An Assessment of the Performance of Machine Learning Techniques When Applied to Trajectory Optimization
Description
Prior research has confirmed that supervised learning is an effective alternative to computationally costly numerical analysis. Motivated by NASA's use of abort scenario matrices to aid in mission operations and planning, this paper applies supervised learning to trajectory optimization in an effort to assess the accuracy of a less time-consuming method of producing the magnitude of delta-v vectors required to abort from various points along a Near Rectilinear Halo Orbit. Although the utility of the study is limited, the accuracy of the delta-v predictions made by a Gaussian regression model is fairly accurate after a relatively swift computation time, paving the way for more concentrated studies of this nature in the future.
Date Created
The date the item was original created (prior to any relationship with the ASU Digital Repositories.)
2018-05
Agent
- Author (aut): Smallwood, Sarah Lynn
- Thesis director: Peet, Matthew
- Committee member: Liu, Huan
- Contributor (ctb): Mechanical and Aerospace Engineering Program
- Contributor (ctb): School of Earth and Space Exploration
- Contributor (ctb): Barrett, The Honors College