Spacecraft Identification Leveraging Unsupervised Learning Techniques for Formation and Swarm Missions
Abstract
The small satellite revolution has opened the door to a new era in satellite development. As spacecraft hardware continues to advance, traditional monolithic satellites can potentially be replaced with cooperative swarms of smaller spacecraft. For mission success, satellites in the group will need to identify their nearest neighbors. This research presents a solution for the spacecraft identification problem using an unsupervised learning architecture that classifies spacecraft from monocular camera images. The algorithm employs on-board learning to identify multiple space objects in an image and track their trajectories over time. Preliminary results show high levels of classification accuracy as well as the ability of the algorithm to properly evolve as the spacecraft swarm changes throughout the simulation.
Recommended Citation
J. C. Davis and H. J. Pernicka, "Spacecraft Identification Leveraging Unsupervised Learning Techniques for Formation and Swarm Missions," Proceedings of the AIAA Scitech 2020 Forum (2020, Orlando, FL), American Institute of Aeronautics and Astronautics (AIAA), Jan 2020.
The definitive version is available at https://doi.org/10.2514/6.2020-1195
Meeting Name
AIAA Scitech 2020 Forum (2020: Jan. 6-10, Orlando, FL)
Department(s)
Mechanical and Aerospace Engineering
International Standard Book Number (ISBN)
978-162410595-1
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2020 American Institute of Aeronautics and Astronautics (AIAA), All rights reserved.
Publication Date
10 Jan 2020
