuit, the swarm target allocation problem is formulated into three coupled sub-problems, i.e., target allocation order, target allocation for sub-swarms, and target allocation for individuals. These sub-problems are solved by the presented double-layer contract net protocol algorithm to maximize task completion efficiency. Then, the orbital maneuver problem is decomposed into two coupled problems to maximize pursuit benefits, i.e., long-range rendezvous, and close-distance game maneuvers. For the long-range rendezvous, the optimal Lambert algorithm is developed to efficiently obtain the discrete optimal pursuit time and corresponding orbital transfer maneuver. To address close-distance games more proficiently, a hybrid orbital maneuver algorithm, combining the proximal policy optimization and the Lambert algorithm is proposed. Finally, comparison simulations verified the effectiveness and superiority of the proposed method. • Satellite swarm pursuit problem is transformed to the coupled problem with swarm target allocation and orbital maneuvers. • Swarm target allocation is formulated as a coupled problem with target order, allocations for subgroups and individuals. • An improved DLCNP algorithm is proposed to pursue a reasonable target allocation solution for higher task efficiency. • Optimal Lambert algorithm is developed to obtain the optimal maneuver strategyfor long-range rendezvous. • A hybrid algorithm combining PPO and the Lambert algorithm is presented to get closed-loop control for close-distance games. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF