Skip to main navigation Skip to search Skip to main content

Reinforcement Learning Based Spacecraft Autonomous Evasive Maneuvers Method against Multi-interceptors

  • School of Astronautics, Harbin Institute of Technology
  • China Aerospace Science and Technology Corporation

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper proposed an autonomous intelligent decision-making method, which can be used to evade the attack of multi-interceptors. A self-learning model based on MADDPG algorithm is established with four engines of a spacecraft as multi-agent system. The model takes the relative distance and the total maneuvering time as variables to design the evaluation function. A simulation environment is constructed with four interceptors intercepting a spacecraft at the same time. The autonomous evasion impulse maneuvers of the spacecraft are realized by training. Compared with the random evasion maneuvers method, this autonomous maneuvers method improves the success probability of escape by nearly 30%. This research provides a valuable theoretical method for modern space operations.

Original languageEnglish
Title of host publicationProceedings of 2020 3rd International Conference on Unmanned Systems, ICUS 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1108-1113
Number of pages6
ISBN (Electronic)9781728180250
DOIs
StatePublished - 27 Nov 2020
Externally publishedYes
Event3rd International Conference on Unmanned Systems, ICUS 2020 - Harbin, China
Duration: 27 Nov 202028 Nov 2020

Publication series

NameProceedings of 2020 3rd International Conference on Unmanned Systems, ICUS 2020

Conference

Conference3rd International Conference on Unmanned Systems, ICUS 2020
Country/TerritoryChina
CityHarbin
Period27/11/2028/11/20

Keywords

  • Evasive maneuvers
  • Intelligent decision-making
  • Multi-agents
  • Multi-interceptors
  • Self-learning model

Fingerprint

Dive into the research topics of 'Reinforcement Learning Based Spacecraft Autonomous Evasive Maneuvers Method against Multi-interceptors'. Together they form a unique fingerprint.

Cite this