| 56 | 0 | 88 |
| 下载次数 | 被引频次 | 阅读次数 |
针对载机主动防御场景下多枚低速弱机动弱势拦截弹协同拦截多个高速高机动优势目标的协同制导问题，本文设计了一种基于拦截态势函数和群体Critic多智能体深度确定性策略梯度（Group Criti Multi-agent Deep Deterministic Policy Gradient ， GC-MADDPG）的协同制导律。首先，建立了综合考虑拦截弹群协同拦截成功率、拦截角度、剩余飞行时间、过载、视场角和目标威胁度等多因素的拦截态势量化函数，为制导律设计提供了量化评估指标。其次，提出的GC-MADDPG方法通过引入群体Critic和局部Critic网络，在追求群体整体拦截成功率最大化的同时，确保各拦截弹满足自身约束条件。仿真结果表明，所设计的MMCIG制导律具有较强的鲁棒性和适应性，相比传统比例导引律（Proportional Navigation Guidance，PNG）在整体拦截成功率、脱靶量以及过载需求等方面均表现出明显优势。
Abstract：This paper addresses the cooperative guidance problem for multiple low-speed weakly-maneuverable inferior interceptors cooperatively intercepting multiple high-speed highly-maneuverable superior targets in active defense scenarios of aerial platforms. A cooperative guidance law based on an interception situation function and Group Critic Multi-agent Deep Deterministic Policy Gradient (GC-MADDPG) is proposed. First， an interception situation quantification function is established by comprehensively considering multiple factors， including the cooperative interception success rate of the interceptor group， interception angle， time-to-go， lateral acceleration， field-of-view angle， and target threat level， thereby providing quantitative evaluation metrics for guidance law design. Second， the GC-MADDPG method is proposed. By introducing group Critic and local Critic networks， this method maximizes the overall cooperative interception success rate while ensuring that each interceptor satisfies its own constraints. Simulation results demonstrate that the proposed MMCIG guidance law exhibits strong robustness and adaptability， and achieves significant improvements over the conventional Proportional Navigation Guidance (PNG) law in terms of overall interception success rate， miss distance， and acceleration demand.
[1] 董希旺， 于江龙， 化永朝等. 多飞行器攻击时间一致性协同制导进展综述与展望[J]. 北京航空航天大学学报， 2022， 48(09): 1836-1844.
[2] 王宁宇，王正涛，王小刚.多弹反机动目标一致性时间协同制导律[J]. 战术导弹技术， 2024， No. 228(06): 80-86+106.
[3] 肖航，许正，王垚，等.群对群高动态对抗下共识协同制导方法[J].战术导弹技术， 2025， No.233(05): 127-140.
[4] 杨登峰， 闫晓东. 基于视线协同和DMPC的载机-拦截弹群协同主动防御制导策略[J]. 系统工程与电子技术， 2024， 46(05): 1724-1733.
[5] 吴盘龙， 王勇， 钟俊等. 拦截机动目标的多约束下协同制导律[J]. 中国惯性技术学报， 2023， 31(11): 1142-1149.
[6] 杨登峰， 闫晓东. 多拦截弹主动防御系统协同一致拦截[J]. 战术导弹技术， 2023， (05):73-82.
[7] 胡乔杨， 潘涛， 孔哲等. 一种攻击机动目标的角度约束时间协同制导律研究[J]. 战术导弹技术， 2022， (04): 50-59+68.
[8] Zheng Y， Zheng C， Shao X， et al. Time-optimal guidance for intercepting moving targets with impact-angle constraints[J]. Chinese Journal of Aeronautics， 2022， 35(7): 157-167.
[9] Chen X， Wang J. Optimal control based guidance law to control both impact time and impact angle[J]. Aerospace Science and Technology， 2019， 84: 454-463.
[10] Li Y， Zhou H， Chen W C. Three-dimensional impact time and angle control guidance based on MPSP[J]. International Journal of Aerospace Engineering， 2019， 28: 1-17.
[11] Jiang H， An Z， Chen S， et al. Cooperative guidance with multiple constraints using convex optimization[J]. Aerospace science and technology， 2018， 79: 426-440.
[12] Su W S， Li K B， Chen L. Coverage-based three-dimensional cooperative guidance strategy against highly maneuvering target[J]. Aerospace Science and Technology， 2019， 85: 556-566.
[13] Yang D F， Yan X D. Dynamic encircling cooperative guidance for intercepting superior target with overload， impact angle and simultaneous time constraints[J]. Aerospace， 2024， 11: 375-395.
[14] Yang D F， Yan X D. Three-dimensional cooperative surrounding and capturing guidance for intercepting superior target with multi-constraints[J]. Aerospace Science and Technology， 2025， 157: 109787.
[15] Yin Y F， Yang G， Su Q R， et al. Task Allocation of Multiple Unmanned Aerial Vehicles Based on Deep Transfer Reinforcement Learning[J]. Drones， 2022， 6(8): 215.
[16] Liu J Y， Wang G， Fu Q， et al. Task Assignment in Ground-to-Air Confrontation Based on Multiagent Deep Reinforcement Learning[J]. Defence Technology， 2023， 19: 210–219.
[17] Aus F， Gir C， Mic F， et al. Game Theory for Automated Maneuvering during Air-to-Air Combat[J]. Journal of Guidance Control and Dynamics， 1990， 13(6): 1143–1149.
[18] Mcg J S， How J P， Wil B， et al. Air-Combat Strategy Using Approximate Dynamic Programming[J]. Journal of Guidance Control and Dynamics， 2010， 33(5): 1641–1654.
[19] Hong D， Kim M， Sun P. Study on Reinforcement Learning-Based Missile Guidance Law[J]. Applied Sciences， 2020， 10(18): 65-67.
[20] Zhu J G， Zou W， Zhu Z. Learning Evasion Strategy in Pursuit-Evasion by Deep Q-Network[C]. The 24th International Conference on Pattern Recognition (ICPR)， 2018， 67-72.
[21] Li S W， Wang Y C， Zhou Y M， et al. Multi-UAV Cooperative Air Combat Decision-Making Based on Multi-Agent Double-Soft Actor-Critic[J]. Aerospace， 2023， 10: 574-584.
基本信息:
DOI：10.16358/j.issn.1009-1300.20260090
中图分类号:TJ765.3
引用信息:
[1]杨登峰,骆盛,秦晨,等.基于态势函数和GC-MADDPG的载机主动防御场景下多对多拦截制导律[J].战术导弹技术().DOI:10.16358/j.issn.1009-1300.20260090.
2026-06-30
2026-06-30
2026-06-30