Relative motion guidance for near-rectilinear lunar orbits with path constraints via actor-critic reinforcement learning

Andrea Scorsoglio, Roberto Furfaro, Richard Linares, Mauro Massari

Research output: Contribution to journalArticlepeer-review

13 Scopus citations

Abstract

This paper presents a feedback guidance algorithm for proximity operation in cislunar environment based on actor-critic reinforcement learning. The algorithm is lightweight, closed-loop, and capable of taking path constraints into account. The method relies on reinforcement learning to make the well known Zero-Effort-Miss/Zero-Effort-Velocity guidance state dependent and allow for path constraints to be directly embedded. The algorithm is tested in the circular restricted three-body problem (CRTBP) framework for Near Rectilinear Orbits (NRO) in the Earth-Moon system. It shows promising results in terminal guidance error and satisfies path constraints in constraint scenarios comprising spherical constraints and keep-out-spheres with approach corridors. Furthermore, this approach indicates that reinforcement learning can be effectively used to solve constrained relative spacecraft guidance problems in complex environments and thus can be effective for autonomous relative motion operations in the Earth-Moon dynamical environment.

Original languageEnglish (US)
Pages (from-to)316-335
Number of pages20
JournalAdvances in Space Research
Volume71
Issue number1
DOIs
StatePublished - Jan 1 2023

Keywords

  • Actor-critic
  • Machine learning
  • Near Rectilinear Orbits
  • Reinforcement learning
  • Spacecraft guidance

ASJC Scopus subject areas

  • Aerospace Engineering
  • Astronomy and Astrophysics
  • Geophysics
  • Atmospheric Science
  • Space and Planetary Science
  • General Earth and Planetary Sciences

Fingerprint

Dive into the research topics of 'Relative motion guidance for near-rectilinear lunar orbits with path constraints via actor-critic reinforcement learning'. Together they form a unique fingerprint.

Cite this