EUVIMEDEUVIMED entdecken
Crossref

Autonomous Guidance Between Quasiperiodic Orbits in Cislunar Space via Deep Reinforcement Learning

Lorenzo Federici, Andrea Scorsoglio, Alessandro Zavoli, Roberto Furfaro

Journal of Spacecraft and Rockets · 2023-11 · 60 (6) · 1954-1965

DOI: 10.2514/1.a35747 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Spacecraft and Rockets, 2023-11. Verfasst von Lorenzo Federici und 3 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 31 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper investigates the use of reinforcement learning for the fuel-optimal guidance of a spacecraft during a time-free low-thrust transfer between two libration point orbits in the cislunar environment. To this aim, a deep neural network is trained via proximal policy optimization to map any spacecraft state to the optimal control action. A general-purpose reward is used to guide the network toward a fuel-optimal control law, regardless of the specific pair of libration orbits considered and without the use of any ad hoc reward shaping technique. Eventually, the learned control policies are compared with the optimal solutions provided by a direct method in two different mission scenarios, and Monte Carlo simulations are used to assess the policies’ robustness to navigation uncertainties.

Zitieren

APA

Federici, L., Scorsoglio, A., Zavoli, A., & Furfaro, R. (2023). Autonomous Guidance Between Quasiperiodic Orbits in Cislunar Space via Deep Reinforcement Learning. Journal of Spacecraft and Rockets, 60(6), 1954-1965. https://doi.org/10.2514/1.a35747

Vancouver

Federici L, Scorsoglio A, Zavoli A, Furfaro R. Autonomous Guidance Between Quasiperiodic Orbits in Cislunar Space via Deep Reinforcement Learning. Journal of Spacecraft and Rockets. 2023;60(6):1954-1965. doi:10.2514/1.a35747

BibTeX
@article{Federici2023,
  author = {Federici, Lorenzo and Scorsoglio, Andrea and Zavoli, Alessandro and Furfaro, Roberto},
  title = {Autonomous Guidance Between Quasiperiodic Orbits in Cislunar Space via Deep Reinforcement Learning},
  journal = {Journal of Spacecraft and Rockets},
  year = {2023},
  volume = {60},
  number = {6},
  pages = {1954--1965},
  doi = {10.2514/1.a35747}
}
Kostenlos starten →