Guidance for Closed-Loop Transfers using Reinforcement Learning with Application to Libration Point Orbits
Author(s)
LaFarge, Nicholas B; Miller, Daniel; Howell, Kathleen C; Linares, Richard
DownloadAccepted version (1.599Mb)
Open Access Policy
Open Access Policy
Creative Commons Attribution-Noncommercial-Share Alike
Terms of use
Metadata
Show full item recordAbstract
While human presence in cislunar space continues to expand, so too does the demand for ‘lightweight’ automated on-board processes. In nonlinear dynamical environments, computationally efficient guidance strategies are challenging. Many traditional approaches rely on either simplifying assumptions in the dynamical model or abundant computational resources. The proposed controller employs the use of the nonlinear equations of motion without imposing a heavy workload on a flight computer. The guidance framework is nevertheless able to leverage high-performance computing by separating the training from the resulting controller. Practical examples demonstrate the flexibility of a reinforcement learning approach, and suggest extendability to higher-fidelity domains.
Date issued
2020Department
Massachusetts Institute of Technology. Department of Aeronautics and AstronauticsJournal
AIAA Scitech 2020 Forum
Publisher
American Institute of Aeronautics and Astronautics (AIAA)
Citation
LaFarge, Nicholas B, Miller, Daniel, Howell, Kathleen C and Linares, Richard. 2020. "Guidance for Closed-Loop Transfers using Reinforcement Learning with Application to Libration Point Orbits." AIAA Scitech 2020 Forum, 1 PartF.
Version: Author's final manuscript