CaltechAUTHORS
  A Caltech Library Service

Advances in Deep Space Exploration via Simulators & Deep Learning

Bird, James and Petzold, Linda and Lubin, Philip and Deacon, Julia (2021) Advances in Deep Space Exploration via Simulators & Deep Learning. New Astronomy, 84 . Art. No. 101517. ISSN 1384-1076. https://resolver.caltech.edu/CaltechAUTHORS:20201006-102117215

[img] PDF - Accepted Version
See Usage Policy.

1691Kb
[img] PDF - Submitted Version
See Usage Policy.

1404Kb
[img] XML - Supplemental Material
See Usage Policy.

249b

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20201006-102117215

Abstract

The NASA Starlight and Breakthrough Starshot programs conceptualize fast interstellar travel via small relativistic spacecraft that are propelled by directed energy. This process is radically different from traditional space travel and trades large and slow spacecraft for small, fast, inexpensive, and fragile ones. The main goal of these wafer satellites is to gather useful images during their deep space journey. We introduce and solve some of the main problems that accompany this concept. First, we need an object detection system that can detect planets that we have never seen before, some containing features that we may not even know exist in the universe. Second, once we have images of exoplanets, we need a way to take these images and rank them by importance. Equipment fails and data rates are slow, thus we need a method to ensure that the most important images to humankind are the ones that are prioritized for data transfer. Finally, the energy on board is minimal and must be conserved and used sparingly. No exoplanet images should be missed, but using energy erroneously would be detrimental. We introduce simulator-based methods that leverage artificial intelligence, mostly in the form of computer vision, in order to solve all three of these issues. Our results confirm that simulators provide an extremely rich training environment that surpasses that of real images, and can be used to train models on features that have yet to be observed by humans. We also show that the immersive and adaptable environment provided by the simulator, combined with deep learning, lets us navigate and save energy in an otherwise implausible way.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1016/j.newast.2020.101517DOIArticle
https://arxiv.org/abs/2002.04051arXivDiscussion Paper
ORCID:
AuthorORCID
Petzold, Linda0000-0001-6251-6078
Additional Information:© 2020 Published by Elsevier B.V. Received 8 June 2020, Revised 20 August 2020, Accepted 2 October 2020, Available online 2 October 2020. PML gratefully acknowledges funding from NASA NIAC NNX15AL91G and NASA NIAC NNX16AL32G for the NASA Starlight program and the NASA California Space Grant NASA NNX10AT93H, a generous gift from the Emmett and Gladys W. Technology Fund, as well as support from the Breakthrough Foundation for its Breakthrough Star Shot program. More details on the NASA Starlight program can be found at http://www.deepspace.ucsb.edu/Starlight. Declaration of Competing Interest: The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: NASA NIAC NNX15AL91G and NASA NIAC NNX16AL32G for the NASA Starlight program and the NASA California Space Grant NASA NNX10AT93H, a generous gift from the Emmett and Gladys W. Technology Fund, as well as support from the Breakthrough Foundation for its Break-through Star Shot program.More details on the NASA Starlight program can be found at http://www.deepspace.ucsb.edu/Starlight.
Funders:
Funding AgencyGrant Number
NASANNX15AL91G
NASANNX16AL32G
NASANNX10AT93H
Emmett and Gladys W. Technology FundUNSPECIFIED
Breakthrough FoundationUNSPECIFIED
Subject Keywords:computer vision; simulator; deep learning; space; universe; exoplanet; object detection; novelty detection
Record Number:CaltechAUTHORS:20201006-102117215
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20201006-102117215
Official Citation:James Bird, Linda Petzold, Philip Lubin, Julia Deacon, Advances in deep space exploration via simulators & deep learning, New Astronomy, Volume 84, 2021, 101517, ISSN 1384-1076, https://doi.org/10.1016/j.newast.2020.101517. (http://www.sciencedirect.com/science/article/pii/S1384107620302219)
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:105835
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:07 Oct 2020 00:23
Last Modified:20 Oct 2020 17:21

Repository Staff Only: item control page