TRENDS IN THE USE OF ARTIFICIAL INTELLIGENCE METHODS IN PLANNING THE TRAJECTORIES OF MULTI-TARGET LOW-ORBIT ACTIVE SPACE DEBRIS REMOVAL MISSIONS

Анотація

Space debris (SD) has become a pressing problem due to the growing number of satellites and rockets launched into space since the beginning of the space age. The space around the Earth is now filled with thousands of operating satellites and SD objects. The greatest danger to operating satellites comes from small SD fragments, whose main source is abandoned large SD objects: defunct satellites, spent rocket stages, and boosters. The increasing frequency of collisions of SD fragments with valuable space objects has stimulated numerous studies devoted to active space debris removal (ASDR). They provide examples of effective multi-target ASDR missions, whose implementation involves complex and expensive maneuvers of automated transfer vehicles (ATV). Multi-target ASDR missions must be economically and technically effective under conditions of a changing environment and changing mission requirements. In multi-target ASDR missions, one or groups of robotic ATVs with high or low thrust propulsion systems move along trajectories from one ASDR object to another, capture them. and remove them from orbit, or attach removal modules to them. ATV trajectories include sequences of orbital transfers for rendezvous with ASDR objects, and they significantly depend on the ballistic schemes of ASDR missions and the ATV propulsion system thrust. The complexity of ATV maneuvers and the scarcity of ASDR mission resources call for systematic planning of ATV trajectories. Moreover, ASDR missions require a high level of autonomy in planning ATV trajectories. Planning the trajectories of multi-target ASDR missions calls for solving complex problems of optimal distribution of ASDR objects between the mission ATVs and single- or multi-criteria problems of choosing optimal ASDR trajectories. Mathematically, the problem of planning the trajectories of multi-target ASDR missions is a time-dependent optimization combinatorial problem of space flight mechanics with discrete and continuous variables.

The goal of this paper is to identify trends in the use of artificial intelligence methods in planning the trajectories of multi-target low-orbit ASDR missions.

The paper presents a comparative analysis of the current trends in and prospects for the use of meta-heuristic and machine learning methods in trajectory planning for multi-target ASDR missions. Promising areas of application for the methods considered are identified. It is shown that a neural network pre-trained using reinforcement learning or deep reinforcement learning methods can be used in autonomous planning of ASDR missions under conditions of a changing environment and changing mission requirements. The novelty of the paper lies in identifying current trends in and prospects for the use of artificial intelligence methods in planning the trajectories of multi-target low-orbit ASDR missions.

REFERENCES

1. Maestrini M., Di Lizia P. Guidance strategy for autonomous inspection of unknown non-cooperative resident space objects. Journal of Guidance, Control and Dynamics. 2022. V. 45. No. 6. Pp. 1126-1136.
https://doi.org/10.2514/1.G006126

2. Cerf M. Multiple space debris collection mission: Optimal mission planning. Journal of Optimization Theory and Applications. 2015. V. 167. No. 1. Pp. 195-218.
https://doi.org/10.1007/s10957-015-0705-0

3. Coello C. Evolutionary multi-objective optimization: a historical view of the field. IEEE Computational Intelligence Magazine. 2006. V. 1. No. 1. Pp. 28-36.
https://doi.org/10.1109/MCI.2006.1597059

4. Baibee B. W., Alfano S., Pinon. E. et. al. Design of spacecraft missions to remove multiple orbital debris objects. Proc. IEEE Aerospace Conference. 2011. Pp. 1-14.
https://doi.org/10.1109/AERO.2011.5747303

5. Zhao J., Feng W., Yuan J. A novel two-level optimization strategy for multi-debris active removal mission in LEO. Computer Modeling in Engineering & Sciences. 2020. V. 122. Pp. 149-174.
https://doi.org/10.32604/cmes.2020.07504

6. Bérend N., Olive X. Bi-objective optimization of a multiple-target active debris removal mission. Acta Astronautica. 2016. V. 122. Pp. 324- 335. https://doi.org/10.1016/j.actaastro.2016.02.005

7. Yu J., Chen X. Q., Chen L.H. Optimal planning of LEO active debris removal based on hybrid optimal control theory. Advances in Space Research. 2015. V. 55. No. 11. Pp. 2628-2640.
https://doi.org/10.1016/j.asr.2015.02.026

8. Zuiani F., Vasile M. Preliminary design of debris removal missions by means of simplified models for low-thrust, many-revolution transfers. J. Aerosp. Eng. 2012. V. 2012. Iss. 1. Art. 836250.
https://doi.org/10.1155/2012/836250

9. Braun V., Liipken A., Flegel S. Active debris removal of multiple priority targets. Adv. Space Res. 2013. V. 51. Iss. 9. Pp. 1638-1648.
https://doi.org/10.1016/j.asr.2012.12.003

10. Zhang N., Zhang Z., Baoyirt H. et. al. An optimization algorithm for solving multiple debris removal missions of the time-dependent traveling salesman problem model. Astrodynamics. 2022. V. 6. Iss. 2. Pp. 219- 234.
https://doi.org/10.1007/s42064-021-0107-z

11. Haiyang L., Shiyu C., Hexi B. J2-Perturbed multitarget rendezvous optimization with low thrust. Guid. Control Dyn. 2018. V. 41. No. 3. Pp.796-803.
https://doi.org/10.2514/1.G002889

12. Olympio J., Frouvelle N. Space debris selection and optimal guidance for removal in the SSO with low-thrust propulsion. Acta Astronautica. 2014. V .99. Pp. 263-275.
https://doi.org/10.1016/j.actaastro.2014.03.005

13. Barea A., Urrutxua H., Cadarso L. Large-scale object selection and trajectory planning for multi-target space debris removal missions. Acta Astronautica. 2020. V. 170. Pp. 289-301.
https://doi.org/10.1016/j.actaastro.2020.01.032

14. Madakat D., Morio J., Vanderpooten D. Biobjective planning of an active debris removal mission. Acta Astronautica. 2013. V. 84. Pp. 182-188.
https://doi.org/10.1016/j.actaastro.2012.10.038

15. Forrest S. Genetic algorithms. ACM. Comput. Surv. (CSUR). 1996. V. 28. Iss. 1. Pp. 77-80.
https://doi.org/10.1145/234313.234350

16. Laarhoven P., Aarts E. Simulated annealing. Theory and Applications. Mathematics and Its Applications. 1987. 187 pp. URL: https://link.springer.com/book/10.1007/978-94-015-7744-1 (Last accessed on July 16, 2026).

17. Eberhart R., Kennedy J. A new optimizer, using particle swarm theory. Proceedings of the Sixth International Symposium on Micro Machine and Human Science, Nagoya, Japan, 4-6 October 1995. Pp. 39-43.
https://doi.org/10.1109/MHS.1995.494215

18. Dorigo, M., Maniezzo, V., Colorni A. Ant system: Optimization by a colony of cooperating agents. IEEE Trans. SMC-Part B. 1996. V. 26. Pp. 29-41.
https://doi.org/10.1109/3477.484436

19. Chen Y., Bai Y. Optimal mission planning of active space debris removal based on genetic algorithm. lOP Conf. Ser. Mater. Sci. 2020. V. 715. Art. 012025.
https://doi.org/10.1088/1757-899X/715/1/012025

20. Mohammadi-Dehabadi A., Daneshjou K.. Bakhtiari M. Mission planning for on-orbit servicing through multiple servicing satellites: A new approach. Adv. Space Res. 2017. V. 60. Pp. 1148-1162.
https://doi.org/10.1016/j.asr.2017.05.037

21. Stuart J., Howell K., Wilson R. Application of multi-agent coordination methods to the design of space debris mitigation tours. Adv. Space Res. 2015. V. 57. Pp. 911-928.
https://doi.org/10.1016/j.asr.2015.05.002

22. Shen H. X., Zhang T., Casalino L. et. al. Optimization of active debris removal missions with multiple targets. Space and Rocket. 2018. V. 55. Iss. 1. Pp. 181-189.
https://doi.org/10.2514/1.A33883

23. Snelling D., Devereux E., Payne N. et. al. Innovation in planning space debris removal missions using artificial intelligence and quantum-inspired computing. 8th European Conference on Space Debris. 2021. Pp. 20-23. URL: https://www.researchgate.net/publication/351023286_Innovation_in_planning_space_debris_removal_missions_using_artificial_intelligence_and_quantum-inspired_computing (Last accessed on July 16, 2026).

24. Yang J., Hou X., Hen Hu Yu. et al. A reinforcement learning scheme for active multi-debris removal mission planning with modified upper confidence bound tree search. IEEE Access. 2020. V. 8. Pp.108461-108473. https://doi.org/10.1109/ACCESS.2020.3001311

25. Wang Z., Chen C., Li X. et al. A novel incremental learning scheme for reinforcement learning in dynamic environments. Proc. 12-th World Congr. Intel. Control Automat. 2016. Pp. 2426-2431.
https://doi.org/10.1109/WCICA.2016.7578530

26. Yingjie X., Xiaolu L., Renjie H. et. al. Active debris removal mission planning method based on machine learning. Mathematics. 2023. V. 11. Iss. 6. Art. 1419. https://doi.org/10.3390/math11061419

27. Tomanek-Volynets E., Ceriotti M., Mcinnes C. et. al. Optimization with deep reinforcement learning. Astronautical Congress (IAC2024). 2024. Pp. 1432-1442. https://doi.org/10.52202/078368-0123