城市作战背景下多无人机航路规划仿真研究  

Simulation Research on Multi-UAV Route Planning Under the Background of Urban Combat

作　　者：屠壮 杨柳庆[1,3] 林志坚 张勇 TU Zhuang;YANG Liuqing;LIN Zhijian;ZHANG Yong(College of Automation Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing 210016;Key Laboratory of Unmanned Aerial Vehicle Technology,Ministry of Industry and Information Technology,Nanjing 210016;Research Institute of Pilotless Aircraft,Nanjing University of Aeronautics and Astronautics,Nanjing 210016)

机构地区：[1]南京航空航天大学自动化学院,南京210016 [2]中小型无人机先进技术工业和信息化部重点实验室,南京210016 [3]南京航空航天大学无人机研究院,南京210016

出　　处：《舰船电子工程》2024年第9期48-54,共7页Ship Electronic Engineering

摘　　要：针对城市作战背景下多无人机航路规划问题,论文选用无人机集群系统仿真平台对城市场景进行建模,使用新型航路规划算法自主决策机制算法进行多无人机航路规划。该算法使用深度强化学习对环境进行学习,能够实时地选择算法库中存储的不同算法进行无人机的航路规划。城市场景建模完成后,根据奖励值大小比较该新型算法与其他几种常用的群智能算法在多无人机航路规划问题上性能的优劣。最终将自主决策机制算法加入到无人机集群系统仿真平台中,完成自主决策机制算法的仿真验证。Aiming at the problem of multi-UAV route planning under the background of urban combat,this paper uses the UAV cluster system simulation platform to model the urban scene,and uses the novel route planning algorithm autonomous decision mechanism algorithm to carry out multi-UAV route planning.The algorithm uses deep reinforcement learning to learn the environment,and can select different algorithms stored in the algorithm library in real time for route planning of UAVs.After the urban scene modeling is completed,the performance of the new algorithm is compared with other common swarm intelligence algorithms in multi-UAV route planning according to the reward value.Finally,the autonomous decision mechanism algorithm is added to the UAV cluster system simulation platform to complete the simulation and verification of the autonomous decision mechanism algorithm.

关 键 词：自主决策机制算法 无人机集群仿真 航迹规划 城市场景 

分 类 号：TP212.9[自动化与计算机技术—检测技术与自动化装置]