人工智能在航天器制导与控制中的应用综述

doi:10.7527/S1000-6893.2020.24201

综述

本期目录 | 过刊浏览 | 高级检索

前一篇 | 后一篇

人工智能在航天器制导与控制中的应用综述

黄旭星¹, 李爽¹, 杨彬¹, 孙盼¹, 刘学文¹, 刘新彦²

1. 南京航空航天大学航天学院, 南京 210016;
2. 北京控制工程研究所, 北京 100190

收稿日期:2020-05-08 修回日期:2020-06-04 发布日期:2020-07-06
通讯作者: 李爽 E-mail:lishuang@nuaa.edu.cn
基金资助:
民用航天技术预先研究项目（D010305）；空间智能控制技术实验室开放基金（HTKJ2019KL502012，KGJZDSYS-2018-11）

Spacecraft guidance and control based on artificial intelligence: Review

HUANG Xuxing¹, LI Shuang¹, YANG Bin¹, SUN Pan¹, LIU Xuewen¹, LIU Xinyan²

1. College of Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China;
2. Beijing Institute of Control Engineering, Beijing 100190, China

Received:2020-05-08 Revised:2020-06-04 Published:2020-07-06
Supported by:
Technology and Industry Bureau of Civil Aerospace "13^th Five-Year" preliminary Research Project (D010305); Funded by Science and Technology on Space Intelligent Control Laboratory (HTKJ2019KL502012,KGJZDSYS-2018-11)

摘要/Abstract

摘要： 航天器制导与控制技术是保障空间任务顺利实施的关键技术之一。当前，动力学模型的强非线性以及参数不确定性制约了高精度姿轨控技术的发展，而系统故障则决定航天器姿轨控的成败。以机器学习为代表的新一代人工智能技术航天器制导控制领域展现了巨大的应用潜力。首先对基于人工智能技术的轨迹制导和姿态控制中的研究发展及应用现状进行归纳，分析航天器轨迹规划、姿态控制、故障诊断以及容错控制技术的发展趋势。然后，从鲁棒轨迹规划、自适应姿态控制、快速故障诊断和自适应容错控制等4个方面总结适用于未来航天任务的航天器姿轨控关键技术。最后，针对智能姿轨控技术的应用所面临的挑战，从姿轨控架构、算法最优性、算法的训练以及技术验证等方面提出相应的发展建议。

关键词: 人工智能, 轨迹制导, 姿态控制, 智能制导, 自适应控制, 故障诊断, 容错控制

Abstract: Spacecraft guidance and control technology is one of the key technologies to ensure successful implementation of space missions. Currently, the strong nonlinearity of dynamic models and the uncertainty of parameters restrict the development of high-precision attitude and orbit control technology, while the system failure determines the success or failure of the spacecraft attitude and orbit control. The new generation of artificial intelligence technology represented by machine learning shows tremendous potential in the field of spacecraft guidance and control. This paper first summarizes the research development and application status of trajectory guidance and attitude control based on artificial intelligence technology, and analyzes the development trend of spacecraft trajectory planning, attitude control, fault diagnosis and fault-tolerant control technology. Then, from the four aspects of robust trajectory planning, adaptive attitude control, rapid fault diagnosis, and adaptive fault tolerance control, the key technologies of spacecraft attitude and orbit control suitable for future space missions are reviewed. Finally, according to the challenges faced by the application of intelligent navigation and control technology, corresponding development suggestions are proposed in terms of strategy construction, algorithm optimality, training and technical verification.

Key words: artificial intelligence, trajectory guidance, attitude control, intelligence guidance, adaptive guidance, fault diagnosis, fault tolerant control

中图分类号:

V448.21

黄旭星, 李爽, 杨彬, 孙盼, 刘学文, 刘新彦. 人工智能在航天器制导与控制中的应用综述[J]. 航空学报, 2021, 42(4): 524201-524201.

HUANG Xuxing, LI Shuang, YANG Bin, SUN Pan, LIU Xuewen, LIU Xinyan. Spacecraft guidance and control based on artificial intelligence: Review[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021, 42(4): 524201-524201.

参考文献

[1] WARWICK G. DARPA leads drive to build trust in AI for aerospace. Aviationweek[EB/OL]. (2019-07-24)[2020-04-03]. https://aviationweek.com/air-transport/darpa-leads-drive-build-trust-ai-aerospace.
[2] SEBASTIANELLI A, DEL ROSSO M P, ULLO S L. Automatic dataset builder for machine learning applications to satellite imagery[DB/OL]. arXiv preprint arXiv:2008.01578, 2020.
[3] IZZO D, MRTENS M, PAN B F. A survey on artificial intelligence trends in spacecraft guidance dynamics and control[J]. Astrodynamics, 2019, 3(4):287-299.
[4] IZZO D, SPRAGUE C I, TAILOR D V. Machine learning and evolutionary techniques in interplanetary trajectory design[M]//Modeling and optimization in space engineering. Cham:Springer, 2019:191-210.
[5] 王伟林. 空间机动飞行器清除碎片任务规划与制导控制技术[D]. 长沙:国防科技大学, 2017:1-17. WANG W L. Mission plan of active debris removal and design of guidance and control techniques applying space maneuver vehicle[D]. Changsha:National University of Defense Technology, 2017:1-17(in Chinese).
[6] 刘付成. 人工智能在航天器控制中的应用[J]. 飞控与探测, 2018, 1(1):30-39. LIU F C. Application of artificial intelligence in spacecraft[J]. Flight Control & Detection, 2018, 1(1):30-39(in Chinese).
[7] XU Y, LUO D, LI D, et al. Target-enclosing affine formation control of two-layer networked spacecraft with collision avoidance[J]. Chinese Journal of Aeronautics, 2019, 32(12):2679-2693.
[8] LI S, SHE Y. Recent advances in contact dynamics and post-capture control for combined spacecraft[J]. Progress in Aerospace Sciences, 2021,120:100678.
[9] 袁利, 黄煌. 空间飞行器智能自主控制技术现状与发展思考[J]. 空间控制技术与应用, 2019, 45(4):7-18. YUAN L, HUANG H. Current trends of spacecraft intelligent autonomous control[J]. Aerospace Control and Application, 2019, 45(4):7-18(in Chinese).
[10] 蔡鹏. 挠性航天器建模与姿态控制系统研究[D]. 哈尔滨:哈尔滨工业大学, 2008:1-16. CAI P. Dynamic modeling and attitude control for flexible spacecraft[D]. Harbin:Harbin Institute of Technology, 2008:1-16(in Chinese).
[11] 葛东明, 史纪鑫, 邓润然, 等. 一种柔性多体动力学建模方法及其工程应用[J]. 航天器环境工程, 2019, 36(4):323-329. GE D M, SHI J X, DENG R R, et al. Flexible multi-body dynamics modeling and its engineering application[J]. Spacecraft Environment Engineering, 2019, 36(4):323-329(in Chinese).
[12] 袁旭, 朱圣英, 乔栋, 等. 小天体着陆动力学参数不确定性影响分析[J]. 深空探测学报, 2014, 1(2):56-61. YUAN X, ZHU S Y, QIAO D, et al. Impact analysis of dynamic parameters uncertainty on small celestial body landing[J]. Journal of Deep Space Exploration, 2014, 1(2):56-61(in Chinese).
[13] HUANG Y X, LI S, SUN J. Mars entry fault-tolerant control via neural network and structure adaptive model inversion[J]. Advances in Space Research, 2019, 63(1):557-571.
[14] 张远龙, 谢愈. 滑翔飞行器弹道规划与制导方法综述[J].航空学报, 2020, 41(1):50-62. ZHANG Y L, XIE Y. Review of trajectory planning and guidance methods for gliding vehicles[J]. Acta Aeronautica et Astronautica Sinica, 2020, 41(1):50-62(in Chinese).
[15] 包为民.航天智能控制技术让运载火箭"会学习"[J].航空学报, 2021, 42(11):525055. BAO W M. Space intelligent control technology enables launch vehicle to "self-learning"[J].Acta Aeronautica et Astronautica Sinica, 2021, 42(11):525055(in Chinese).
[16] TRUSZKOWSKI W, HALLOCK H, ROUFF C, et al. Autonomous and autonomic systems:With applications to NASA intelligent spacecraft operations and exploration systems[M]. Berlin:Springer Science & Business Media, 2010:173-186.
[17] HASSRIZAL H B, ROSSITER J A. A survey of control strategies for spacecraft attitude and orientation[C]//2016 UKACC 11th International Conference on Control (CONTROL). Piscataway:IEEE Press, 2016.
[18] SCHIERMAN J D, WARD D G, HULL J R, et al. Integrated adaptive guidance and control for re-entry vehicles with flight test results[J]. Journal of Guidance Control and Dynamics, 2004, 27(6):975-988.
[19] REITER J A, SPENCER D B, LINARES R. Spacecraft detection avoidance maneuver optimization using reinforcement learning[C]//29th AAS/AIAA Space Flight Mechanics Meeting, 2019:3055-3069.
[20] ZHU Y H, LUO Y Z. Fast evaluation of low-thrust transfers via deep neural networks[DB/OL]. arXiv preprint:1902.03738, 2019.
[21] 李海洋, 宝音贺西. 小推力转移燃料消耗估计的机器学习方法[J]. 深空探测学报, 2019, 6(2):195-200. LI H Y, BAOYIN H X. Machine learning method of estimation for fuel consumption of low-thrust transfers[J]. Journal of Deep Space Exploration, 2019, 6(2):195-200(in Chinese).
[22] LI H Y, TOPPUTO F, BAOYIN H X. Autonomous time-optimal many-revolution orbit raising for electric propulsion geo satellites via neural networks[DB/OL]. arXiv preprint:1909.08768, 2019.
[23] LI H Y, CHEN S, IZZO D, et al. Deep networks as approximators of optimal transfers solutions in multitarget missions[DB/OL]. arXiv preprint:1902.00250, 2019.
[24] SULLIVAN C J, BOSANAC N. Using reinforcement learning to design a low-thrust approach into a periodic orbit in a multi-body system[C]//AIAA Scitech 20

人工智能在航天器制导与控制中的应用综述

Spacecraft guidance and control based on artificial intelligence: Review

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献