What is it about?
The focus of the paper is machine-learning-assisted computation of low-thrust orbit-raising trajectories. We consider a sequential algorithm for computing multi-revolution trajectories, whose optimization cost function parameters can be updated through a high-level planner utilizing a suitably trained artificial neural network. Considering two different orbit-raising mission scenarios based on the final target orbit (geostationary and near-rectilinear halo orbit), we conduct numerical simulations to compare the results of this approach with that provided by a deep reinforcement learning framework.
Featured Image
Photo by Kevin Stadnyk on Unsplash
Why is it important?
Advancements in solar-electric propulsion technology have led to its widespread adoption in various space missions, including interplanetary, geocentric, and cislunar missions, due to significant mass savings. However, the complex mission planning process, especially in the presence of eclipses and nonlinear dynamics in cislunar scenarios, poses challenges. This paper focuses on the multi-revolution low-thrust orbit-raising problem, considering two types of missions from super-synchronous geosynchronous transfer orbit (GTO) to either geocentric equatorial orbit (GEO) or near-rectilinear halo orbit (NRHO).
Perspectives
Read the Original
This page is a summary of: Machine Learning Assisted Low-Thrust Orbit-Raising: A Comparative Assessment of a Sequential Algorithm and Deep Reinforcement Learning Approach, January 2024, American Institute of Aeronautics and Astronautics (AIAA),
DOI: 10.2514/6.2024-1669.
You can read the full text:
Contributors
The following have contributed to this page