Machine learning and evolutionary techniques in interplanetary trajectory design
Neural and Evolutionary Computing
2018-10-01 v2 Systems and Control
Abstract
After providing a brief historical overview on the synergies between artificial intelligence research, in the areas of evolutionary computations and machine learning, and the optimal design of interplanetary trajectories, we propose and study the use of deep artificial neural networks to represent, on-board, the optimal guidance profile of an interplanetary mission. The results, limited to the chosen test case of an Earth-Mars orbital transfer, extend the findings made previously for landing scenarios and quadcopter dynamics, opening a new research area in interplanetary trajectory planning.
Cite
@article{arxiv.1802.00180,
title = {Machine learning and evolutionary techniques in interplanetary trajectory design},
author = {Dario Izzo and Christopher Sprague and Dharmesh Tailor},
journal= {arXiv preprint arXiv:1802.00180},
year = {2018}
}
Comments
Submitted to as a book chapter for a Springer book on "Optimization in Space Engineering"