Skip to main content

ORIGINAL RESEARCH article

Front. Robot. AI
Sec. Space Robotics
Volume 11 - 2024 | doi: 10.3389/frobt.2024.1402846
This article is part of the Research Topic AI-based Techniques for the Guidance Navigation and Control (GNC) System of Spacecraft and Surface, Aerial and Underwater Vehicles View all articles

Adaptive Satellite Attitude Control for Varying Masses Using Deep Reinforcement Learning

Provisionally accepted
Wiebke Retagne Wiebke Retagne *Jonas Dauer Jonas Dauer Günther Waxenegger-Wilfing Günther Waxenegger-Wilfing *
  • German Aerospace Center (DLR), Hardthausen, Germany

The final, formatted version of the article will be published soon.

    Traditional spacecraft attitude control often relies heavily on the dimension and mass information of the spacecraft. In Active Debris Removal scenarios these characteristics cannot be known beforehand, since the debris can take any shape or mass. Additionally, it is not possible to measure the mass of the combined system of satellite and debris object in orbit. Therefore, it is crucial to develop an adaptive satellite attitude control that can extract mass information of the satellite from other measurements. The authors propose using Deep Reinforcement Learning (DRL) algorithms, employing stacked observations to handle widely varying masses. The satellite is simulated in the Basilisk Software and the control performance is assessed using Monte Carlo simulations. The results demonstrate the benefits of DRL with stacked observations in comparison to a classical PID controller for the spacecraft attitude control. The algorithm is able to adapt, especially in scenarios with changing physical properties.

    Keywords: Attitude control, deep reinforcement learning, Adaptive control, Spacecraft dynamics, Varying masses, space debris, Active debris removal

    Received: 18 Mar 2024; Accepted: 30 May 2024.

    Copyright: © 2024 Retagne, Dauer and Waxenegger-Wilfing. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence:
    Wiebke Retagne, German Aerospace Center (DLR), Hardthausen, Germany
    Günther Waxenegger-Wilfing, German Aerospace Center (DLR), Hardthausen, Germany

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.