Single Agent On-Orbit Inspection: Energy-Awareness, Data Down-linking and Orbital Exploration via Deep-Q-Learning
Augustin DAY, Francesco Paolo SALZO, Gabriele GEMIGNANI, Stéphanie LIZY-DESTREZ, Giordana BUCCHIONI
Abstract. The increasing demand for autonomous space operations motivates lightweight AI-based approaches to Resident Space Objects (RSO) inspection, where spacecraft must balance trajectory optimization with strict onboard resource limitations in real-time. This paper presents a Deep Q-Network (DQN) for single-agent RSO inspection, combining fuel-efficient orbital exploration with battery management and data down-linking in a unified control policy. The environment features a discrete set of relative orbits, stochastic resource dynamics, and a closed-loop transfer method based on Relative Orbital Elements (ROEs). Results show how, across multiple training runs, the agent learns to accomplish the mission with a low number of transfers while efficiently handling battery and data processes.
Keywords
On-Orbit Inspection, Reinforcement Learning, Task Scheduling
Published online 7/20/2026, 6 pages
Copyright © 2026 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Augustin DAY, Francesco Paolo SALZO, Gabriele GEMIGNANI, Stéphanie LIZY-DESTREZ, Giordana BUCCHIONI, Single Agent On-Orbit Inspection: Energy-Awareness, Data Down-linking and Orbital Exploration via Deep-Q-Learning, Materials Research Proceedings, Vol. 69, pp 902-907, 2026
DOI: https://doi.org/10.21741/9781644904251-159
The article was published as article 159 of the book CEAS – AIDAA Conference 2025
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] Benjamin Bernhard, Changrak Choi, Amir Rahmani, Soon-Jo Chung, and Fred Hadaegh. Coordinated motion planning for on-orbit satellite inspection using a swarm of small-spacecraft. In 2020 IEEE Aerospace Conference, pages 1–13. IEEE, 2020. https://doi.org/10.1109/AERO47225.2020.9172747
[2] Yashwanth Kumar Nakka, Wolfgang H¨onig, Changrak Choi, Alexei Harvard, Amir Rahmani, and Soon-Jo Chung. Information-based guidance and control architecture for multi-spacecraft on-orbit inspection. Journal of Guidance, Control, and Dynamics, 45(7):1184–1201, 2022. https://doi.org/10.2514/1.G006278
[3] Francesco Capolupo and Pierre Labourdette. Receding-horizon trajectory planning algorithm for passively safe on-orbit inspection missions. Journal of Guidance, Control, and Dynamics, 42(5):1023–1032, 2019. https://doi.org/10.2514/1.G003736
[4] Jian Wu, Yuning Chen, Yongming He, Lining Xing, and Yangrui Hu. Survey on autonomous task scheduling technology for earth observation satellites. Journal of Systems Engineering and Electronics, 33(6):1176–1189, 2022. 10.23919/JSEE.2022.000141
[5] Xiaoyu Chen, Gerhard Reinelt, Guangming Dai, and Andreas Spitz. A mixed integer linear programming model for multi-satellite scheduling. European Journal of Operational Research, 275(2):694–707, 2019. https://doi.org/10.1016/j.ejor.2018.11.058
[6] Adam Herrmann and Hanspeter Schaub. Reinforcement learning for the agile earth-observing satellite scheduling problem. IEEE Transactions on Aerospace and Electronic Systems, 59(5):5235–5247, 2023. 10.1109/TAES.2023.3251307
[7] Qingyu Qu, Kexin Liu, Wei Wang, and Jinhu L¨u. Spacecraft proximity maneuvering and rendezvous with collision avoidance based on reinforcement learning. IEEE Transactions on Aerospace and Electronic Systems, 58(6):5823–5834, 2022. 10.1109/TAES.2022.3180271
[8] WH Clohessy and RS Wiltshire. Terminal guidance system for satellite rendezvous. Journal of the aerospace sciences, 27(9):653–658, 1960. https://doi.org/10.2514/8.8704
[9] Sylvain Renevey and David A Spencer. Establishment and control of spacecraft formations using artificial potential functions. Acta Astronautica, 162:314–326, 2019. https://doi.org/10.1016/j.actaastro.2019.06.024
[10] T. A. Lovell, D. A Spencer. Relative orbital elements formulation based upon the clohessy-wiltshire equations. The Journal of the Astronautical Sciences, 61(4):341–366, 2014. https://doi.org/10.1007/s40295-014-0029-6
[11] Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A Rusu, Joel Veness, Marc G Bellemare, Alex Graves, Martin Riedmiller, Andreas K Fidjeland, Georg Ostrovski, et al. Human-level control through deep reinforcement learning. nature, 518(7540):529–533, 2015. https://doi.org/10.1038/nature14236
