MULTI-VARIATE GAUSSIAN PROCESS REGRESSION FOR ANGLES-ONLY INITIAL ORBIT DETERMINATION

David Schwab; Puneet Singla; Daning Huang

MULTI-VARIATE GAUSSIAN PROCESS REGRESSION FOR ANGLES-ONLY INITIAL ORBIT DETERMINATION

David Schwab, Puneet Singla, Daning Huang

Aerospace Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Vital for Space Situational Awareness, initial orbit determination is used to initialize object tracking and associate observations with a tracked satellite. These classical IOD algorithms provide only a point solution and have been shown to be sensitive to noisy measurements and to certain target-observer geometry. In this work, a multivariate Gaussian process regression (GPR) is trained to perform angles-only orbit determination. This work extends the GPR approach to accurately quantify the orbit states along with associated covariance. The numerical simulations shows that by accounting for correlations in the outputs, the GPR process provides more accurate estimate of orbit uncertainty.

Original language	English (US)
Title of host publication	ASTRODYNAMICS 2020
Editors	Roby S. Wilson, Jinjun Shan, Kathleen C. Howell, Felix R. Hoots
Publisher	Univelt Inc.
Pages	3077-3096
Number of pages	20
ISBN (Print)	9780877036753
State	Published - 2021
Event	AAS/AIAA Astrodynamics Specialist Conference, 2020 - Virtual, Online Duration: Aug 9 2020 → Aug 12 2020

Publication series

Name	Advances in the Astronautical Sciences
Volume	175
ISSN (Print)	0065-3438

Conference

Conference	AAS/AIAA Astrodynamics Specialist Conference, 2020
City	Virtual, Online
Period	8/9/20 → 8/12/20

All Science Journal Classification (ASJC) codes

Aerospace Engineering
Space and Planetary Science

Cite this

@inproceedings{c6b1b114d1ce48ab9d2d5f505a1aa069,

title = "MULTI-VARIATE GAUSSIAN PROCESS REGRESSION FOR ANGLES-ONLY INITIAL ORBIT DETERMINATION",

abstract = "Vital for Space Situational Awareness, initial orbit determination is used to initialize object tracking and associate observations with a tracked satellite. These classical IOD algorithms provide only a point solution and have been shown to be sensitive to noisy measurements and to certain target-observer geometry. In this work, a multivariate Gaussian process regression (GPR) is trained to perform angles-only orbit determination. This work extends the GPR approach to accurately quantify the orbit states along with associated covariance. The numerical simulations shows that by accounting for correlations in the outputs, the GPR process provides more accurate estimate of orbit uncertainty.",

author = "David Schwab and Puneet Singla and Daning Huang",

year = "2021",

language = "English (US)",

isbn = "9780877036753",

series = "Advances in the Astronautical Sciences",

publisher = "Univelt Inc.",

pages = "3077--3096",

editor = "Wilson, {Roby S.} and Jinjun Shan and Howell, {Kathleen C.} and Hoots, {Felix R.}",

booktitle = "ASTRODYNAMICS 2020",

address = "United States",

}

MULTI-VARIATE GAUSSIAN PROCESS REGRESSION FOR ANGLES-ONLY INITIAL ORBIT DETERMINATION. / Schwab, David; Singla, Puneet ; Huang, Daning.
ASTRODYNAMICS 2020. ed. / Roby S. Wilson; Jinjun Shan; Kathleen C. Howell; Felix R. Hoots. Univelt Inc., 2021. p. 3077-3096 (Advances in the Astronautical Sciences; Vol. 175).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - MULTI-VARIATE GAUSSIAN PROCESS REGRESSION FOR ANGLES-ONLY INITIAL ORBIT DETERMINATION

AU - Schwab, David

AU - Singla, Puneet

AU - Huang, Daning

PY - 2021

Y1 - 2021

N2 - Vital for Space Situational Awareness, initial orbit determination is used to initialize object tracking and associate observations with a tracked satellite. These classical IOD algorithms provide only a point solution and have been shown to be sensitive to noisy measurements and to certain target-observer geometry. In this work, a multivariate Gaussian process regression (GPR) is trained to perform angles-only orbit determination. This work extends the GPR approach to accurately quantify the orbit states along with associated covariance. The numerical simulations shows that by accounting for correlations in the outputs, the GPR process provides more accurate estimate of orbit uncertainty.

AB - Vital for Space Situational Awareness, initial orbit determination is used to initialize object tracking and associate observations with a tracked satellite. These classical IOD algorithms provide only a point solution and have been shown to be sensitive to noisy measurements and to certain target-observer geometry. In this work, a multivariate Gaussian process regression (GPR) is trained to perform angles-only orbit determination. This work extends the GPR approach to accurately quantify the orbit states along with associated covariance. The numerical simulations shows that by accounting for correlations in the outputs, the GPR process provides more accurate estimate of orbit uncertainty.

UR - http://www.scopus.com/inward/record.url?scp=85126235011&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85126235011&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85126235011

SN - 9780877036753

T3 - Advances in the Astronautical Sciences

SP - 3077

EP - 3096

BT - ASTRODYNAMICS 2020

A2 - Wilson, Roby S.

A2 - Shan, Jinjun

A2 - Howell, Kathleen C.

A2 - Hoots, Felix R.

PB - Univelt Inc.

T2 - AAS/AIAA Astrodynamics Specialist Conference, 2020

Y2 - 9 August 2020 through 12 August 2020

ER -

MULTI-VARIATE GAUSSIAN PROCESS REGRESSION FOR ANGLES-ONLY INITIAL ORBIT DETERMINATION

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this