A DNN based trajectory optimization method for intercepting non-cooperative maneuvering spacecraft

doi:10.23919/JSEE.2022.000044

Journal of Systems Engineering and Electronics ›› 2022, Vol. 33 ›› Issue (2): 438-446.doi: 10.23919/JSEE.2022.000044

收稿日期:2020-11-30 出版日期:2022-05-06 发布日期:2022-05-06

A DNN based trajectory optimization method for intercepting non-cooperative maneuvering spacecraft

Fuyunxiang YANG(), Leping YANG(), Yanwei ZHU*(), Xin ZENG()

¹ College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China

Received:2020-11-30 Online:2022-05-06 Published:2022-05-06
Contact: Yanwei ZHU E-mail:yfyxgood@hotmail.com;ylp_1964@163.com;zywnudt@163.com;xzavier0214@outlook.com
About author:|YANG Fuyunxiang was born in 1996. He received his B.S. degree from National University of Defense Technology (NUDT), Changsha, China, in 2018. He is a Ph.D. candidate with the College of Aeronautics and Astronautics, NUDT. His research interests include aerospace dynamics, guidance and control, application of artificial intelligence to the control of astronautic systems.E-mail: yfyxgood@hotmail.com||YANG Leping was born in 1964. He received his B.S. and M.S. degrees from National University of Defense Technology (NUDT), Changsha, China, in 1984 and 1987, respectively. He is a professor with the College of Aeronautics and Astronautics, NUDT. His research interests include aerospace dynamics, guidance and control, astronautic mission planning and design.E-mail: ylp_1964@163.com||ZHU Yanwei was born in 1981. He received his B.S., M.S., and Ph.D. degrees from National University of Defense Technology (NUDT), Changsha, China, in 2002, 2004 and 2009, respectively. He is an associate professor with the College of Aeronautics and Astronautics, NUDT. His research interests include aerospace dynamics, guidance and control, astronautic mission planning and design.E-mail: zywnudt@163.com||ZENG Xin was born in 1992. He received his B.S. and M.S. degrees from National University of Defense Technology (NUDT), Changsha, China, in 2014 and 2016, respectively. He is a Ph.D. candidate with the College of Aeronautics and Astronautics, NUDT. His research interests include aerospace dynamics, guidance and control, application of artificial intelligence to the control of astronautic systems.E-mail: xzavier0214@outlook.com
Supported by:
This work was supported by the National Defense Science and Technology Innovation (18-163-15-Lz-001-004-13)

摘要/Abstract

Abstract:

Current successes in artificial intelligence domain have revitalized interest in neural networks and demonstrated their potential in solving spacecraft trajectory optimization problems. This paper presents a data-free deep neural network (DNN) based trajectory optimization method for intercepting non-cooperative maneuvering spacecraft, in a continuous low-thrust scenario. Firstly, the problem is formulated as a standard constrained optimization problem through differential game theory and minimax principle. Secondly, a new DNN is designed to integrate interception dynamic model into the network and involve it in the process of gradient descent, which makes the network endowed with the knowledge of physical constraints and reduces the learning burden of the network. Thus, a DNN based method is proposed, which completely eliminates the demand of training datasets and improves the generalization capacity. Finally, numerical results demonstrate the feasibility and efficiency of our proposed method.

Key words: non-cooperative maneuvering spacecraft, neural network, differential game, trajectory optimization

. [J]. Journal of Systems Engineering and Electronics, 2022, 33(2): 438-446.

Fuyunxiang YANG, Leping YANG, Yanwei ZHU, Xin ZENG. A DNN based trajectory optimization method for intercepting non-cooperative maneuvering spacecraft[J]. Journal of Systems Engineering and Electronics, 2022, 33(2): 438-446.

图/表 11

参考文献 23

1	SHEN H C, LORENZO C Revisit of the three-dimensional orbital pursuit-evasion game. Journal of Guidance, Control and Dynamics, 2018, 41 (8): 1820- 1828.
2	ZHAI G, BI X Z, ZHAO H Y, et al Non-cooperative maneuvering spacecraft tracking via a variable structure estimator. Aerospace Science and Technology, 2018, 79, 352- 363. doi: 10.1016/j.ast.2018.05.052
3	HU Q L, LIU Y Y, ZHANG Y M Control of non-cooperative spacecraft in final phase proximity operations under input constraints. Control Engineering Practice, 2019, 87, 83- 96. doi: 10.1016/j.conengprac.2019.04.001
4	PONTANI M, CONWAY B A Numerical solution of the three-dimensional orbital pursuit-evasion game. Journal of Guidance, Control and Dynamics, 2009, 32 (2): 474- 487. doi: 10.2514/1.37962
5	BASAR T, OLSDER G J. Dynamic noncooperative game theory. Philadelphia: Academic Press, 1999.
6	TUOMAS R, HARRI E Visual aircraft identification as a pursuit-evasion game. Journal of Guidance, Control and Dynamics, 2000, 23 (4): 701- 708. doi: 10.2514/2.4586
7	STUPIK J, PONTANI M, CONWAY B A. Optimal pursuit/evasion spacecraft trajectories in the Hill reference frame. Proc. of the AIAA/AAS Astrodynamics Specialist Conference, 2012. DOI: 10.2514/6.2012-4882.
8	LI Z Y, ZHU H, YANG Z, et al A dimension-reduction solution of free-time differential games for spacecraft pursuit-evasion. Acta Astronautica, 2019, 163, 201- 210. doi: 10.1016/j.actaastro.2019.01.011
9	HORIE K, CONWAY B A. Optimal fighter pursuit-evasion maneuvers found via two-sided optimization. Journal of Guidance, Control and Dynamics, 2006, 29(1): 105–112.
10	SUN S T, ZHANG Q H, LOXTON R, et al Numerical solution of a pursuit-evasion differential game involving two spacecraft in low earth orbit. Journal of Industrial and Management Optimization, 2015, 11 (4): 1127- 1147. doi: 10.3934/jimo.2015.11.1127
11	SANCHEZ-SANCHEZ C, IZZO D, HENNES D. Learning the optimal state-feedback using deep networks. Proc. of the IEEE Symposium Series on Computational Intelligence Conference, 2016. DOI: 10.1109/SSCI.2016.7850105.
12	WU Q C, LI B, LI J, et al Solution of infinite time domain spacecraft pursuit strategy based on deep neural network. Aerospace Control, 2019, 37 (6): 13- 18,58.
13	GEORGE B C. Optimal and robust neural network controllers for proximal spacecraft maneuvers. Wright-Patterson Air Force Base, America: Air Force Institute of Technology, 2019.
14	ULYANOV D, VEDALDI A, LEMPITSKY V Deep image prior. International Journal of Computer Vision, 2020, 128 (7): 1867- 1888. doi: 10.1007/s11263-020-01303-4
15	AZADI S, FISHER M, KIM V, et al Multi-content GAN for few-shot font style transfer. Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, 7564- 7573.
16	DITTMER S, KLUTH T, MAASS P, et al Regularization by architecture: a deep prior approach for inverse problems. Journal of Mathematical Imaging and Vision, 2019, 62, 456- 470.
17	LONG Z C, LU Y P, DONG B PDE-Net 2. 0:learning PDEs from data with a numeric-symbolic hybrid deep network. Journal of Computational Physics, 2019, 399, 108- 125.
18	ZHU Y H, ZABARAS N, KOUTSOURELAKIS P S, et al Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data. Journal of Computational Physics, 2019, 394, 56- 81. doi: 10.1016/j.jcp.2019.05.024
19	HOYER S, SOHL-DICKSTEIN J, GREYDANUS S. Neural reparameterization improves structural optimization. https://arxiv.org/abs/1909.04240.
20	CHOI H L, HYEOK R, TAHK M J, et al A co-evolutionary method for pursuit-evasion games with non-zero lethal radii. Engineering Optimization, 2004, 36 (1): 19- 36. doi: 10.1080/03052150310001634862
21	ISAACS R. Differential games. New York: Wiley, 1965.
22	FRIEDMAN A. Differential games. Rhode Island: American Mathematical Society, 1974.
23	YANG H W, LI J Y, BAOYIN H X Low-cost transfer between asteroids with distant orbits using multiple gravity assists. Advances in Space Research, 2015, 56 (5): 837- 847. doi: 10.1016/j.asr.2015.05.013

ID	x/km	y/km	z/km	$\dot x $ /(m/s)	$\dot y $ /(m/s)	$\dot z $ /(m/s)
Target	?33.8	?50.4	6.7	2.0	4.9	0.0
Pursuer	0.0	0.0	0.0	0.0	0.0	0.0

ID	Relative distance/km	Relative velocity/(m/s)
Target	$ \sqrt {{x^2} + {y^2} + {z^2}} \leqslant 100 $	$ \sqrt {v_x^2 + v_y^2 + v_z^2} \leqslant 10 $
Pursuer	$ \sqrt {{x^2} + {y^2} + {z^2}} \leqslant 100 $	$ \sqrt {v_x^2 + v_y^2 + v_z^2} \leqslant 10 $

Method name	Dataset	${n_s}$ in Case 1?Case 7	${n_s}$ in Case 8?Case 10	${r_s}/{\text{%} }$
Method 1	500	3	0	30
Method 2	–	7	3	100

A DNN based trajectory optimization method for intercepting non-cooperative maneuvering spacecraft

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 23

相关文章 0

编辑推荐

Metrics

本文评价