What is it about?
Here we are trying to create optimal spacecraft configuration designs by training an AI model. Each time the model creates a design, it is evaluated by some constraints and objectives, and the model updates itself based on the performance of the design it just created. We found that an AI model trained in this way can create better spacecraft configuration designs than other common methods.
Featured Image
Photo by NASA Hubble Space Telescope on Unsplash
Read the Original
This page is a summary of: Spacecraft Configuration Design Exploration Through Transformer-Based Reinforcement Learning, January 2025, American Institute of Aeronautics and Astronautics (AIAA),
DOI: 10.2514/6.2025-0894.
You can read the full text:
Contributors
The following have contributed to this page
