汪晨,曹林,王金晓,高鹏飞,宋沛然,杜康宁

• 1:北京信息科技大学目标认知信息处理科学与技术中心
• 2:中国科学院目标认知与应用技术重点实验室
• 3:中国科学院空天信息创新研究院

摘要(Abstract)：

随着对高时效、高精度地球观测需求的持续增长，敏捷卫星任务规划在大规模与高复杂约束条件下面临严峻挑战。针对上述问题，提出一种基于近端策略优化（proximal policy optimization, PPO）策略选择引导灰狼优化的敏捷卫星任务规划算法。该算法利用灰狼优化算法生成多种候选调度策略，并通过快速评估构建规模受控的候选集合，在此基础上引入PPO进行自适应策略选择，形成启发式生成与强化学习决策相结合的混合优化框架。为适应大规模场景，算法通过候选集筛选构建稀疏动作空间，降低决策复杂度并保持有效探索能力。实验结果表明，所提算法在求解效率与任务收益率上均优于A-ALNS、GRILS及RL-GA算法，验证了其在大规模敏捷卫星任务规划中的有效性。

关键词(KeyWords)： 敏捷卫星;任务规划;灰狼优化算法;强化学习

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目（U20A20163,62201066）;; 目标认知与应用技术重点实验室开放基金项目（2023-CXPT-LC-005）;; 北京市自然科学基金项目（4264103）

作者(Author): 汪晨,曹林,王金晓,高鹏飞,宋沛然,杜康宁

DOI: 10.16508/j.cnki.11-5866/n.2026.04.001

参考文献(References)：

• [1]向尚，陈盈果，李国梁，等.卫星自主与协同任务调度规划综述[J].自动化学报，2019,45(2):252-264.Xiang Shang,Chen Yingguo,Li Guoliang,et al. Review on satellite autonomous and collaborative task scheduling planning[J]. Acta Automatica Sinica,2019,45(2):252-264.(in Chinese)
• [2]Liu Dongning,Zhou Guanghui. Deep reinforcement learningbased attention decision network for agile earth observation satellite scheduling[J]. Remote Sensing,2024,16(23):4436.
• [3]He Changyuan,Dong Yunfeng,Li Hongjue,et al. Reasoningbased scheduling method for agile earth observation satellites with multi-subsystem coupling[J]. Remote Sensing,2023,15(6):1577.
• [4]Jacquet A,Infantes G,Meuleau N,et al. Earth observation satellite scheduling with graph neural networks[PP/OL].(2024-08-27)[2026-02-24]. https：//arxiv. org/html/2408. 15041v1.
• [5]Wang Xinwei, Wu Guohua, Xing Lining, et al. Agile earth observation satellite scheduling over 20 years:formulations,methods, and future directions[J]. IEEE Systems Journal,2021, 15(3):3881-3892.
• [6]陈旺，邵庆龙，周晓，等.海洋一号卫星观测任务规划算法设计及系统应用[J].中国空间科学技术（中英文），2024,44(2):145-153.Chen Wang,Shao Qinglong,Zhou Xiao,et al. Algorithm design and system application of HY-1 satellite observation mission planning[J]. Chinese Space Science and Technology,2024,44(2):145-153.(in Chinese)
• [7]Cho D H,Kim J H,Choi H L. Optimization-based scheduling method for agile earth-observing satellite constellation[J].Journal of Aerospace Information Systems,2018,15(11):611-626.
• [8]杜永浩，邢立宁，姚锋，等.航天器任务调度模型、算法与通用求解技术综述[J].自动化学报，2021,47(12):2715-2741.Du Yonghao,Xing Lining,Yao Feng,et al. Survey on models,algorithms and general techniques for spacecraft mission scheduling[J]. Acta Automatica Sinica,2021,47(12):2715-2741.(in Chinese)
• [9]尹霞，韩笑冬，李朝玉，等.资源强耦合下改进遗传测控调度方法[J].中国空间科学技术（中英文），2025,45(1):59-68.Yin Xia,Han Xiaodong,Li Zhaoyu,et al. Improved genetic method for satellite TT&C scheduling under strong resource coupling[J]. Chinese Space Science and Technology,2025,45(1):59-68.(in Chinese)
• [10]王沛，谭跃进.多星联合对地观测调度问题的列生成算法[J].系统工程理论与实践，2011,31(10):1932-1939.Wang Pei,Tan Yuejin. Column generation for the earth observation satellites scheduling problem[J]. Systems Engineering-Theory&Practice,2011,31(10):1932-1939.(in Chinese)
• [11]Peng Guansheng,Song Guopeng,He Yongming,et al. Solving the agile earth observation satellite scheduling problem with time-dependent transition times[J]. IEEE Transactions on Systems,Man,and Cybernetics:Systems,2022,52(3):1614-1625.
• [12]Wu Jian,Song Bingyu,Zhang Guoting,et al. A data-driven improved genetic algorithm for agile earth observation satellite scheduling with time-dependent transition time[J]. Computers&Industrial Engineering,2022,174:108823.
• [13]樊慧晶，章文毅，田妙苗，等.基于粒子群算法的卫星任务地面站资源调度方法[J].中国科学院大学学报（中英文），2022,39(6):801-808.Fan Huijing,Zhang Wenyi,Tian Miaomiao,et al. A resource scheduling method for satellite mission ground station based on particle swarm optimization algorithm[J]. Journal of University of Chinese Academy of Sciences,2022,39(6):801-808.(in Chinese)
• [14]何奇恩，李峰，钟兴.多目标算法在卫星区域覆盖调度及数传规划上的应用综述[J].遥感技术与应用，2023,38(4):783-793.He Qien,Li Feng,Zhong Xing. A review of the application of multi-objective algorithms in satellite regional coverage scheduling and data transmission planning[J]. Remote Sensing Technology and Application,2023,38(4):783-793.(in Chinese)
• [15]Li Jiaojiao,Zhu Jianghan,Xu Dongyang,et al. Earth observation satellite scheduling with interval-varying profits[J]. IEEE Transactions on Aerospace and Electronic Systems,2024,60(6):8273-8288.
• [16]Liu Zheng,Xiong Wei,Jia Zhuoya,et al. Two-stage deep reinforcement learning method for agile optical satellite scheduling problem[J]. Complex&Intelligent Systems,2025,11(1):35.
• [17]Song Yanjie,Wei Luona,Yang Qing,et al. RL-GA:a reinforcement learning-based genetic algorithm for electromagnetic detection satellite scheduling problem[J].Swarm and Evolutionary Computation,2023,77:101236.
• [18]Du Yonghao,Wang Tao,Xin Bin,et al. A data-driven parallel scheduling approach for multiple agile earth observation satellites[J]. IEEE Transactions on Evolutionary Computation,2020,24(4):679-693.
• [19]Liu Xiaolu,Laporte G,Chen Yingwu,et al. An adaptive large neighborhood search metaheuristic for agile satellite scheduling with time-dependent transition time[J]. Computers&Operations Research,2017,86:41-53.
• [20]He Lei,Liu Xiaolu,Laporte G,et al. An improved adaptive large neighborhood search algorithm for multiple agile satellites scheduling[J]. Computers&Operations Research,2018,100:12-25.
• [21]Mirjalili S,Mirjalili S M,Lewis A. Grey wolf optimizer[J].Advances in Engineering Software,2014,69:46-61.
• [22]Schulman J,Wolski F,Dhariwal P,et al. Proximal policy optimization algorithms[PP/OL]. V2.(2017-08-28)[2026-02-24]. https：//arxiv. org/abs/1707. 06347.
• [23]Chen Ming,Du Yonghao,Tang Ke,et al. Learning to construct a solution for the agile satellite scheduling problem with timedependent transition times[J]. IEEE Transactions on Systems,Man,and Cybernetics:Systems,2024,54(10):5949-5963.
• [24]Dilkina B,Havens B. Agile satellite scheduling via permutation search with constraint propagation[EB/OL].(2005-05-31)[2026-02-24]. https：//www2. cs. sfu. ca/CourseCentral/827/havens/papers/topic%2312(SatelliteScheduling)/SatelliteSched.pdf.