Autonomous artificial neural network star tracker for spacecraft attitude determination

Aaron J. Trask, Victoria Coverstone

Research output: Contribution to journalConference article

1 Citation (Scopus)

Abstract

An artificial neural network based autonomous star tracker prototype for precise spacecraft attitude determination is developed. A new technique of star pattern encoding that removes the star magnitude dependency is presented. The convex hull technique is developed in which the stars in the field of view are treated as a set of points. The convex hull of these points is found and stored as line segments and interior angles moving clockwise from the shortest segment. This technique does not depend on star magnitudes and allows a varying number of stars to be identified and used in calculating the attitude quaternion. This technique combined with feed-forward neural network pattern identification creates a robust and fast technique for solving the "lost-in-space" problem. Night sky testing is used to validate a system consisting of a charged-coupled-device-based camera head unit and integrated control hardware and software. The artificial neural network star pattern match algorithm utilizes a sub catalog of the SKY2000 star catalog. The experimental results are real time comparisons of the star tracker observed motion with the rotational motion of the Earth. The time required to solve the "lost-in-space" problem for this star tracker prototype is on average 9.5 seconds.

Original languageEnglish (US)
Pages (from-to)1317-1336
Number of pages20
JournalAdvances in the Astronautical Sciences
Volume114 II
StatePublished - Dec 1 2003
Externally publishedYes
EventSpaceflight Mechanics 2003: Proceedings of the AAS/AIAA Space Flight Mechanics Meeting - Ponce, Puerto Rico
Duration: Feb 9 2003Feb 13 2003

Fingerprint

Star trackers
star trackers
hull
artificial neural network
Stars
Spacecraft
spacecraft
Neural networks
stars
field of view
hardware
software
prototypes
night sky
astronomical catalogs
quaternions
Integrated control
Feedforward neural networks
catalogs
coding

ASJC Scopus subject areas

  • Aerospace Engineering
  • Space and Planetary Science

Cite this

Autonomous artificial neural network star tracker for spacecraft attitude determination. / Trask, Aaron J.; Coverstone, Victoria.

In: Advances in the Astronautical Sciences, Vol. 114 II, 01.12.2003, p. 1317-1336.

Research output: Contribution to journalConference article

@article{ea42db416bcd4514b923f95dfce201e4,
title = "Autonomous artificial neural network star tracker for spacecraft attitude determination",
abstract = "An artificial neural network based autonomous star tracker prototype for precise spacecraft attitude determination is developed. A new technique of star pattern encoding that removes the star magnitude dependency is presented. The convex hull technique is developed in which the stars in the field of view are treated as a set of points. The convex hull of these points is found and stored as line segments and interior angles moving clockwise from the shortest segment. This technique does not depend on star magnitudes and allows a varying number of stars to be identified and used in calculating the attitude quaternion. This technique combined with feed-forward neural network pattern identification creates a robust and fast technique for solving the {"}lost-in-space{"} problem. Night sky testing is used to validate a system consisting of a charged-coupled-device-based camera head unit and integrated control hardware and software. The artificial neural network star pattern match algorithm utilizes a sub catalog of the SKY2000 star catalog. The experimental results are real time comparisons of the star tracker observed motion with the rotational motion of the Earth. The time required to solve the {"}lost-in-space{"} problem for this star tracker prototype is on average 9.5 seconds.",
author = "Trask, {Aaron J.} and Victoria Coverstone",
year = "2003",
month = "12",
day = "1",
language = "English (US)",
volume = "114 II",
pages = "1317--1336",
journal = "Advances in the Astronautical Sciences",
issn = "1081-6003",
publisher = "Univelt Inc.",

}

TY - JOUR

T1 - Autonomous artificial neural network star tracker for spacecraft attitude determination

AU - Trask, Aaron J.

AU - Coverstone, Victoria

PY - 2003/12/1

Y1 - 2003/12/1

N2 - An artificial neural network based autonomous star tracker prototype for precise spacecraft attitude determination is developed. A new technique of star pattern encoding that removes the star magnitude dependency is presented. The convex hull technique is developed in which the stars in the field of view are treated as a set of points. The convex hull of these points is found and stored as line segments and interior angles moving clockwise from the shortest segment. This technique does not depend on star magnitudes and allows a varying number of stars to be identified and used in calculating the attitude quaternion. This technique combined with feed-forward neural network pattern identification creates a robust and fast technique for solving the "lost-in-space" problem. Night sky testing is used to validate a system consisting of a charged-coupled-device-based camera head unit and integrated control hardware and software. The artificial neural network star pattern match algorithm utilizes a sub catalog of the SKY2000 star catalog. The experimental results are real time comparisons of the star tracker observed motion with the rotational motion of the Earth. The time required to solve the "lost-in-space" problem for this star tracker prototype is on average 9.5 seconds.

AB - An artificial neural network based autonomous star tracker prototype for precise spacecraft attitude determination is developed. A new technique of star pattern encoding that removes the star magnitude dependency is presented. The convex hull technique is developed in which the stars in the field of view are treated as a set of points. The convex hull of these points is found and stored as line segments and interior angles moving clockwise from the shortest segment. This technique does not depend on star magnitudes and allows a varying number of stars to be identified and used in calculating the attitude quaternion. This technique combined with feed-forward neural network pattern identification creates a robust and fast technique for solving the "lost-in-space" problem. Night sky testing is used to validate a system consisting of a charged-coupled-device-based camera head unit and integrated control hardware and software. The artificial neural network star pattern match algorithm utilizes a sub catalog of the SKY2000 star catalog. The experimental results are real time comparisons of the star tracker observed motion with the rotational motion of the Earth. The time required to solve the "lost-in-space" problem for this star tracker prototype is on average 9.5 seconds.

UR - http://www.scopus.com/inward/record.url?scp=1542359677&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1542359677&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:1542359677

VL - 114 II

SP - 1317

EP - 1336

JO - Advances in the Astronautical Sciences

JF - Advances in the Astronautical Sciences

SN - 1081-6003

ER -