Flocking and Collision Avoidance for a Dynamic Squad of Fixed-Wing UAVs Using Deep Reinforcement Learning

被引:10
|
作者
Yan, Chao [1 ]
Xiang, Xiaojia [1 ]
Wang, Chang [1 ]
Lan, Zhen [1 ]
机构
[1] Natl Univ Def Technol, Coll Intelligence Sci & Technol, Changsha 410073, Peoples R China
基金
中国国家自然科学基金;
关键词
D O I
10.1109/IROS51168.2021.9636183
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Developing the flocking behavior for a dynamic squad of fixed-wing UAVs is still a challenge due to kinematic complexity and environmental uncertainty. In this paper, we deal with the decentralized flocking and collision avoidance problem through deep reinforcement learning (DRL). Specifically, we formulate a decentralized DRL-based decision making framework from the perspective of every follower, where a collision avoidance mechanism is integrated into the flocking controller. Then, we propose a novel reinforcement learning algorithm PS-CACER for training a shared control policy for all the followers. Besides, we design a plug-n-play embedding module based on convolutional neural networks and the attention mechanism. As a result, the variable-length system state can be encoded into a fixed-length embedding vector, which makes the learned DRL policy independent with the number and the order of followers. Finally, numerical simulation results demonstrate the effectiveness of the proposed method, and the learned policies can be directly transferred to semi-physical simulation without any parameter finetuning.
引用
收藏
页码:4738 / 4744
页数:7
相关论文
共 50 条
  • [1] Fixed-Wing UAVs flocking in continuous spaces: A deep reinforcement learning approach
    Yan, Chao
    Xiang, Xiaojia
    Wang, Chang
    [J]. ROBOTICS AND AUTONOMOUS SYSTEMS, 2020, 131
  • [2] Deep Reinforcement Learning of Collision-Free Flocking Policies for Multiple Fixed-Wing UAVs Using Local Situation Maps
    Yan, Chao
    Wang, Chang
    Xiang, Xiaojia
    Lan, Zhen
    Jiang, Yuna
    [J]. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2022, 18 (02) : 1260 - 1270
  • [3] Reinforcement Learning-Based Collision Avoidance Guidance Algorithm for Fixed-Wing UAVs
    Zhao, Yu
    Guo, Jifeng
    Bai, Chengchao
    Zheng, Hongxing
    [J]. COMPLEXITY, 2021, 2021
  • [4] Deep Reinforcement Learning Attitude Control of Fixed-Wing UAVs
    Zhen, Yan
    Hao, Mingrui
    Sun, Wendi
    [J]. PROCEEDINGS OF 2020 3RD INTERNATIONAL CONFERENCE ON UNMANNED SYSTEMS (ICUS), 2020, : 239 - 244
  • [5] A Continuous Actor-Critic Reinforcement Learning Approach to Flocking with Fixed-Wing UAVs
    Wang, Chang
    Yan, Chao
    Xiang, Xiaojia
    Zhou, Han
    [J]. ASIAN CONFERENCE ON MACHINE LEARNING, VOL 101, 2019, 101 : 64 - 79
  • [6] Flocking Control of Fixed-Wing UAVs With Cooperative Obstacle Avoidance Capability
    Zhao, Weiwei
    Chu, Hairong
    Zhang, Mingyue
    Sun, Tingting
    Guo, Lihong
    [J]. IEEE ACCESS, 2019, 7 : 17798 - 17808
  • [7] Cooperative formation control of fixed-wing UAVs based on deep reinforcement learning
    Yue, Keyuan
    Yuan, Jianquan
    Hao, Mingrui
    [J]. SEVENTH ASIA PACIFIC CONFERENCE ON OPTICS MANUFACTURE (APCOM 2021), 2022, 12166
  • [8] Leader-Follower Formation Control for Fixed-Wing UAVs using Deep Reinforcement Learning
    Shi, Yu
    Song, Jianshuang
    Hua, Yongzhao
    Yu, Jianglong
    Dong, Xiwang
    Ren, Zhang
    [J]. 2022 41ST CHINESE CONTROL CONFERENCE (CCC), 2022, : 3456 - 3461
  • [9] Deep Reinforcement Learning Attitude Control of Fixed-Wing UAVs Using Proximal Policy Optimization
    Bohn, Eivind
    Coates, Erlend M.
    Moe, Signe
    Johansen, Tor Arne
    [J]. 2019 INTERNATIONAL CONFERENCE ON UNMANNED AIRCRAFT SYSTEMS (ICUAS' 19), 2019, : 523 - 533
  • [10] Reinforcement Learning Based Assistive Collision Avoidance for Fixed-Wing Unmanned Aerial Vehicles
    d'Apolito, Francesco
    Sulzbachner, Christoph
    [J]. 2023 IEEE/AIAA 42ND DIGITAL AVIONICS SYSTEMS CONFERENCE, DASC, 2023,