Generative Adversarial Network Enhanced Adaptive Control for Aerospace Launch Vehicles
DOI:
https://doi.org/10.71222/qw0cd226Keywords:
deep learning, GANs, adaptive control, satellite theoryAbstract
A theoretical analysis of an on-line, autonomously intelligent, adaptive tracking controller for satellites-employing Generative Adversarial Networks (GANs)-is presented. The controller receives real-time sensory data and a scalar performance signal, autonomously refining thruster or attitude-control commands without requiring explicit foreknowledge of the satellite's internal dynamics. By leveraging an adversarial interplay between a generator and a discriminator module, the approach rapidly adapts to evolving orbital conditions and unanticipated disturbances, thus preserving robust tracking accuracy. The underlying on-line learning mechanism enables continuous policy adjustments, obviating the need for extensive offline tuning. Experimental evidence, derived from a representative satellite undergoing maneuvers in a low-Earth-orbit environment, demonstrates the algorithm's capacity to compensate for nonstationary aerodynamic drag and shifting mass distribution while maintaining precise trajectory regulation. This work underscores the viability of GAN-augmented adaptive methods for advanced aerospace applications, offering heightened resilience and efficiency in the face of dynamic mission constraints.References
1. L. Casalino, and D. Pastrone, "Optimal design and control of hybrid rockets for access to space," In 41st AIAA/ASME/SAE/ASEE Joint Propulsion Conference & Exhibit, July, 2005, p. 3547. doi: 10.2514/6.2005-3547
2. Z. Zou, and A. Dutta, "Capacity achieving by diagonal permutation for mu-mimo channels," In GLOBECOM 2023-2023 IEEE Global Communications Conference, December, 2023, pp. 2536-2541. doi: 10.1109/globecom54140.2023.10437159
3. X. Liu, "Fuel-optimal rocket landing with aerodynamic controls," Journal of Guidance, Control, and Dynamics, vol. 42, no. 1, pp. 65-77, 2019. doi: 10.2514/1.g003537
4. B. D. Fried, and J. M. Richardson, "Optimum rocket trajectories," Journal of Applied Physics, vol. 27, no. 8, pp. 955-961, 1956. doi: 10.1063/1.1722521
5. S. Li, L. Gao, J. Wang, C. Che, X. Xiao, J. Cao, and H. R. Karimi, "Information-theoretic graph fusion with vision-language-action model for policy reasoning and dual robotic control," Information Fusion, 2026. doi: 10.1016/j.inffus.2026.104193
6. K. Mo, W. Liu, F. Shen, X. Xu, L. Xu, X. Su, and Y. Zhang, "Precision kinematic path optimization for high-dof robotic manipulators utilizing advanced natural language processing models," In 2024 5th International Conference on Electronic Communication and Artificial Intelligence (ICECAI), May, 2024, pp. 649-654. doi: 10.2139/ssrn.4952757
7. G. Colasurdo, D. Pastrone, and L. Casalino, "Optimal performance of a dual-fuel single-stage rocket," Journal of spacecraft and rockets, vol. 35, no. 5, pp. 667-671, 1998. doi: 10.2514/2.3383
8. Y. Zhang, Q. Chen, L. Gao, R. Liu, L. Chu, K. Mo, and X. Zhang, "Invertible liquid neural network-based learning of inverse kinematics and dynamics for robotic manipulators," Scientific Reports, vol. 15, no. 1, p. 42311, 2025. doi: 10.1038/s41598-025-26422-1
9. D. F. Lawden, "Minimal rocket trajectories," Journal of the American Rocket Society, vol. 23, no. 6, pp. 360-367, 1953.
10. L. P. Kaelbling, M. L. Littman, and A. W. Moore, "Reinforcement learning: A survey," Journal of artificial intelligence research, vol. 4, pp. 237-285, 1996. doi: 10.1613/jair.301
11. Y. Mao, Y. Zhang, and L. Gao, "Liquid-Augmented MPC in Quadrupedal Robot for Disturbance Learning," Electronics, vol. 14, no. 24, p. 4843, 2025. doi: 10.3390/electronics14244843
12. R. S. Sutton, "Integrated architectures for learning, planning, and reacting based on approximating dynamic programming," In Machine learning proceedings 1990, 1990, pp. 216-224. doi: 10.1016/b978-1-55860-141-3.50030-4
13. Z. Zou, X. Wei, X. Tian, G. Chen, A. Dutta, K. Pham, and E. Blasch, "Joint interference cancellation with imperfect csi," In MILCOM 2024-2024 IEEE Military Communications Conference (MILCOM), October, 2024, pp. 1-6. doi: 10.1109/milcom61039.2024.10774048
14. R. Liu, X. Xu, Y. Shen, A. Zhu, C. Yu, T. Chen, and Y. Zhang, "Enhanced detection classification via clustering svm for various robot collaboration task," In 2024 6th International Conference on Communications, Information System and Computer Engineering (CISCE), May, 2024, pp. 1121-1125. doi: 10.1109/cisce62493.2024.10653146
15. R. Kumar, and H. J. Kelley, "Singular optimal atmospheric rocket trajectories," Journal of Guidance, Control, and Dynamics, vol. 11, no. 4, pp. 305-312, 1988. doi: 10.2514/3.20312
16. B. S. Goh, "Optimal singular rocket and aircraft trajectories," In 2008 Chinese Control and Decision Conference, July, 2008, pp. 1531-1536. doi: 10.1109/ccdc.2008.4597574
17. J. S. Haberl, G. Zilbershtein, J. C. Baltazar, C. Mao, A. Ugursal, I. Nelson, and M. Hussain, "Methodology to Develop the Airport Terminal Building Energy Use Intensity (ATB-EUI) Benchmarking Tool (No. ACRP 09-10)," ACRP 09-10), 2015.
18. T. Lew, F. Lyck, and G. Müller, "Chance-constrained optimal altitude control of a rocket," In European Conference for Aeronautics and Space Sciences (EUCASS)., 2019.
19. I. M. Ross, "Space trajectory optimization and L1-optimal control problems," In Elsevier Astrodynamics Series, 2006, pp. 155-.
20. P. Pradhyumna, "A survey of modern deep learning based generative adversarial networks (gans)," In 2022 6th international conference on computing methodologies and communication (ICCMC), March, 2022, pp. 1146-1152. doi: 10.1109/iccmc53470.2022.9753782
21. D. J. Bayley, R. J. Hartfield Jr, J. E. Burkhalter, and R. M. Jenkins, "Design optimization of a space launch vehicle using a genetic algorithm," Journal of Spacecraft and Rockets, vol. 45, no. 4, pp. 733-740, 2008.
22. K. Chudej, H. J. Pesch, M. Wächter, G. Sachs, and F. Le Bras, "Instationary heat-constrained trajectory optimization of a hypersonic space vehicle by ODE-PDE-constrained optimal control," In Variational analysis and aerospace engineering, 2009, pp. 127-144. doi: 10.1007/978-0-387-95857-6_8
23. M. Hausknecht, and P. Stone, "Deep reinforcement learning in parameterized action space," arXiv preprint arXiv:1511.04143, 2015.
24. Z. Zou, I. Amarasekara, and A. Dutta, "Learning to decompose asymmetric channel kernels for generalized eigenwave multiplexing," In IEEE INFOCOM 2024-IEEE Conference on Computer Communications, May, 2024, pp. 1341-1350. doi: 10.1109/infocom52122.2024.10621411
25. B. Ning, F. H. T. Lin, and S. Jaimungal, "Double deep q-learning for optimal execution," Applied Mathematical Finance, vol. 28, no. 4, pp. 361-380, 2021. doi: 10.1080/1350486x.2022.2077783
26. G. Dulac-Arnold, R. Evans, H. van Hasselt, P. Sunehag, T. Lillicrap, J. Hunt, and B. Coppin, "Deep reinforcement learning in large discrete action spaces," arXiv preprint arXiv:1512.07679, 2015.
27. A. Jiang, K. Mo, S. Fujimoto, M. Taylor, S. Kumar, C. Dimitrios, and E. Ruiz, "Maximum solar energy tracking leverage high-DoF robotics system with deep reinforcement learning," In Proceedings of the 2024 International Conference on Industrial Automation and Robotics, October, 2024, pp. 64-69. doi: 10.1145/3707402.3707414
28. L. Casalino, and D. Pastrone, "Optimization of hybrid sounding rockets for hypersonic testing," Journal of Propulsion and Power, vol. 28, no. 2, pp. 405-411, 2012. doi: 10.2514/1.b34218
29. Y. Zhang, R. Liu, Q. Chen, K. Mo, L. Chu, and Z. Kang, "SDARL: Safe Deep Adaptive Representation Learning for High-DoF Non-Linear System Manipulation in Space," IEEE Access, 2025. doi: 10.1109/access.2025.3602449
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Abdulrahman Fahad, Fatemeh Mohammadi, Amir Hussain, Mariam Eissa, Hassan El-Nur, Sara Al-Sabah, Krzysztof Zalewski (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
