基于强化学习的多发导弹协同攻击智能制导律
Reinforcement Learning-based Intelligent Guidance Law for Cooperative Attack of Multiple Missiles
查看参考文献30篇
文摘
|
为实现多发导弹对目标的协同攻击,提升打击效能,提出一种基于深度确定性策略梯度下降神经网络的强化学习协同制导律。修正了基于线性交战动力学的剩余飞行时间估计方程,不再受小角度假设的约束,进而提高剩余飞行时间估计精度。以各弹的剩余飞行时间误差为协调变量,与各弹的剩余飞行距离一同作为强化学习算法的观测量。利用脱靶量和剩余飞行时间误差构造奖励函数,离线训练生成强化学习智能体。闭环制导过程中,强化学习智能体将实时生成可实现同时打击的制导指令。仿真结果表明:该强化学习制导律能够实现多发导弹对目标的同时攻击;与传统协同制导律相比,强化学习协同制导律的脱靶量较小,攻击时间误差也较小。 |
其他语种文摘
|
A reinforcement learning-based cooperative guidance law utlitizing a deep deterministic policy gradient descent neural network is proposed to achieve the cooperative attack of multiple missiles against a target and improve the attack effectiveness. The estimation equation of time-to-go based on the linear engagement dynamics is revised to improve the estimation accuracy of time-to-go, which is no longer restricted by the assumption of small angle. The time-to-go error of each missile is regarded as the coordination variable. The time-to-go error and range-to-go of each missile are used as the observables of the reinforcement learning algorithm. The reward function is constructed by using miss distance and time-to-go error, and then a reinforcement learning agent is generated by offline training. In the process of closed-loop guidance, the reinforcement learning agent generates guidance commands in real time, by that simultaneous attack can be achieved. Simulated results verify that the proposed reinforcement learning guidance law can achieve simultaneous attack on the target. Compared with the traditional cooperative guidance law, the reinforcement learning cooperative guidance law can be used to obtain smaller miss distances and smaller attack time errors. |
来源
|
兵工学报
,2021,42(8):1638-1647 【核心库】
|
DOI
|
10.3969/j.issn.1000-1093.2021.08.008
|
关键词
|
导弹
;
协同制导律
;
同时攻击
;
强化学习
;
深度确定性策略梯度下降算法
|
地址
|
1.
北京航空航天大学宇航学院, 北京, 100191
2.
中国运载火箭技术研究院, 北京, 100076
|
语种
|
中文 |
文献类型
|
研究性论文 |
ISSN
|
1000-1093 |
学科
|
武器工业 |
基金
|
2021年度"卓越百人"博士后支持计划项目
;
国防基础科研基金
|
文献收藏号
|
CSCD:7048623
|
参考文献 共
30
共2页
|
1.
Garcia E. Cooperative missile guidance for active defense of air vehicles.
IEEE Transactions on Aerospace & Electronic Systems,2018,54(2):706-721
|
CSCD被引
11
次
|
|
|
|
2.
Kumar S R. Cooperative nonlinear guidance strategies for aircraft defense.
Journal of Guidance, Control, and Dynamics,2016,40(1):124-138
|
CSCD被引
25
次
|
|
|
|
3.
Shalumov V. Optimal cooperative guidance laws in a multiagent target-missile-defender engagement.
Journal of Guidance, Control, and Dynamics,2019,42(9):1993-2006
|
CSCD被引
8
次
|
|
|
|
4.
任章. 飞行器集群协同制导控制方法及应用研究.
导航定位与授时,2019,6(5):1-9
|
CSCD被引
7
次
|
|
|
|
5.
赵建博. 多导弹协同制导研究综述.
航空学报,2017,38(1):17-29
|
CSCD被引
13
次
|
|
|
|
6.
叶鹏鹏. 非持续连通通信拓扑下的多导弹协同制导.
兵工学报,2018,39(3):474-484
|
CSCD被引
9
次
|
|
|
|
7.
Jeon I S. Homing guidance law for cooperative attack of multiple missiles.
Journal of Guidance, Control, and Dynamics,2010,33(1):275-280
|
CSCD被引
132
次
|
|
|
|
8.
Jeon I S. Impact-time-control guidance with generalized proportional navigation based on nonlinear formulation.
Journal of Guidance, Control, and Dynamics,2016,39(8):1885-1890
|
CSCD被引
35
次
|
|
|
|
9.
马培蓓. 多导弹攻击时间和攻击角度协同制导研究综述.
飞航导弹,2018(6):59-63
|
CSCD被引
2
次
|
|
|
|
10.
Cho D. Nonsingular sliding mode gui-dance for impact time control.
Journal of Guidance, Control, and Dynamics,2016,39(1):61-68
|
CSCD被引
49
次
|
|
|
|
11.
Liu X D. Adaptive sliding mode guidance with impact time and angle constraints.
IEEE Access,2020,8:26926-26932
|
CSCD被引
3
次
|
|
|
|
12.
Zhou J L. Distributed guidance law design for cooperative simultaneous attacks with multiple missiles.
Journal of Guidance, Control, and Dynamics,2016,39(10):2439-2447
|
CSCD被引
42
次
|
|
|
|
13.
Sinha A. Super-twisting control based impact time constrained guidance.
AIAA SciTech 2020 Forum,2020
|
CSCD被引
1
次
|
|
|
|
14.
李文. 速度时变情况下多飞行器时间协同制导方法研究.
兵工学报,2020,41(6):1096-1110
|
CSCD被引
12
次
|
|
|
|
15.
马卫华. “会学习”运载火箭的制导控制技术.
航天控制,2020,38(2):3-8
|
CSCD被引
12
次
|
|
|
|
16.
黄旭星. 人工智能在航天器制导与控制中的应用综述.
航空学报,2021,42(4):524201
|
CSCD被引
13
次
|
|
|
|
17.
Cottrell R G. Minimizing interceptor size using neural networks for terminal guidance law synthesis.
Journal of Guidance, Control, and Dynamics,1996,19(3):557-562
|
CSCD被引
6
次
|
|
|
|
18.
Huang L M. Deep learning midcourse guidance for interceptor missile.
Proceedings of 2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference,2019:1129-1134
|
CSCD被引
1
次
|
|
|
|
19.
Gaudet B. Reinforcement learning for angle-only intercept guidance of maneuvering targets.
Aerospace Science and Technology,2020,99:105746
|
CSCD被引
27
次
|
|
|
|
20.
南英. 基于深度强化学习的弹道导弹中段突防控制.
指挥信息系统与技术,2020,11(4):1-9,27
|
CSCD被引
7
次
|
|
|
|
|