EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Parallel Reconfiguration Planning for Modular Self-Reconfigurable Satellites via Multi-Agent Reinforcement Learning

Bo Wang, Shilong Li, Jialin Yu, Dong Ye, Zhaowei Sun

Aerospace · 17.08.2026 · 13 (8) · 731

DOI: 10.3390/aerospace13080731 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Aerospace, online erschienen am 17.08.2026. Verfasst von Bo Wang und 4 weiteren Autor:innen. Die Arbeit nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Modular self-reconfigurable satellites can adapt to diverse space missions by dynamically rearranging their configurations. Enabling multiple modules to move simultaneously enhances reconfiguration efficiency but remains constrained by existing planning algorithms. This article introduces the Parallel Reconfiguration Planner (PRP), a learning-based approach that ensures safe, concurrent module movements. PRP leverages multi-agent reinforcement learning to generate reconfiguration policies while incorporating safety constraints modeled using Linear Temporal Logic (LTL). To improve learning efficiency, PRP integrates a guarded exploration mechanism based on these safety specifications. Experiments on 3D reconfiguration scenarios demonstrate that PRP achieves more efficient reconfiguration policies in scenarios that have more moving modules compared to the baseline method.

Zitieren

APA

Wang, B., Li, S., Yu, J., Ye, D., & Sun, Z. (2026). Parallel Reconfiguration Planning for Modular Self-Reconfigurable Satellites via Multi-Agent Reinforcement Learning. Aerospace, 13(8), 731. https://doi.org/10.3390/aerospace13080731

Vancouver

Wang B, Li S, Yu J, Ye D, Sun Z. Parallel Reconfiguration Planning for Modular Self-Reconfigurable Satellites via Multi-Agent Reinforcement Learning. Aerospace. 2026;13(8):731. doi:10.3390/aerospace13080731

BibTeX
@article{Wang2026,
  author = {Wang, Bo and Li, Shilong and Yu, Jialin and Ye, Dong and Sun, Zhaowei},
  title = {Parallel Reconfiguration Planning for Modular Self-Reconfigurable Satellites via Multi-Agent Reinforcement Learning},
  journal = {Aerospace},
  year = {2026},
  volume = {13},
  number = {8},
  pages = {731},
  doi = {10.3390/aerospace13080731}
}
Kostenlos starten →