航空学报2025，Vol.46Issue(24)：36-47,12.DOI:10.7527/S1000-6893.2025.32345
基于深度强化学习调参的制导控制一体化方法
Integrated guidance and control method based on deep reinforcement learning parameter tuning
摘要
Abstract
To address the dynamic optimization problem of guidance and control parameters of hypersonic flight ve-hicles,a Deep reinforcement learning parameter tuning method based on the Twin Delayed Deep Deterministic policy gradient(TD3)algorithm is proposed.Firstly,the motion model of the hypersonic flight vehicle and the integrated model of guidance and control were established,and the controller based on the backstepping method was designed.The consistent final boundedness was proved via Lyapunov stability.Then,the controller parameter optimization prob-lem was transformed into a Markov decision process model,and the data-driven online adaptive optimization of con-troller parameters was achieved based on the TD3 algorithm.This method constructs a parameter optimization mecha-nism that integrates the prior knowledge of the model and data-driven approaches,significantly enhancing the autono-mous adaptability of the controller in the parameter space.Finally,the effectiveness and robustness of the proposed method were verified through numerical simulation.关键词
高超声速飞行器/制导控制一体化/深度强化学习/自适应参数/反步控制Key words
hypersonic flight vehicle/integrated guidance and control/deep reinforcement learning/adaptive parameters/backstepping control分类
航空航天引用本文复制引用
XIE Qichao,CAO Chengyu,ZHAO Yiyun,LI Fanbiao..基于深度强化学习调参的制导控制一体化方法[J].航空学报,2025,46(24):36-47,12.基金项目
国家自然科学基金大飞机基础研究联合基金重点支持项目(U2570207) （U2570207）
国家优秀青年科学基金(62222317) （62222317）
湖南省科技重大专项(2021GK1030) （2021GK1030）
湖南省重点研发计划(2023GK2023) Key Program of the Joint Fund for Basic Research on Large Aircraft of the National Natural Science Foundation of China(U2570207) （2023GK2023）
National Science Fund for Excellent Young Scholars(62222317) （62222317）
Hunan Provincial Key Technology Innovation Program(2021GK1030) （2021GK1030）
Key Research and Development Program of Hunan Province(2023GK2023) （2023GK2023）
