智能系统学报2025，Vol.20Issue(2)：416-424,9.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
Automatic landing control of carrier-based aircraft based on reinforcement learning and direct lift
摘要
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 air-craft.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 non-linear fitting using a neural network trained by deep reinforcement learning algorithms.This approach improves the pre-cision of the aircraft to the ideal glide path in the presence of disturbances and eliminates the need for complicated para-meter 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,su-perior capability to restrict the effects of carrier air wake disturbance,and improved landing precision.关键词
舰载机着舰/飞行控制/强化学习/直接升力控制/制导律/舰尾流/神经网络/路径跟踪Key words
landing of carrier-based aircraft/flight control/reinforcement learning/direct lift control/guidance law/car-rier air wake/neural network/path tracking分类
信息技术与安全科学引用本文复制引用
王子博,朱齐丹,孔令鑫,王立鹏..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):416-424,9.基金项目
国家自然科学基金项目(52171299,62173103) （52171299,62173103）
黑龙江省自然科学基金项目(LH2024F037) （LH2024F037）
中央高校基本科研业务费专项资金项目(3072024XX0403). （3072024XX0403）
