摘要
近年来,随着深度强化学习(DRL)方法快速发展,其在无人机(UAV)自主导航上的应用也受到越来越广泛的关注.然而,面对复杂未知的环境,现存的基于DRL的UAV自主导航算法常受限于对全局信息的依赖和特定训练环境的约束,极大地限制了其在各种场景中的应用潜力.为解决上述问题,提出多尺度输入用于平衡感受野与状态维度,以及截断操作来使智能体能够在扩张后的环境中运行.此外,构建自主感知−规划−控制架构,赋予UAV在多样复杂环境中自主导航的能力.
In recent years,with the rapid development of deep reinforcement learning(DRL)methods,their application in the field of unmanned aerial vehicle(UAV)autonomous navigation has attracted increasing attention.However,when facing complex and unknown environments,existing DRL-based UAV autonomous navigation algorithms are often limited by their dependence on global information and the constraints of specific training environments,greatly limiting their potential for application in various scenarios.To address these issues,multi-scale input is proposed to balance the receptive field and the state dimension,and truncation operation is proposed to enable the agent to operate in the expanded environment.In addition,the autonomous perception-planning-control architecture is constructed to give the UAV the ability to navigate autonomously in diverse and complex environments.
作者
吕茂隆
丁晨博
韩浩然
段海滨
LV Mao-Long;DING Chen-Bo;HAN Hao-Ran;DUAN Hai-Bin(Air Traffic Control and Navigation College,Air Force En-gineering University,Xi'an 710051;National Key Laborat-ory of Unmanned Aerial Vehicle Technology,Air Force Engineering University,Xi'an 710051;Graduate School,Air Force Engin-eering University,Xi'an 710051;School of Information and Communication Engineering,University of Electronic Science and Technology,Chengdu 611731;National Key Laboratory of Aircraft Integrated Flight Control,School of Automation Sci-ence and Electrical Engineering,Beihang University,Beijing 100083)
出处
《自动化学报》
北大核心
2025年第6期1305-1319,共15页
Acta Automatica Sinica
基金
国家自然科学基金(62303489,GKJJ24050502,62350048,T2121003)
博士后面上基金(2022M723877)
博士后特别资助(2023T160790)
中国博士后国际交流引进计划(YJ20220347)
陕西省青年人才托举工程(20220101)
陕西省自然科学基础研究计划(2024JC-YBQN-0668,2025JC-QYCX-052)资助。
关键词
无人机
深度强化学习
自主导航
复杂未知环境
Unmanned aerial vehicle
deep reinforcement learning
autonomous navigation
complex unknown environment
