基于强化混合遗传算法的卫星与无人机联合任务规划方法

doi:10.12305/j.issn.1001-506X.2026.07.15

摘要/Abstract

摘要：

针对面向静态点任务的卫星与无人机联合任务规划问题，以最大化完成任务的观测收益为目标构建数学模型，提出一个三阶段联合任务规划框架，设计强化混合遗传算法（reinforcement hybrid genetic algorithm, RHGA）。提出基于最小负荷法的种群初始化机制和基于禁忌表搜索的局部优化机制；同时，将交叉变异参数调优过程建模为马尔可夫决策过程（Markov decision process, MDP），并基于强化学习设计动态调参方法。消融实验进一步分析了所提算法中3种改进机制的有效性。所提算法在求解质量与解稳定性方面具有良好的性能。

关键词: 空天协同, 对地观测, 任务规划, 强化混合遗传算法, 强化学习

Abstract:

To address the satellite and unmanned aerial vehicle joint mission planning problem for static point tasks, a mathematical model is established with the objective of maximizing the completing tasks observation benefits. A three-stage joint mission planning framework is proposed, and a reinforcement hybrid genetic algorithm （RHGA） is designed. A minimum-load-method based population initialization strategy and a tabu list-search-based local optimization mechanism are proposed. Meanwhile, the crossover-mutation parameter tuning process is modeled as a Markov decision process （MDP）, and a dynamic parameter tuning method based on reinforcement learning is designed. Ablation experiments further analyze the effectiveness of the three improved mechanisms in the proposed algorithm. The proposed algorithm has superior performance in terms of solution quality and stability.

Key words: aerospace collaboration, earth observation, mission planning, reinforcement hybrid genetic algorithm, reinforcement learning

中图分类号:

TP 391

尹天然, 罗贺, 石悦, 强小蝶, 王国强. 基于强化混合遗传算法的卫星与无人机联合任务规划方法[J]. 系统工程与电子技术, 2026, 48(7): 2293-2306.

Tianran YIN, He LUO, Yue SHI, Xiaodie QIANG, Guoqiang WANG. A satellite and UAV joint mission planning method based on a reinforcement hybrid genetic algorithm[J]. Systems Engineering and Electronics, 2026, 48(7): 2293-2306.

图/表 20

图1

图2

图3

图4

图5

图6

图7

图8

表1

表2

图9

表3

图10

图11

图12

图13

图14

表4

图15

表5

参考文献 37

1	HUANG G, HU M, YANG X Y, et al. A review of constrained multi-objective evolutionary algorithm-based unmanned aerial vehicle mission planning: key techniques and challenges[J]. Drones, 2024, 8 (7): 316. doi: 10.3390/drones8070316
2	WANG G, LV X, CUI L Z, et al. The methods of task pre-allocation and reallocation for multi-UAV cooperative reconnaissance mission[J]. IET Collaborative Intelligent Manufacturing, 2023, 5 (4): e12090. doi: 10.1049/cim2.12090
3	YANG X Y, HU M, HUANG G, et al. A hybrid local replanning strategy for multi-satellite imaging mission planning in uncertain environments[J]. IEEE Access, 2023, 11, 120780- 120804. doi: 10.1109/ACCESS.2023.3327343
4	LUO Y L, JIANG X Q, ZHONG S C, et al. Air-to-ground reconnaissance-attack task allocation for heterogeneous UAV swarm[J]. Journal of Systems Engineering and Electronics, 2025, 36 (1): 155- 175. doi: 10.23919/JSEE.2025.000012
5	ZHANG J, DU X, DONG Q C, et al. Distributed collaborative complete coverage path planning based on hybrid strategy[J]. Journal of Systems Engineering and Electronics, 2024, 35 (2): 463- 472. doi: 10.23919/JSEE.2023.000118
6	LU Z Z, SHEN X, LI D R, et al. Multiple super-agile satellite collaborative mission planning for area target imaging[J]. International Journal of Applied Earth Observation and Geoinformation, 2023, 117, 103211. doi: 10.1016/j.jag.2023.103211
7	YANG X Y, HU M, ZHANG R, et al. A unified model for multi-satellite imaging mission planning in various scenarios[J]. IEEE Access, 2023, 11, 46144- 46163. doi: 10.1109/ACCESS.2023.3275016
8	MENG S S, ZHU Q, XIA F, et al. Research on parameter optimisation of dynamic priority scheduling algorithm based on improved reinforcement learning[J]. IET Generation, Transmission & Distribution, 2020, 14 (16): 3171- 3178.
9	MORRIS R A, DUNGAN J L, BRESINA J L. Challenges in coordinating remote sensing systems[C]//Proc. of the AAAI Spring Symposium-Technical Report, 2006: 65−72.
10	HEROLD T M. Asynchronous, distributed optimization for the coordinated planning of air and space assets[D]. Cambridge: Massachusetts Institute of Technology, 2010.
11	李夏苗, 廖文昆, 伍国华, 等. 基于两阶段迭代优化的空天观测资源协同任务规划方法[J]. 控制与决策, 2021, 36 (5): 1147- 1156.
	LI X M, LIAO W K, WU G H, et al. A two-stage iterative optimization method for the coordinated task planning of space and air observation resources[J]. Control and Decision, 2021, 36 (5): 1147- 1156.
12	梁星星, 修保新, 范长俊, 等. 面向海上移动目标的空天协同连续观测模型[J]. 系统工程理论与实践, 2018, 38 (1): 229- 240.
	LIANG X X, XIU B X, FAN C J, et al. The aerospace cooperative planning model for maritime moving target continuation observation[J]. Systems Engineering - Theory & Practice, 2018, 38 (1): 229- 240.
13	DENG M, LIU B J, LI S M, et al. A two-phase coordinated planning approach for heterogeneous earth-observation resources to monitor area targets[J]. IEEE Trans. on Systems, Man, and Cybernetics: Systems, 2021, 51 (10): 6388- 6403.
14	WU G H, MAO X, CHEN Y G, et al. Coordinated scheduling of air and space observation resources via divide-and-conquer framework and iterative optimization[J]. IEEE Trans. on Aerospace and Electronic Systems, 2023, 59 (4): 3631- 3642. doi: 10.1109/TAES.2022.3228832
15	王慧林, 伍国华, 马满好. 多类异构对地观测平台协同任务规划方法[J]. 航空学报, 2016, 37 (3): 997- 1014.
	WANG H L, WU G H, MA M H. Coordinated task planning method for multiple heterogeneous earth observation platforms[J]. Chinese Journal of Aeronautics, 2016, 37 (3): 997- 1014.
16	LIU J M, CHEN Y G, WANG R, et al. Complex task planning method of space-aeronautics cooperative observation based on multi-layer interaction[J]. Journal of Systems Engineering and Electronics, 2023, 34 (6): 1550- 1564. doi: 10.23919/JSEE.2022.000098
17	SHANG X, WANG L, XING L N, et al. Knowledge-based memetic algorithm for joint task planning of multi-platform earth observation system[J]. Computers & Industrial Engineering, 2021, 160, 107559.
18	LIANG Z Y, LIU M, ZHONG P S, et al. Application research of a new neighbourhood structure with adaptive genetic algorithm for job shop scheduling problem[J]. International Journal of Production Research, 2023, 61 (2): 362- 381. doi: 10.1080/00207543.2021.2007310
19	CUI Y B, HU W, RAHMANI A. A reinforcement learning based artificial bee colony algorithm with application in robot path planning[J]. Expert Systems with Applications, 2022, 203, 117389. doi: 10.1016/j.eswa.2022.117389
20	LI T H, YIN Y C, YANG B, et al. A self-learning bee colony and genetic algorithm hybrid for cloud manufacturing services[J]. Computing, 2022, 104 (9): 1977- 2003. doi: 10.1007/s00607-022-01079-0
21	姜一啸, 吉卫喜, 何鑫, 等. 基于改进非支配排序遗传算法的多目标柔性作业车间低碳调度[J]. 中国机械工程, 2022, 33 (21): 2564- 2577.
	JIANG Y X, JI W X, HE X, et al. Low-carbon scheduling of multi-objective flexible job-shop based on improved NSGA-II[J]. China Mechanical Engineering, 2022, 33 (21): 2564- 2577.
22	张长泽, 李引珍, 尹胜男, 等. 多目标模糊柔性作业车间调度问题优化[J]. 科学技术与工程, 2020, 20 (3): 1099- 1106.
	ZHANG C Z, LI Y Z, YIN S N, et al. Optimization of multi-objective fuzzy flexible job shop scheduling problem[J]. Science Technology and Engineering, 2020, 20 (3): 1099- 1106.
23	WANG T, FU L Y, WEI Z X, et al. Unmanned ground weapon target assignment based on deep Q-learning network with an improved multi-objective artificial bee colony algorithm[J]. Engineering Applications of Artificial Intelligence, 2023, 117, 105612. doi: 10.1016/j.engappai.2022.105612
24	LI R, GONG W Y, LU C. A reinforcement learning based RMOEA/D for bi-objective fuzzy flexible job shop scheduling[J]. Expert Systems with Applications, 2022, 203, 117380. doi: 10.1016/j.eswa.2022.117380
25	CHEN R H, YANG B, LI S, et al. A self-learning genetic algorithm based on reinforcement learning for flexible job-shop scheduling problem[J]. Computers & Industrial Engineering, 2020, 149, 106778.
26	SONG Y J, OU J W, SUGANTHAN P N, et al. Learning adaptive genetic algorithm for earth electromagnetic satellite scheduling[J]. IEEE Trans. on Aerospace and Electronic Systems, 2023, 59 (6): 9010- 9025. doi: 10.1109/TAES.2023.3312626
27	赵慧敏, 罗贺, 阴酉龙, 等. 面向集合任务的多无人机电力巡检任务分配方法研究[J]. 系统工程理论与实践, 2025, 45 (2): 666- 684.
	ZHAO H M, LUO H, YIN Y L, et al. Research on task allocation method for multiple drones power inspection for collective tasks[J]. Systems Engineering - Theory & Practice, 2025, 45 (2): 666- 684.
28	SHAHRABI J, ADIBI M A, MAHOOTCHI M. A reinforcement learning approach to parameter estimation in dynamic job shop scheduling[J]. Computers & Industrial Engineering, 2017, 110, 75- 82.
29	UZUNOGLU A, GAHM C, WAHL S, et al. Learning-augmented heuristics for scheduling parallel serial-batch processing machines[J]. Computers & Operations Research, 2023, 151, 106122.
30	SONG Y J, WEI L N, YANG Q, et al. RL-GA: a reinforcement learning-based genetic algorithm for electromagnetic detection satellite scheduling problem[J]. Swarm and Evolutionary Computation, 2023, 77, 101236. doi: 10.1016/j.swevo.2023.101236
31	FALLAHI A, AMANI B E, NIAKI S T A. A constrained multi-item EOQ inventory model for reusable items: reinforcement learning-based differential evolution and particle swarm optimization[J]. Expert Systems with Applications, 2022, 207, 118018. doi: 10.1016/j.eswa.2022.118018
32	LI R F, ZHANG X Y, JIANG L L, et al. An adaptive heuristic algorithm based on reinforcement learning for ship scheduling optimization problem[J]. Ocean & Coastal Management, 2022, 230, 106375.
33	CAO Z C, LIN C R, ZHOU M C. A knowledge-based cuckoo search algorithm to schedule a flexible job shop with sequencing flexibility[J]. IEEE Trans. on Automation Science and Engineering, 2021, 18 (1): 56- 69. doi: 10.1109/TASE.2019.2945717
34	GUO W Q, ZHANG X Y, LI Y K, et al. Collaborative optimization of vessel scheduling and tugboat allocation in seaports using a multi-action deep reinforcement learning framework[J]. Engineering Applications of Artificial Intelligence, 2025, 156, 111239. doi: 10.1016/j.engappai.2025.111239
35	CHEN M K, CHANG C L, LIN C J, et al. Vehicle detection on express roads using YOLOv7 with Taguchi parameter optimization method[J]. Sensors and Materials, 2024, 36 (4): 1605- 1625. doi: 10.18494/SAM4718
36	CHANG D L, SHI H B, LIU C, et al. Scheduling optimization of flexible flow shop with buffer capacity limitation based on an improved discrete particle swarm optimization algorithm[J]. Engineering Optimization, 2024, 57 (2): 571- 597.
37	LU F X, DAI Q Y, YANG G, et al. Online task planning method of anti-ship missile based on rolling optimization[J]. Journal of Systems Engineering and Electronics, 2024, 35 (3): 720- 731. doi: 10.23919/JSEE.2024.000059

参数名称	符号	设置
任务点数量	m	[50,400]
任务点优先级	$ p $	[1,10]
任务所需观测时间/s	$ {\mathrm{ct}} $	[10,60]
无人机基地坐标	$ {t}_{0} $	（25°,119°）
无人机、卫星数量组合	−	{（5,4）,（10,8）}
无人机平均飞行速度/（km/h）	$ {\mathrm{m{s}}}_{a } $	200
无人机最大巡航距离/km	$ {\mathrm{m{l}}}_{a } $	1000
卫星侧摆单位角度电量消耗/（Wh/°）	$ {\epsilon}_{a } $	0.6
卫星调度周期的最大电量/Wh	$ {\mathrm{M{E}}}_{a } $	3000
任务图像分辨率需求/（m/pixel）	$ {\text{obvRes}}_{i} $	[1,3]
资源图像分辨率/（m/pixel）	$ {{\mathrm{obvRes}}}_{i}^{k} $	{0.5,1,2,3}
任务的可见时间窗长度/h	−	12

参数	范围	水平1	水平2	水平3
种群规模N	30~50	30	40	50
遗传迭代次数It1	200~300	200	250	300
禁忌迭代次数It2	600~800	600	700	800
禁忌表长度L	20~40	20	30	40
学习率α	0.1~0.2	0.1	0.15	0.2
折扣率γ	0.85~0.95	0.85	0.9	0.95
勘探速率ε	0.85~0.95	0.85	0.9	0.95

算法名称	实验方法
移除强化学习模块	移除融合强化学习参数调优模块，选用Taguchi正交实验获得的参数
移除IM模块	移除基于最小负荷法的种群初始化机制，选用随机方式生成初始种群
移除CM模块	移除基于禁忌表搜索的局部优化策略，采用GA优化
移除强化学习、IM、 CM模块	移除3种改进机制，分别采用对应移除方法替换

算例	RHGA	移除强化学习模块		移除IM模块		移除CM模块		移除强化学习、IM、CM模块
算例	平均值	平均值	Gap/%	平均值	Gap/%	平均值	Gap/%	平均值	Gap/%
S-50	250.9	243.7	−2.87	250.1	−0.32	246.5	−1.75	238.9	−4.78
S-60	266.8	258.4	−3.15	265.7	−0.41	259.2	−2.85	251.6	−5.69
S-70	345.2	334.8	−3.01	344.1	−0.32	336.5	−2.52	327.9	−4.95
S-80	395.8	381.4	−3.63	394.2	−0.40	384.6	−2.83	373.5	−5.63
S-90	522.7	504.9	−3.40	520.1	−0.49	509.2	−2.58	492.5	−5.78
S-100	548.0	527.6	−3.72	545.2	−0.51	532.4	−2.85	516.7	−5.71
L-150	728.2	695.4	−4.50	622.8	−14.47	610.3	−16.18	591.1	−18.84
L-200	957.4	906.7	−5.29	948.3	−1.01	915.6	−4.36	789.4	−17.54
L-250	1113.3	1052.8	−5.43	1004.7	−9.75	1078.4	−3.13	929.5	−16.51
L-300	1379.4	1298.5	−5.86	1265.2	−8.27	1234.6	−3.25	1167.8	−15.34
L-350	1623.7	1524.8	−6.09	1407.9	−13.30	1378.2	−15.12	1289.3	−20.59
L-400	1840.3	1728.4	−6.08	1621.6	−11.89	1585.9	−13.82	1489.2	−18.97
平均值	−	−	−4.25	−	−5.08	−	−6.10	−	−12.87

[1]	马赞, 刘禹彬, 白杰, 陈勇, 孙淑光. 基于分层STPA-MC的无人机智能避让适航安全风险评估[J]. 系统工程与电子技术, 2026, 48(6): 2000-2013.
[2]	韩维, 丛婧羽, 成一阳, 韩啸华, 郭放, 李常久, 苏析超. 面向随机扰动事件的舰载直升机任务动态调度研究方法[J]. 系统工程与电子技术, 2026, 48(6): 2014-2030.
[3]	贾振帅, 肖冰, 钱寒雨, 张哲宇. 基于多策略学习的航天器在轨观测机动决策方法[J]. 系统工程与电子技术, 2026, 48(5): 1590-1598.
[4]	张华卿, 张晓飞, 郝明瑞, 姜吉祥, 李闪. 鲁棒多智能体协同对抗策略离线强化学习[J]. 系统工程与电子技术, 2026, 48(5): 1670-1681.
[5]	张少辉, 李璐璐, 李亚飞, 吴庆顺, 李冠峰, 徐明亮. 舰载机弹药保障作业规划方法研究综述[J]. 系统工程与电子技术, 2026, 48(4): 1303-1321.
[6]	刘浩, 贺子鹏, 徐广德. 基于CUDA纹理插值的空间多目标交会序列快速规划方法[J]. 系统工程与电子技术, 2026, 48(4): 1331-1339.
[7]	骆婧娴, 周光辉, 于金月, 张扬. 基于Q学习文化基因算法的考虑任务聚类的多敏捷对地观测卫星调度研究[J]. 系统工程与电子技术, 2026, 48(4): 1349-1359.
[8]	金志刚, 刘泽培, 武晓栋. 物联网安全与隐私保护中博弈论的应用综述[J]. 系统工程与电子技术, 2026, 48(3): 1072-1082.
[9]	杨鹏程, 杨清清, 高盈盈, 杨志伟, 杨克巍, 艾波. 基于强化学习的海上移动目标搜索路径规划[J]. 系统工程与电子技术, 2026, 48(2): 515-523.
[10]	王旭, 蔡光斌, 余晓亚, 叶子绮, 单斌. 基于双动态PPO算法的高超声速飞行器姿态控制[J]. 系统工程与电子技术, 2026, 48(2): 694-704.
[11]	林志康, 刘甲磊, 马佳智, 施龙飞, 徐进宝. 利用分布式辐射源闪烁诱偏的抗反辐射方法[J]. 系统工程与电子技术, 2026, 48(1): 1-11.
[12]	洪芳宇, 叶青, 张利宁, 伍国华. 面向区域搜索的车载多无人机协同任务规划方法[J]. 系统工程与电子技术, 2026, 48(1): 144-156.
[13]	薛锦妍, 张雅声, 陶雪峰, 杨茗棋, 赵帅龙. GEO航天器轨道机动控制研究进展[J]. 系统工程与电子技术, 2026, 48(1): 290-300.
[14]	宋传龙, 张倩武, 何健, 周文骏, 王辉, 孔巍巍, 田文波. 基于MADDPG算法的星地协同边缘计算任务卸载方法[J]. 系统工程与电子技术, 2026, 48(1): 350-360.
[15]	袁健波, 杜永浩, 陈盈果, 何永明. 面向点群与大区域目标的成像卫星任务规划模型与算法研究[J]. 系统工程与电子技术, 2025, 47(9): 2939-2950.