自动化学报2025，Vol.51Issue(6)：1305-1319,15.DOI:10.16383/j.aas.c240639
基于深度强化学习的无人机自主感知-规划-控制策略
Autonomous Perception-Planning-Control Strategy Based on Deep Reinforcement Learning for Unmanned Aerial Vehicles
摘要
Abstract
In recent years,with the rapid development of deep reinforcement learning(DRL)methods,their applic-ation 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 al-gorithms are often limited by their dependence on global information and the constraints of specific training envir-onments,greatly limiting their potential for application in various scenarios.To address these issues,multi-scale in-put is proposed to balance the receptive field and the state dimension,and truncation operation is proposed to en-able the agent to operate in the expanded environment.In addition,the autonomous perception-planning-control ar-chitecture is constructed to give the UAV the ability to navigate autonomously in diverse and complex environ-ments.关键词
无人机/深度强化学习/自主导航/复杂未知环境Key words
Unmanned aerial vehicle/deep reinforcement learning/autonomous navigation/complex unknown en-vironment引用本文复制引用
吕茂隆,丁晨博,韩浩然,段海滨..基于深度强化学习的无人机自主感知-规划-控制策略[J].自动化学报,2025,51(6):1305-1319,15.基金项目
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Supported by National Natural Science Foundation of China(62303489,GKJJ24050502,62350048,T2121003),Post-Doctoral Foundation(2022M723877),Post-Doctoral Special Grant(2023T160790),China Post-Doctoral International Exchange In-troduction Program(YJ20220347),Shaanxi Provincial Youth Talent Promotion Project(20220101),and Shaanxi Natural Sci-ence Basic Research Program(2024JC-YBQN-0668,2025JC-QYCX-052) （62303489,GKJJ24050502,62350048,T2121003）
