Designing Sun–Earth L2 Halo Orbit Stationkeeping Maneuvers via Reinforcement Learning

What is it about?

Reinforcement learning is used to design impulsive station-keeping maneuvers for a spacecraft operating near Sun-Earth L2. Such maneuvers often occur regularly over the span of several years to ensure the spacecraft remains near a reference trajectory. We demonstrate that the station-keeping maneuvers designed using the presented reinforcement learning approach result in boundedness to the vicinity of the selected reference trajectory with low total maneuver requirements, producing comparable results to a traditionally-formulated constrained optimization scheme.

Featured Image