基于深度强化学习的尾旋改出技术
Aircraft Spin Recovery Technique Based on Deep Reinforcement Learning
谭健美 1王君秋1
作者信息
摘要
本文搭建了飞机仿真环境,基于近端策略优化(PPO)算法建立了尾旋改出算法测试模型,设计了基准版单阶段、基准版双阶段、加深版单阶段、加深版双阶段四种网络结构,用于探究网络结构和改出阶段对尾旋改出效果的影响,设置了鲁棒性测试试验,从时延、误差和高度等方面进行了算法测试和结果分析.
Abstract
This paper builds an aircraft simulation environment,and establishes a test model of an automated spin recovery algorithm based on proximal policy optimization(PPO)algorithm.Four kinds of network structures are de-signed,that are basis single stage,basis double stage,deep single stage and deep double stage,to explore the influ-ence of network structure and recovery stage on spin recovery effect.A robustness test experiment is set up,and the al-gorithm is tested and the results are analyzed from the aspects of delay,error and height.
关键词
尾旋改出/深度学习/强化学习/近端策略优化/算法测试/飞机Key words
spin recovery/deep learning/reinforcement learning/proximal policy optimization/algorithm test/aircraft引用本文复制引用
出版年
2024
国家科技期刊平台
NSTL
万方数据