中文摘要针对非完全信息条件下博弈决策中目标意图未知和机动策略难以优选的问题，提出了基于意图识别的空间轨道机动决策方法。首先结合航天器脉冲机动特点，设计了有限时间区域内的模型预测控制框架，能够针对单一场景快速优化护卫策略。然后，本文提出了一种融合非合作目标运动意图识别结果的护卫机动博弈策略优化方法，适用于多意图场景。依据意图识别的概率动态调整策略优化指标，使得护卫机动策略在应对复杂、不确定的空间环境时更加灵活。实验结果表明，所提出的基于意图识别的轨道机动决策方法，在多种空间护卫场景中展显优势。
To address the challenges of unknown target intent and strategy selection under incomplete-information orbital games, an intent-inference-based maneuver-decision framework is proposed. Exploiting the impulsive characteristics of spacecraft, a model-predictive-control scheme is first devised within a finite-time horizon to rapidly generate guardian strategies for a single prespecified intent. Subsequently, an integrated guardian maneuver optimization method is developed that fuses probabilistic intent-inference outputs, thereby extending applicability to multi-intent scenarios. The optimization objective is dynamically re-weighted according to the inferred intent distribution, affording enhanced adaptability to uncertain operational environments. Simulation results across diverse space-guardian missions confirm the superior performance of the proposed approach.
[1]. Zhao L , Zhang Y , Dang Z .PRD-MADDPG: An efficient learning-based algorithm for orbital pursuit-evasion game with impulsive maneuvers[J].Advances in Space Research, 2023, 72(2):211-230.
[2]. Liu Y, Jiang Y, Li H et al. Determining origins of satellite breakup events in LEO region. Astrodynamics 7, 465–476 (2023).
[3]. Cherniakov M, Hoare E G, Gashinova M, et al. Recognition of objects in orbit and their intentions with space-borne sub-thz inverse synthetic aperture radar[J]. IET Radar, Sonar & Navigation, 2024, 18(4): 564-576.
[4]. Chen S, Li J, Xie Y, et al. Approaching intention prediction of orbital maneuver based on dynamic bayesian network.[J]. Transactions of Nanjing University of Aeronautics & Astronautics, 2023, 40(4).
[5]. Li J, Yang Z, Luo Y. Intention inference for space targets using deep convolutional neural network[J]. Advances in Space Research, 2025, 75(2): 2184-2200.
[6]. Zhang H, Luo J, Gao Y, et al. An intention inference method for the space non-cooperative target based on bigru-self attention[J]. Advances in Space Research, 2023, 72(5): 1815-1828.
[7]. Sun Q, Dang Z. Deep neural network for non-cooperative space target intention recognition[J]. Aerospace Science and Technology, 2023, 142: 108681.
[8]. Sun Q, Zhao L, Tang S, et al. Orbital motion intention recognition for space noncooperative targets based on incomplete time series data[J]. Aerospace Science and Technology, 2025, 158: 109912.
[9]. 罗亚中, 李振瑜, 祝海. 航天器轨道追逃微分对策研究综述[J]. 中国科学: 技术科学,2020, 50(12): 1533-1545.
LUO Y Z, LI Z Y, ZHU H. Review on Differential Games for Spacecraft Orbit Pursuit-Evasion [J]. Science China: Technological Sciences, 2020, 50(12): 1533-1545 (in Chinese).
[10]. Shen D, Jia B, Chen G, et al. Pursuit-evasion games with information uncertainties for
elusive orbital maneuver and space object tracking[C]. Sensors and Systems for Space
Applications VIII. SPIE, 2015: 151-160.
[11]. Li Z, Zhu H, Luo Y. An escape strategy in orbital pursuit-evasion games with incomplete information[J]. Science China Technological Sciences, 2021, 64(3): 559-570.
[12]. Wang Z, Gong B, Yuan Y, et al. Incomplete information pursuit-evasion game control for a space non-cooperative target[J]. Aerospace, 2021, 8(8): 211.
[13]. Yang B, Liu P, Feng J, et al. Two-stage pursuit strategy for incomplete-information impulsive space pursuit-evasion mission using reinforcement learning[J]. Aerospace, 2021,8(10): 299.
[14]. 祝海. 基于微分对策的航天器轨道追逃最优控制策略[D]. 长沙: 国防科技大学,2017.
ZHU H. Optimal Control Strategy for Spacecraft Orbit Pursuit-Evasion Based on Differential Games [D]. Changsha: National University of Defense Technology, 2017 (in Chinese).
[15]. 马昌凤. 最优化计算方法及其 MATLAB 程序实现[M]. 国防工业出版社, 2015:219-222.
MA C F. Optimization Calculation Methods and Their MATLAB Program Implementation [M]. National Defense Industry Press, 2015: 219-222 (in Chinese).
[16]. Sun Q, Zhao L, Dang Z. BiGAT: A Model for Recognizing Motion Intentions of Space Non-Cooperative Targets[J]. IEEE Transactions on Aerospace and Electronic Systems, 2024.
[17]. Mavsar M, Morimoto J, Ude A. Gan-based semi-supervised training of lstm nets for intention recognition in cooperative tasks[J]. IEEE Robotics and Automation Letters, 2023, 9(1): 263-270.
[18]. Khodabandelou G, Moon H, Amirat Y, et al. A fuzzy convolutional attention-based gru network for human activity recognition[J]. Engineering Applications ofArtificial Intelligence, 2023, 118: 105702.
[19]. Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[J]. Advances in neural information processing systems, 2017, 30.
[20]. Sun, Q., Zhao, L. & Dang, Z. Comprehensive classification of non-periodic relative motion styles of spacecraft: A geometric approach and applications. Astrodynamics (2025). https://doi.org/10.1007/s42064-025-0263-7
CJA