Task Assignment of UAV Swarms Based on Deep Reinforcement Learning

被引:6
|
作者
Liu, Bo [1 ]
Wang, Shulei [1 ]
Li, Qinghua [1 ]
Zhao, Xinyang [1 ]
Pan, Yunqing [1 ]
Wang, Changhong [1 ]
机构
[1] Harbin Inst Technol, Space Control & Inertial Technol Res Ctr, Harbin 150000, Peoples R China
关键词
UAV swarm; task assignment; deep reinforcement learning; Ex-MADDPG; ALLOCATION;
D O I
10.3390/drones7050297
中图分类号
TP7 [遥感技术];
学科分类号
081102 ; 0816 ; 081602 ; 083002 ; 1404 ;
摘要
UAV swarm applications are critical for the future, and their mission-planning and decision-making capabilities have a direct impact on their performance. However, creating a dynamic and scalable assignment algorithm that can be applied to various groups and tasks is a significant challenge. To address this issue, we propose the Extensible Multi-Agent Deep Deterministic Policy Gradient (Ex-MADDPG) algorithm, which builds on the MADDPG framework. The Ex-MADDPG algorithm improves the robustness and scalability of the assignment algorithm by incorporating local communication, mean simulation observation, a synchronous parameter-training mechanism, and a scalable multiple-decision mechanism. Our approach has been validated for effectiveness and scalability through both simulation experiments in the Multi-Agent Particle Environment (MPE) and a real-world experiment. Overall, our results demonstrate that the Ex-MADDPG algorithm is effective in handling various groups and tasks and can scale well as the swarm size increases. Therefore, our algorithm holds great promise for mission planning and decision-making in UAV swarm applications.
引用
收藏
页数:21
相关论文
共 50 条
  • [1] Task Assignment for UAV Swarm Saturation Attack: A Deep Reinforcement Learning Approach
    Qian, Feng
    Su, Kai
    Liang, Xin
    Zhang, Kan
    [J]. ELECTRONICS, 2023, 12 (06)
  • [2] Deep Reinforcement Learning Task Assignment Based on Domain Knowledge
    Liu, Jiayi
    Wang, Gang
    Guo, Xiangke
    Wang, Siyuan
    Fu, Qiang
    [J]. IEEE Access, 2022, 10 : 114402 - 114413
  • [3] Deep Reinforcement Learning Task Assignment Based on Domain Knowledge
    Liu, Jiayi
    Wang, Gang
    Guo, Xiangke
    Wang, Siyuan
    Fu, Qiang
    [J]. IEEE ACCESS, 2022, 10 : 114402 - 114413
  • [4] Flocking Control of UAV Swarms with Deep Reinforcement Learning Approach
    Yan, Peng
    Bai, Chengchao
    Zheng, Hongxing
    Guo, Jifeng
    [J]. PROCEEDINGS OF 2020 3RD INTERNATIONAL CONFERENCE ON UNMANNED SYSTEMS (ICUS), 2020, : 592 - 599
  • [5] A Method of Multi-UAV Cooperative Task Assignment Based on Reinforcement Learning
    Zhao, Xiaohu
    Jiang, Hanli
    An, Chenyang
    Wu, Ruocheng
    Guo, Yijun
    Yang, Daquan
    [J]. MOBILE INFORMATION SYSTEMS, 2022, 2022
  • [6] Task Assignment of UAV Swarms Based on Auction Algorithm in Poor Communication Environments
    Chen, Zihao
    Li, Juan
    Liu, Chang
    Li, Jie
    [J]. JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS, 2023, 27 (06) : 1142 - 1150
  • [7] Deep Reinforcement Learning for Task Assignment in Spatial Crowdsourcing and Sensing
    Sun, Lijun
    Yu, Xiaojie
    Guo, Jiachen
    Yan, Yang
    Yu, Xu
    [J]. IEEE SENSORS JOURNAL, 2021, 21 (22) : 25323 - 25330
  • [8] Digital-Twin-Assisted Task Assignment in Multi-UAV Systems: A Deep Reinforcement Learning Approach
    Tang, Xin
    Li, Xiaohuan
    Yu, Rong
    Wu, Yuan
    Ye, Jin
    Tang, Fengzhu
    Chen, Qian
    [J]. IEEE INTERNET OF THINGS JOURNAL, 2023, 10 (17): : 15362 - 15375
  • [9] Task assignment in ground-to-air confrontation based on multiagent deep reinforcement learning
    Jia-yi Liu
    Gang Wang
    Qiang Fu
    Shao-hua Yue
    Si-yuan Wang
    [J]. Defence Technology, 2023, 19 (01) : 210 - 219
  • [10] Task assignment in ground-to-air confrontation based on multiagent deep reinforcement learning
    Liu, Jia-yi
    Wang, Gang
    Fu, Qiang
    Yue, Shao-hua
    Wang, Si-yuan
    [J]. DEFENCE TECHNOLOGY, 2023, 19 : 210 - 219