无线电工程2025，Vol.55Issue(9)：1869-1876,8.DOI:10.3969/j.issn.1003-3106.2025.09.014
基于改进指针网络的无人机数据采集路径规划
UAV Data Collection Path Planning Based on Improved Pointer Network
摘要
Abstract
Due to the limited battery capacity of UAVs,it is impossible to complete data collection from all sensor points in a single flight mission.The UAVs need multiple trips between charging stations for energy replenishment.To solve the problem of path planning of rechargeable UAV data collection under limited energy,a deep reinforcement learning algorithm is developed.A sequence decision model is established by a pointer network to solve the combinatorial optimization problem.To improve the decision output of the Pointer Networks(PN)model,parameters are trained through the Actor-Critic reinforcement learning framework,and short-term prediction of UAV decisions is conducted.The simulation results show that the convergence rate of the proposed algorithm has increased by more than 10%,and the optimal results of the algorithm have improved by 7%～17%.The proposed algorithm not only significantly enhances the efficiency of UAV task execution,but also improves the revenue of UAV data collection.关键词
无人机数据采集任务规划/组合优化问题/指针网络/Actor-Critic/深度强化学习Key words
UAV data collection mission planning/combinatorial optimization problem/pointer network/Actor-Critic/deep reinforcement learning分类
信息技术与安全科学引用本文复制引用
陈修恒,左燕,彭冬亮..基于改进指针网络的无人机数据采集路径规划[J].无线电工程,2025,55(9):1869-1876,8.基金项目
国家自然科学基金(61673146) （61673146）
浙江省自然科学基金重点项目(LZ23F030002)National Natural Science Foundation of China(61673146) （LZ23F030002）
Key Program of Zhejiang Provincial Natural Science Foun-dation of China(LZ23F030002) （LZ23F030002）
