[1]王子博,朱齐丹,孔令鑫,等.基于强化学习与直接升力的舰载机自动着舰控制[J].智能系统学报,2025,20(2):416-424.[doi:10.11992/tis.202312026]
WANG Zibo,ZHU Qidan,KONG Lingxin,et al.Automatic landing control of carrier-based aircraft based on reinforcement learning and direct lift[J].CAAI Transactions on Intelligent Systems,2025,20(2):416-424.[doi:10.11992/tis.202312026]
点击复制
WANG Zibo,ZHU Qidan,KONG Lingxin,et al.Automatic landing control of carrier-based aircraft based on reinforcement learning and direct lift[J].CAAI Transactions on Intelligent Systems,2025,20(2):416-424.[doi:10.11992/tis.202312026]
基于强化学习与直接升力的舰载机自动着舰控制
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
20
期数:
2025年第2期
页码:
416-424
栏目:
学术论文—智能系统
出版日期:
2025-03-05
- Title:
- Automatic landing control of carrier-based aircraft based on reinforcement learning and direct lift
- Keywords:
- landing of carrier-based aircraft; flight control; reinforcement learning; direct lift control; guidance law; carrier air wake; neural network; path tracking
- 分类号:
- TP273
- 摘要:
- 舰载机着舰过程是舰载机作业事故率最高的阶段，为实现舰载机高精度全自动着舰，提出了一种新的舰载机自动着舰控制方法，设计了基于直接升力的控制器与基于强化学习的纵向制导律。直接升力控制实现舰载机飞行状态之间的解耦，增强舰载机姿态角与气流角的稳定性。制导律通过深度强化学习算法训练的神经网络非线性拟合得到，提高了扰动情况下舰载机对理想下滑道的跟踪精度，同时避免了传统方法繁杂的参数整定工作以及对模型的依赖。通过对比仿真结果，在舰尾流扰动下，相比于滑模控制方法、预设性能控制方法、PID控制方法与基于径向基神经网络的自适应控制方法，本文方法具有更好的鲁棒性，增强了对舰尾流扰动的抑制能力，提高了着舰精度。
- Abstract:
- The landing of carrier-based aircraft is the stage with the highest accident rate. A novel control method for the automatic landing of carrier-based aircraft is proposed to realize high-precision automatic landing of carrier-based aircraft. This method includes a direct lift controller and a longitudinal guidance law based on reinforcement learning. The direct lift control decouples the flight states of the carrier-based aircraft, while the guidance law is derived through nonlinear fitting using a neural network trained by deep reinforcement learning algorithms. This approach improves the precision of the aircraft to the ideal glide path in the presence of disturbances and eliminates the need for complicated parameter tuning and model dependence typically associated with traditional control methods. Simulation results show that, in the presence of carrier air wake disturbance, the proposed method outperforms the sliding mode control method, PID control, and adaptive control based on a radial basis neural networks. This method demonstrates greater robustness, superior capability to restrict the effects of carrier air wake disturbance, and improved landing precision.
- 参考文献/References:
-
[1] WANG Lipeng, JIANG Xiangli, ZHANG Zhi, et al. Lateral automatic landing guidance law based on risk-state model predictive control[J]. ISA transactions, 2022, 128: 611-623.
[2] URNES J M, HESS R K. Development of the F/A-18A automatic carrier landing system[J]. Journal of guidance, control, and dynamics, 1985, 8(3): 289-295.
[3] 何杭轩, 段海滨, 张秀林, 等. 基于扩张鸽群优化的舰载无人机横侧向着舰自主控制[J]. 智能系统学报, 2022, 17(1): 151-157.
HE Hangxuan, DUAN Haibin, ZHANG Xiulin, et al. Lateral automatic carrier landing control based on expanded pigeon inspired optimization[J]. CAAI transactions on intelligent systems, 2022, 17(1): 151-157.
[4] HESS R A. Analysis of the aircraft carrier landing task, pilot + augmentation/automation[J]. IFAC-PapersOnLine, 2019, 51(34): 359-365.
[5] CRASSIDIS J L, MOOK D J, MCGRATH J M. Automatic carrier landing system utilizing aircraft sensors[J]. Journal of guidance, control, and dynamics, 1993, 16(5): 914-921.
[6] YUAN Yang, DUAN Haibin, ZENG Zhigang. Automatic carrier landing control with external disturbance and input constraint[J]. IEEE transactions on aerospace and electronic systems, 2023, 59(2): 1426-1438.
[7] ZHU Qidan, YANG Zhibo. Design of air-wake rejection control for longitudinal automatic carrier landing cyber-physical system[J]. Computers & electrical engineering, 2020, 84: 106637.
[8] YU Yue, WANG Honglun, LI Na, et al. Automatic carrier landing system based on active disturbance rejection control with a novel parameters optimizer[J]. Aerospace science and technology, 2017, 69: 149-160.
[9] ZHEN Ziyang, YU Chaojun, JIANG Shuoying, et al. Adaptive super-twisting control for automatic carrier landing of aircraft[J]. IEEE transactions on aerospace and electronic systems, 2020, 56(2): 984-997.
[10] MENG Yue, WANG Wei, HAN Hao. Flight control method using neural network in prediction for suppressing ship airwake impact in carrier landing[J]. IEEE aerospace and electronic systems magazine, 2023, 38(7): 20-32.
[11] DENHAM J W. Project MAGIC CARPET: “advanced controls and displays for precision carrier landings” [C]//54th AIAA Aerospace Sciences Meeting. San Diego: AIAA, 2016: 1770.
[12] WU Wenhai, SONG Liting, ZHANG Yang, et al. Nonlinear comprehensive decoupling controller based on direct lift control for carrier landing[J]. IEEE access, 2022, 10: 113875-113887.
[13] 罗飞, 张军红, 王博, 等. 基于直接升力与动态逆的舰尾流抑制方法[J]. 航空学报, 2021, 42(12): 193-208.
LUO Fei, ZHANG Junhong, WANG Bo, et al. Air wake suppression method based on direct lift and nonlinear dynamic inversion control[J]. Acta aeronautica et astronautica sinica, 2021, 42(12): 193-208.
[14] 何胜涛, 江驹, 余朝军, 等. 基于自适应固定时间的直接升力着舰容错控制[J]. 电光与控制, 2023, 30(9): 29-35,98.
HE Shengtao, JIANG Ju, YU Chaojun, et al. Fault-tolerant control of direct lift carrier landing based on adaptive fixed time[J]. Electronics optics & control, 2023, 30(9): 29-35,98.
[15] GUAN Zhiyuan, LIU Hu, ZHENG Zewei, et al. Moving path following with integrated direct lift control for carrier landing[J]. Aerospace science and technology, 2022, 120: 107247.
[16] SILVER D, SCHRITTWIESER J, SIMONYAN K, et al. Mastering the game of Go without human knowledge[J]. Nature, 2017, 550(7676): 354-359.
[17] ZHU Zeyu, ZHAO Huijing. A survey of deep RL and IL for autonomous driving policy learning[J]. IEEE transactions on intelligent transportation systems, 2022, 23(9): 14043-14065.
[18] WANG Ning, GAO Ying, ZHANG Xuefeng. Data-driven performance-prescribed reinforcement learning control of an unmanned surface vehicle[J]. IEEE transactions on neural networks and learning systems, 2021, 32(12): 5456-5467.
[19] LI Bo, GAN Zhigang, CHEN Daqing, et al. UAV maneuvering target tracking in uncertain environments based on deep reinforcement learning and meta-learning[J]. Remote sensing, 2020, 12(22): 3789.
[20] LU Yanqi, WU Chengwei, YAO Weiran, et al. Deep reinforcement learning control of fully-constrained cable-driven parallel robots[J]. IEEE transactions on industrial electronics, 2023, 70(7): 7194-7204.
[21] WU Hui, SONG Shiji, YOU Keyou, et al. Depth control of model-free AUVs via reinforcement learning[J]. IEEE transactions on systems, man, and cybernetics: systems, 2019, 49(12): 2499-2510.
[22] WANG Zhikun, GRO? R, ZHAO Shiyu. Aerobatic tic-toc control of planar quadcopters via reinforcement learning[J]. IEEE robotics and automation letters, 2022, 7(2): 2140-2147.
[23] 付宇鹏, 邓向阳, 何明, 等. 基于强化学习的固定翼飞机姿态控制方法[J]. 控制与决策, 2023, 38(9): 2505-2510.
FU Yupeng, DENG Xiangyang, HE Ming, et al. Reinforcement learning based attitude controller design[J]. Control and decision, 2023, 38(9): 2505-2510.
[24] HAN Haoran, CHENG Jian, XI Zhilong, et al. Cascade flight control of quadrotors based on deep reinforcement learning[J]. IEEE robotics and automation letters, 2022, 7(4): 11134-11141.
[25] 张志冰, 甄子洋, 江驹, 等. 舰载机自动着舰引导与控制综述[J]. 南京航空航天大学学报, 2018, 50(6): 734-744.
ZHANG Zhibing, ZHEN Ziyang, JIANG Ju, et al. Review on development in guidance and control of automatic carrier landing of carrier-based aircraft[J]. Journal of Nanjing University of Aeronautics & Astronautics, 2018, 50(6): 734-744.
[26] 夏桂华, 董然, 许江涛, 等. 考虑扰流的舰载机终端进场线性模型[J]. 航空学报, 2016, 37(3): 970-983.
XIA Guihua, DONG Ran, XU Jiangtao, et al. Linearized carrier-based aircraft model in final approach phase with air turbulence considered[J]. Acta aeronautica et astronautica sinica, 2016, 37(3): 970-983.
[27] 范彦铭. 飞行控制[M]. 北京: 航空工业出版社, 2021: 295-304.
FAN Yanming. Flight control[M]. Beijing: Aviation Industry Press, 2021: 295-304.
[28] ZHEN Ziyang, JIANG Shuoying, MA Kun. Automatic carrier landing control for unmanned aerial vehicles based on preview control and particle filtering[J]. Aerospace science and technology, 2018, 81(6): 99-107.
[29] 吴文海, 汪节, 高丽, 等. MAGIC CARPET着舰技术分析[J]. 系统工程与电子技术, 2018, 40(9): 2079-2091.
WU Wenhai, WANG Jie, GAO Li, et al. Analysis on MAGIC CARPET carrier landing technology[J]. Systems engineering and electronics, 2018, 40(9): 2079-2091.
[30] FUJIMOTO S, VAN H V, MEGER D. Addressing function approximation error in actor-critic methods[C]//35th International conference on machine learning. San Diego: JMLR, 2018: 1587-1596.
[31] CHU Zhenzhong, SUN Bo, ZHU Daqi, et al. Motion control of unmanned underwater vehicles via deep imitation reinforcement learning algorithm[J]. IET intelligent transport systems, 2020, 14(7): 764-774.
[32] LEE S, LEE J, LEE S, et al. Sliding mode guidance and control for UAV carrier landing[J]. IEEE transactions on aerospace and electronic systems, 2019, 55(2): 951-966.
[33] GUAN Zhiyuan, MA Yunpeng, ZHENG Zewei, et al. Prescribed performance control for automatic carrier landing with disturbance[J]. Nonlinear dynamics, 2018, 94(2): 1335-1349.
- 相似文献/References:
-
[1]朱杰斌,秦世引.无人机编队飞行的分布式控制策略与控制器设计[J].智能系统学报,2010,5(5):392.[doi:10.3969/j.issn.1673-4785.2010.05.003]
ZHU Jie-bin,QIN Shi-yin.Distributed control strategy and controller design for UAV formation flight[J].CAAI Transactions on Intelligent Systems,2010,5():392.[doi:10.3969/j.issn.1673-4785.2010.05.003]
备注/Memo
收稿日期:2023-12-19。
基金项目:国家自然科学基金项目(52171299, 62173103); 黑龙江省自然科学基金项目(LH2024F037); 中央高校基本科研业务费专项资金项目(3072024XX0403).
作者简介:王子博，博士研究生，主要研究方向为飞行制导与控制、智能控制。E-mail：wang_zi_bo@163.com;朱齐丹，教授，博士生导师，黑龙江省自动化学会常务理事。主要研究方向为智能机器人技术及应用、智能控制系统设计、图像处理与模式识别。主持国家自然科学基金项目、国家重点基础研究发展计划项目、工业和信息化部高技术船舶科研项目、科工局国防基础研究重点项目、科技部国际合作项目、海军装备“十四五”预研项目等近30项。获国家科技进步二等奖1项、国防科技进步一等奖3项、军队科技进步一等奖1项、黑龙江省科技进步二等奖3项，获发明专利授权20项、软件著作权5项。发表学术论文200余篇，出版专著4部。E-mail：zhuqidan@hrbeu.edu.cn;孔令鑫，博士研究生，主要研究方向为飞行器非线性自适应控制、鲁棒控制。E-mail：konglingxin@hrbeu.edu.cn。
通讯作者:朱齐丹. E-mail：zhuqidan@hrbeu.edu.cn
更新日期/Last Update:
2025-03-05