Maneuvering detection and prediction using inverse reinforcement learning for space situational awareness

Richard Linares, Roberto Furfaro

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

Abstract

This paper uses inverse Reinforcement Learning (RL) to determine the behavior of Space Objects (SOs) by estimating the reward function that an SO is using for control. The approach discussed in this work can be used to analyze maneuvering of SOs from observational data. The inverse RL problem is solved using the feature matching approach. This approach determines the optimal reward function that a SO is using while maneuvering by assuming that the observed trajectories are optimal with respect to the SO’s own reward function. This paper utilizes estimated orbital element data to determine the behavior of SOs in a data-driven fashion. Simple proof-of-concept results are shown for a simulation example.

Original languageEnglish (US)
Title of host publicationASTRODYNAMICS 2017
PublisherUnivelt Inc.
Pages527-536
Number of pages10
Volume162
ISBN (Print)9780877036456
Publication statusPublished - Jan 1 2018
EventAAS/AIAA Astrodynamics Specialist Conference, 2017 - Stevenson, United States
Duration: Aug 20 2017Aug 24 2017

Other

OtherAAS/AIAA Astrodynamics Specialist Conference, 2017
CountryUnited States
CityStevenson
Period8/20/178/24/17

    Fingerprint

ASJC Scopus subject areas

  • Aerospace Engineering
  • Space and Planetary Science

Cite this

Linares, R., & Furfaro, R. (2018). Maneuvering detection and prediction using inverse reinforcement learning for space situational awareness. In ASTRODYNAMICS 2017 (Vol. 162, pp. 527-536). Univelt Inc..