基于深度强化学习的变形滑翔飞行器智能变形决策方法

王滔鋆; 孟凡一; 陈刚

doi:null

您当前的位置：

首页 >

文章列表页 >

基于深度强化学习的变形滑翔飞行器智能变形决策方法

更新时间：2026-01-26

- 基于深度强化学习的变形滑翔飞行器智能变形决策方法
- Intelligent Deformation Decision-making Method for Morphing Glide Vehicle with Deep Reinforcement Learning
- 西安交通大学学报 2026年
- 作者机构：
  
  西安交通大学航天航空学院，710049，西安
- 作者简介：
- 基金信息：
- DOI：
  中图分类号： V448
- 收稿：2025-06-05，
  
  修回：2025-12-29，
  
  录用：2026-01-26，
- 稿件说明：
移动端阅览
王滔鋆, 孟凡一, 陈刚. 基于深度强化学习的变形滑翔飞行器智能变形决策方法[J/OL]. 西安交通大学学报, 2026.

WANG Taojun, MENG Fanyi, CHEN Gang. Intelligent Deformation Decision-making Method for Morphing Glide Vehicle with Deep Reinforcement Learning[J/OL]. JOURNAL OF XI’AN JIAOTONG UNIVERSITY, 2026.
王滔鋆, 孟凡一, 陈刚. 基于深度强化学习的变形滑翔飞行器智能变形决策方法[J/OL]. 西安交通大学学报, 2026. DOI：

WANG Taojun, MENG Fanyi, CHEN Gang. Intelligent Deformation Decision-making Method for Morphing Glide Vehicle with Deep Reinforcement Learning[J/OL]. JOURNAL OF XI’AN JIAOTONG UNIVERSITY, 2026. DOI：

摘要

为了充分发挥变形滑翔飞行器（MGV）相较于传统固定构型飞行器在航程、速度及环境适应性方面的显著优势，解决多物理场耦合下的最优变形构型决策难题，本文提出了一种基于深度强化学习的智能变形决策方法。首先，利用深度神经网络构建翼面变形与气动性能的代理模型，实现了从变形动作到气动数据的端到端快速映射；然后，结合飞行器纵向运动模型建立强化学习框架，并通过算法性能对比，选用近端策略优化（PPO）算法构建智能决策模型，实现了气动/变形/弹道交叉耦合下的自主策略学习；最后，在训练范围外的拉偏环境中进行全流程仿真实验验证。结果表明：该方法能够综合气动/变形/弹道耦合影响进行智能变形决策，使MGV终端射程增加了7.304%，并能有效维持较高的升阻比飞行状态；同时，拉偏测试证明了该方法在不确定环境下依然具备良好的可行性与泛化能力。

Abstract

To fully exploit the significant advantages of Morphing Gliding Vehicles (MGVs) over traditional fixed-configuration vehicles in terms of range

speed

and environmental adaptability

and to address the challenge of optimal configuration decision-making under multi-physics coupling

this paper proposes an intelligent morphing decision-making method based on deep reinforcement learning. Firstly

a deep neural network is employed to construct a surrogate model for wing deformation and aerodynamic performance

facilitating a rapid end-to-end mapping from morphing actions to aerodynamic data. Secondly

a decision-making framework is established by combining the longitudinal motion model with reinforcement learning. Through comparative analysis of algorithm performance

the Proximal Policy Optimization (PPO) algorithm is selected to construct the intelligent model

enabling autonomous strategy learning under the cross-coupling of aerodynamics

morphing

and trajectory. Finally

full-process simulation experiments are conducted in deviated environments outside the training envelope. The results indicate that the proposed method achieves intelligent decision-making by comprehensively considering the cross-coupling of aerodynamics

morphing

and trajectory

increasing the terminal range of the MGV by 7.304%

while effectively maintaining a high lift-to-drag ratio. Furthermore

deviation tests confirm the method's feasibility and generalization capability in adapting to uncertain environmental challenges.

关键词

Keywords

references

SHI R , SONG J . Dynamics and control for an in-plane morphing wing [J ] . Aircraft Engineering and Aerospace Technology , 2013 , 85 ( 1 ): 24 - 31 .

王青 , 王通 , 董朝阳 , 等 . 变体飞行器链式平滑切换控制 [J ] . 控制理论与应用 , 2015 , 32 ( 7 ): 949 - 954 .

WANG Q , WANG T , DONG C , et al . Chained smooth switching control for morphing aircraft [J ] . Control Theory and Applications , 2015 , 32 ( 7 ): 949 - 954 .

郭雷 , 王恩美 , 卢昊 , 等 . 仿生变构型飞行器智能控制技术: 进展与展望 [J ] . 上海航天(中英文) , 2022 , 39 ( 4 ): 25 - 32 .

GUO L , WANG E , LU H , et al . Intelligent Control Technologies for Bio-inspired Morphing Flight Vehicles: Progress and Prospect [J ] . Aerospace Shanghai (Chinese & English) , 2022 , 39 ( 4 ): 25 - 32 .

王子健 , 张书宇 , 侯明哲 . 基于在线参数辨识的变体飞行器控制 [J ] . 兵器装备工程学报 , 2022 , 43 ( 10 ): 60 - 65 .

WANG Z , ZHANG S , HOU M . Morphing aircraft control based on online parameter identification [J ] . Journal of Ordnance Equipment Engineering , 2022 , 43 ( 10 ): 60 - 65 .

BAO W , LU X , BAI G , et al . Exploration on the frontiers of flexible and deformable cross-domain intelligent flight [J ] . Aerospace China , 2021 , 22 ( 1 ): 5 - 11 .

PALACIOS R , MURUA J , COOK R . Structural and aerodynamic models in nonlinear flight dynamics of very flexible aircraft [J ] . AIAA Journal , 2010 , 48 ( 11 ): 2648 - 2659 .

郭东 , 徐敏 , 陈士橹 . 弹性飞行器飞行动力学建模研究 [J ] . 空气动力学学报 , 2013 , 31 ( 04 ): 413 - 419, 436 .

GUO L , XU M , CHEN S . Research on flight dynamic modeling of highly flexible aircrafts [J ] . Acta Aerodynamica Sinica , 2013 , 31 ( 04 ): 413 - 419, 436 .

CHEN X , LI C , GONG C , et al . A study of morphing aircraft on morphing rules along trajectory [J ] . Chinese Journal of Aeronautics , 2012 , 34 ( 7 ): 232 – 243 .

YUE T , ZHANG X , WANG L , et al . Flight dynamic modeling and control for a telescopic wing morphing aircraft via asymmetric wing morphing [J ] . Aerospace Science and Technology , 2017 , 70 : 328 – 338 .

YUE T , WANG L , AI J . Longitudinal Linear Parameter Varying Modeling and Simulation of Morphing Aircraft [J ] . Journal of Aircraft , 2013 , 50 ( 6 ): 1673 – 1681 .

GONG L , WANG Q , HU C , et al . Switching control of morphing aircraft based on Q-learning [J ] . Chinese Journal of Aeronautics , 2020 , 33 ( 2 ): 672 – 687 .

BAO C , WANG P , TANG G . Integrated method of guidance, control and morphing for hypersonic morphing vehicle in glide phase [J ] . Chinese Journal of Aeronautics , 2021 , 34 ( 5 ): 535 – 553 .

SILVER D , LEVER G , HEESS N , et al . Deterministic Policy Gradient Algorithms [C ] . Proceedings of the International Conference on Machine Learning , Beijing, China , 2014 .

SCHULMAN J , WOLSKI F , DHARIWAL P , et al . Proximal Policy Optimization Algorithms [A/OL ] . arXiv , 2017 [ 2023-06-30 ] . http://arxiv.org/abs/1707.06347 http://arxiv.org/abs/1707.06347 . DOI: 10.48550/arXiv.1707.06347 http://dx.doi.org/10.48550/arXiv.1707.06347 .

LILLICRAP T , HUNT J , PRITZEL A , et al . Continuous control with deep reinforcement learning [C ] . Proceedings of The Twelfth International Conference on Learning Representations , San Juan , Puerto Rico , United States , 2015 .

BHATNAGAR S , SUTTON R , GHAVAMZADEH M , LEE M . Natural actor–critic algorithms [J ] . Automatica , 2009 , 45 ( 11 ): 2471 – 2482 .

CHEN W , GAO C , JING W . Proximal policy optimization guidance algorithm for intercepting near-space maneuvering targets [J ] . Aerospace Science and Technology , 2023 , 132 : 108031 .

闫斌斌 , 李勇 , 戴沛 , 等 . 基于增强学习的变体飞行器自适应变体策略与飞行控制方法研究 [J ] . 西北工业大学学报 , 2019 , 37 ( 4 ): 656 - 663 .

YAN B , LI Y , DAI P , et al . Adaptive Wing Morphing Strategy and Flight Control Method of a Morphing Aircraft Based on Reinforcement Learning [J ] . Journal of Northwestern Polytechnical University , 2019 , 37 ( 4 ): 656 - 663 .

XU W , LI Y , PEI B , et al . Coordinated intelligent control of the flight control system and shape change of variable sweep morphing aircraft based on dueling-DQN [J ] . Aerospace Science and Technology , 2022 , 130 : 107898 .

LAMPTON A , NIKSCH A , VALASEK J . Reinforcement learning of morphing airfoils with aerodynamic and structural effects [J ] . Journal of Aerospace Computing, Information, and Communication , 2009 , 6 ( 1 ): 30 - 50 .

LAMPTON A , NIKSCH A , VALASEK J . Reinforcement Learning of a Morphing Airfoil-Policy and Discrete Learning Analysis [C ] . AIAA Guidance, Navigation and Control Conference and Exhibit , Honolulu, Hawaii , 2008 .

TANDALE M , RONG J , VALASEK J , Preliminary Results of Adaptive Reinforcement Learning Control for Morphing Aircraft [C ] . AIAA Guidance, Navigation, and Control Conference and Exhibit, Providence, Rhode Island , 2004 .

VALASEK J , TANDALE M , RONG J . A reinforcement learning-adaptive control architecture for morphing [J ] . Journal of Aerospace Computing, Information, and Communication , 2005 , 2 ( 4 ): 174 - 195 .

XU D , HUI Z , Liu Y , CHEN G . Morphing control of a new bionic morphing UAV with deep reinforcement learning [J ] . Aerospace Science and Technology , 2019 , 92 : 232 - 243 .

GOECKS V , LEAL P , WHITE T , et al . Control of morphing wing shapes with deep reinforcement learning [C ] . Proceedings of AIAA Scitech 2018 forum , Kissimmee, Florida, United States , 2018 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向变形滑翔飞行器的智能变形决策方法

联合联邦学习与深度强化学习的并行服务功能链部署算法

引入深度强化学习思想的脑-机协作精密操控方法

伺服系统瞬态优化的模糊自适应深度强化学习方法

面向储能辅助火电机组一次调频的深度强化学习控制策略