Spacecraft detection avoidance maneuver optimization using reinforcement learning

Jason A. Reiter, David B. Spencer, Richard Linares

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

Abstract

Spacecraft maneuvers are planned with operational objectives in mind, usually ranging from making up for orbit perturbations to maneuvering to avoid a possible collision. Though these areas have been researched in depth, little work has been done exploring maneuvers performed to avoid detection by sensors. This paper explores the optimization of detection avoidance maneuvers using reinforcement learning. Numerical transcription is used for comparison purposes, but the open-loop nature of optimal control is not conducive to solving the entirety of the detection avoidance problem. Reinforcement learning produces reliable results for maneuver optimization which will provide a unique alternative for maneuver planning.

Original languageEnglish (US)
Title of host publicationSpaceflight Mechanics 2019
EditorsFrancesco Topputo, Andrew J. Sinclair, Matthew P. Wilkins, Renato Zanetti
PublisherUnivelt Inc.
Pages3055-3069
Number of pages15
ISBN (Print)9780877036593
StatePublished - Jan 1 2019
Event29th AAS/AIAA Space Flight Mechanics Meeting, 2019 - Maui, United States
Duration: Jan 13 2019Jan 17 2019

Publication series

NameAdvances in the Astronautical Sciences
Volume168
ISSN (Print)0065-3438

Conference

Conference29th AAS/AIAA Space Flight Mechanics Meeting, 2019
CountryUnited States
CityMaui
Period1/13/191/17/19

Fingerprint

avoidance
Reinforcement learning
maneuvers
reinforcement
learning
Spacecraft
spacecraft
optimization
Transcription
Orbits
spacecraft maneuvers
orbit perturbation
Planning
Sensors
optimal control
collision
perturbation
sensor
planning
collisions

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering
  • Space and Planetary Science

Cite this

Reiter, J. A., Spencer, D. B., & Linares, R. (2019). Spacecraft detection avoidance maneuver optimization using reinforcement learning. In F. Topputo, A. J. Sinclair, M. P. Wilkins, & R. Zanetti (Eds.), Spaceflight Mechanics 2019 (pp. 3055-3069). [AAS 19-506] (Advances in the Astronautical Sciences; Vol. 168). Univelt Inc..
Reiter, Jason A. ; Spencer, David B. ; Linares, Richard. / Spacecraft detection avoidance maneuver optimization using reinforcement learning. Spaceflight Mechanics 2019. editor / Francesco Topputo ; Andrew J. Sinclair ; Matthew P. Wilkins ; Renato Zanetti. Univelt Inc., 2019. pp. 3055-3069 (Advances in the Astronautical Sciences).
@inproceedings{49817d848872486294bdf4864c62eb62,
title = "Spacecraft detection avoidance maneuver optimization using reinforcement learning",
abstract = "Spacecraft maneuvers are planned with operational objectives in mind, usually ranging from making up for orbit perturbations to maneuvering to avoid a possible collision. Though these areas have been researched in depth, little work has been done exploring maneuvers performed to avoid detection by sensors. This paper explores the optimization of detection avoidance maneuvers using reinforcement learning. Numerical transcription is used for comparison purposes, but the open-loop nature of optimal control is not conducive to solving the entirety of the detection avoidance problem. Reinforcement learning produces reliable results for maneuver optimization which will provide a unique alternative for maneuver planning.",
author = "Reiter, {Jason A.} and Spencer, {David B.} and Richard Linares",
year = "2019",
month = "1",
day = "1",
language = "English (US)",
isbn = "9780877036593",
series = "Advances in the Astronautical Sciences",
publisher = "Univelt Inc.",
pages = "3055--3069",
editor = "Francesco Topputo and Sinclair, {Andrew J.} and Wilkins, {Matthew P.} and Renato Zanetti",
booktitle = "Spaceflight Mechanics 2019",
address = "United States",

}

Reiter, JA, Spencer, DB & Linares, R 2019, Spacecraft detection avoidance maneuver optimization using reinforcement learning. in F Topputo, AJ Sinclair, MP Wilkins & R Zanetti (eds), Spaceflight Mechanics 2019., AAS 19-506, Advances in the Astronautical Sciences, vol. 168, Univelt Inc., pp. 3055-3069, 29th AAS/AIAA Space Flight Mechanics Meeting, 2019, Maui, United States, 1/13/19.

Spacecraft detection avoidance maneuver optimization using reinforcement learning. / Reiter, Jason A.; Spencer, David B.; Linares, Richard.

Spaceflight Mechanics 2019. ed. / Francesco Topputo; Andrew J. Sinclair; Matthew P. Wilkins; Renato Zanetti. Univelt Inc., 2019. p. 3055-3069 AAS 19-506 (Advances in the Astronautical Sciences; Vol. 168).

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

TY - GEN

T1 - Spacecraft detection avoidance maneuver optimization using reinforcement learning

AU - Reiter, Jason A.

AU - Spencer, David B.

AU - Linares, Richard

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Spacecraft maneuvers are planned with operational objectives in mind, usually ranging from making up for orbit perturbations to maneuvering to avoid a possible collision. Though these areas have been researched in depth, little work has been done exploring maneuvers performed to avoid detection by sensors. This paper explores the optimization of detection avoidance maneuvers using reinforcement learning. Numerical transcription is used for comparison purposes, but the open-loop nature of optimal control is not conducive to solving the entirety of the detection avoidance problem. Reinforcement learning produces reliable results for maneuver optimization which will provide a unique alternative for maneuver planning.

AB - Spacecraft maneuvers are planned with operational objectives in mind, usually ranging from making up for orbit perturbations to maneuvering to avoid a possible collision. Though these areas have been researched in depth, little work has been done exploring maneuvers performed to avoid detection by sensors. This paper explores the optimization of detection avoidance maneuvers using reinforcement learning. Numerical transcription is used for comparison purposes, but the open-loop nature of optimal control is not conducive to solving the entirety of the detection avoidance problem. Reinforcement learning produces reliable results for maneuver optimization which will provide a unique alternative for maneuver planning.

UR - http://www.scopus.com/inward/record.url?scp=85072991921&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072991921&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85072991921

SN - 9780877036593

T3 - Advances in the Astronautical Sciences

SP - 3055

EP - 3069

BT - Spaceflight Mechanics 2019

A2 - Topputo, Francesco

A2 - Sinclair, Andrew J.

A2 - Wilkins, Matthew P.

A2 - Zanetti, Renato

PB - Univelt Inc.

ER -

Reiter JA, Spencer DB, Linares R. Spacecraft detection avoidance maneuver optimization using reinforcement learning. In Topputo F, Sinclair AJ, Wilkins MP, Zanetti R, editors, Spaceflight Mechanics 2019. Univelt Inc. 2019. p. 3055-3069. AAS 19-506. (Advances in the Astronautical Sciences).