首页|基于强化学习的无人机智能组网技术及应用综述

基于强化学习的无人机智能组网技术及应用综述

扫码查看
原文链接
  • 万方数据
  • 维普
针对无人机在民用和军事等领域中的研究热度及应用需求日益增长,传统 Mode1-Based 的网络部署、设计、操作方法无法应对动态变化的无人机场景的问题,本文综述了灵活性高、适应性强的 AI-Based 的智能组网技术,并引入强化学习这一人工智能领域的重要分支.对现有利用强化学习技术解决无人机组网难题的研究进行了概述,结合无人机组网的特性梳理了此领域应用强化学习技术的主要思路.从几个应用场景,以及组网关键技术的角度进行了归纳,给出了基于强化学习的无人机智能组网技术所面临的机遇与挑战,并进行了总结.探究了无人机通信的感知能力与决策能力,适应了其动态变化且需要高度自治的环境需求.为未来无人机智能组网技术的发展提供了有价值的理论基础和实践指导.
Review of unmanned aerial vehicle intelligent networking technology and applications based on reinforcement learning
With the increasing research interest and application demand for unmanned aerial vehicles in both civil and military fields,traditional model-based network deployment,design,and operation methods can hardly cope with dynamically changing unmanned aerial vehicles scenarios.This paper reviews AI-based intelligent networking technology,which offers high flexibility and adaptability and introduces reinforcement learning as an important branch of artificial intelligence.It briefly describes the current research status on the use of reinforcement learning techniques,addresses the difficulties in unmanned aerial vehicles networking,and outlines the main ideas for ap-plying reinforcement learning techniques in this field by combining them with the characteristics of unmanned aerial vehicles networking.The paper reviews several application scenarios and key networking technologies,highlighting the opportunities and challenges encountered by intelligent unmanned aerial vehicles networking technology based on reinforcement learning.The paper concludes that the research enhances unmanned aerial vehicles communica-tion by improving perception and decision-making capabilities,meeting the needs of dynamically changing environ-ments that demand a high degree of autonomy.Additionally,it provides valuable theoretical foundations and practi-cal guidance for the future development of intelligent unmanned aerial vehicles networking technology.

flying Ad Hoc networkreinforcement learningdeep Q-network algorithmmultiagentunmanned aeri-al vehicles swarmintelligent routingresource allocationcross-layer optimization

邱修林、宋博、殷俊、徐雷、柯亚琪、廖振强、杨余旺

展开 >

江苏科技大学 自动化学院,江苏 镇江 212100

南京理工大学 计算机科学与工程学院,江苏 南京 210094

南京邮电大学 江苏省宽带无线通信重点实验室,江苏 南京 210003

苏州高博软件技术职业学院 机电工程学院,江苏 苏州 215163

展开 >

飞行自组网 强化学习 深度Q网络算法 多智能体 无人机集群 智能路由 资源分配 跨层优化

国家自然科学基金项目国家自然科学基金项目国家自然科学基金项目苏州市重点产业技术创新项目

619731616199140461773206SYG201826

2024

10.11990/jheu.202205010

哈尔滨工程大学学报
哈尔滨工程大学

哈尔滨工程大学学报

CSTPCD北大核心
影响因子：0.655
ISSN：1006-7043
年,卷(期)：2024.45(8)