Relative optical navigation around small bodies via extreme learning machines

Roberto Furfaro, Andrew M. Law

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

To perform close proximity operations under a low-gravity environment, relative and absolute position are vital information to the spacecraft maneuver. Hence navigation is inseparably integrated in space travel. This paper presents Extreme Learning Machine (ELM) as an optical navigation method around small celestial bodies. ELM is a Single Layer feed-Forward Network (SLFN), a brand of neural network (NN). The algorithm based on the predicate that input weights and biases can be randomly assigned and does not require back-propagation. The learned model composes of the output weights which can be used to develop into a hypotheses. The proposed method is used to estimate the position of the spacecraft from optical images obtained through a navigation camera. The results show this approach is promising and potentially suitable for on-board navigation.

Original languageEnglish (US)
Title of host publicationAstrodynamics 2015
PublisherUnivelt Inc.
Pages1959-1978
Number of pages20
Volume156
ISBN (Print)9780877036296
StatePublished - 2016
EventAAS/AIAA Astrodynamics Specialist Conference, ASC 2015 - Vail, United States
Duration: Aug 9 2015Aug 13 2015

Other

OtherAAS/AIAA Astrodynamics Specialist Conference, ASC 2015
CountryUnited States
CityVail
Period8/9/158/13/15

Fingerprint

machine learning
navigation
Learning systems
Navigation
Spacecraft
spacecraft maneuvers
spacecraft
celestial bodies
back propagation
microgravity
Backpropagation
travel
proximity
Gravitation
Cameras
cameras
gravity
Neural networks
output
estimates

ASJC Scopus subject areas

  • Aerospace Engineering
  • Space and Planetary Science

Cite this

Furfaro, R., & Law, A. M. (2016). Relative optical navigation around small bodies via extreme learning machines. In Astrodynamics 2015 (Vol. 156, pp. 1959-1978). Univelt Inc..

Relative optical navigation around small bodies via extreme learning machines. / Furfaro, Roberto; Law, Andrew M.

Astrodynamics 2015. Vol. 156 Univelt Inc., 2016. p. 1959-1978.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Furfaro, R & Law, AM 2016, Relative optical navigation around small bodies via extreme learning machines. in Astrodynamics 2015. vol. 156, Univelt Inc., pp. 1959-1978, AAS/AIAA Astrodynamics Specialist Conference, ASC 2015, Vail, United States, 8/9/15.
Furfaro R, Law AM. Relative optical navigation around small bodies via extreme learning machines. In Astrodynamics 2015. Vol. 156. Univelt Inc. 2016. p. 1959-1978
Furfaro, Roberto ; Law, Andrew M. / Relative optical navigation around small bodies via extreme learning machines. Astrodynamics 2015. Vol. 156 Univelt Inc., 2016. pp. 1959-1978
@inproceedings{d9ae43bf4b814694a5aba52329e6103b,
title = "Relative optical navigation around small bodies via extreme learning machines",
abstract = "To perform close proximity operations under a low-gravity environment, relative and absolute position are vital information to the spacecraft maneuver. Hence navigation is inseparably integrated in space travel. This paper presents Extreme Learning Machine (ELM) as an optical navigation method around small celestial bodies. ELM is a Single Layer feed-Forward Network (SLFN), a brand of neural network (NN). The algorithm based on the predicate that input weights and biases can be randomly assigned and does not require back-propagation. The learned model composes of the output weights which can be used to develop into a hypotheses. The proposed method is used to estimate the position of the spacecraft from optical images obtained through a navigation camera. The results show this approach is promising and potentially suitable for on-board navigation.",
author = "Roberto Furfaro and Law, {Andrew M.}",
year = "2016",
language = "English (US)",
isbn = "9780877036296",
volume = "156",
pages = "1959--1978",
booktitle = "Astrodynamics 2015",
publisher = "Univelt Inc.",

}

TY - GEN

T1 - Relative optical navigation around small bodies via extreme learning machines

AU - Furfaro, Roberto

AU - Law, Andrew M.

PY - 2016

Y1 - 2016

N2 - To perform close proximity operations under a low-gravity environment, relative and absolute position are vital information to the spacecraft maneuver. Hence navigation is inseparably integrated in space travel. This paper presents Extreme Learning Machine (ELM) as an optical navigation method around small celestial bodies. ELM is a Single Layer feed-Forward Network (SLFN), a brand of neural network (NN). The algorithm based on the predicate that input weights and biases can be randomly assigned and does not require back-propagation. The learned model composes of the output weights which can be used to develop into a hypotheses. The proposed method is used to estimate the position of the spacecraft from optical images obtained through a navigation camera. The results show this approach is promising and potentially suitable for on-board navigation.

AB - To perform close proximity operations under a low-gravity environment, relative and absolute position are vital information to the spacecraft maneuver. Hence navigation is inseparably integrated in space travel. This paper presents Extreme Learning Machine (ELM) as an optical navigation method around small celestial bodies. ELM is a Single Layer feed-Forward Network (SLFN), a brand of neural network (NN). The algorithm based on the predicate that input weights and biases can be randomly assigned and does not require back-propagation. The learned model composes of the output weights which can be used to develop into a hypotheses. The proposed method is used to estimate the position of the spacecraft from optical images obtained through a navigation camera. The results show this approach is promising and potentially suitable for on-board navigation.

UR - http://www.scopus.com/inward/record.url?scp=85007336458&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85007336458&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85007336458

SN - 9780877036296

VL - 156

SP - 1959

EP - 1978

BT - Astrodynamics 2015

PB - Univelt Inc.

ER -