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

What is it about?

Spacecraft guidance in cislunar space presents significant challenges due to the complex dynamics and nonlinearities of the three-body problem. We use a deep neural network, trained by reinforcement learning, to provide a spacecraft with autonomous and robust guidance capabilities during transfers between quasiperiodic orbits in cislunar space.

Featured Image