基于强化学习的通信受限环境多无人机协同策略
摘要:文章对基于强化学习的通信受限环境中的多无人机协同架构、通信需求和协同策略进行了分析,旨在提高多无人机协同的合理性,解决多无人机在通信受限环境中出现的问题,发挥强化学习的作用。
关键词:强化学习;通信受限;无人机
doi:10.3969/J.ISSN.1672-7274.2023.12.013
中图分类号:TN 92,TP 18,V 279+.2 文献标志码:A 文章编码:1672-7274(2023)12-00-03
Collaborative Strategy of Multiple Unmanned Aerial Vehicles in Communication Restricted Environment Based on Reinforcement Learning
DENG Limin, CHEN Beibei, LIU Hui
(Nanjing Railway Vocational and Technical College, Nanjing 210031, China)
Abstract: The article analyzes the collaborative architecture, communication requirements, and collaborative strategies of multiple unmanned aerial vehicles (UAVs) in communication constrained environments based on reinforcement learning, aiming to improve the rationality of UAV collaboration, solve the problems that arise in communication constrained environments, and play the role of strong chemical learning.
Key words: reinforcement learning; communication restrictions; unmanned aerial vehicle
1 通信受限环境中的多无人机协同架构
通信受限环境中的多无人机协同架构是指在通信受限的环境,无人机之间如何进行信息交互和协同作业的方式。(剩余4773字)