Flocking formation of unmanned aerial vehicles (UAVs) is an open challenge due to kinematics complexity and uncertainties in complex environments. In this paper, the UAV flocking control problem is formulated as a partially observable Markov decision process (POMDP) and solved by deep reinforcing learning. In particular, we consider a leader-follower configuration, where consensus among all UAVs is used to train a shared control policy, and each UAV performs actions based on the local information it collects. In addition, to avoid collision among UAVs and guarantee flocking and navigation, a reward function is added with the global flocking maintenance, mutual reward, and a collision penalty. We adapt deep deterministic policy gradient (DDPG) with centralized training and decentralized execution to obtain the flocking control policy using actor-critic networks and a global state space matrix. The simulation results demonstrate that the trained optimal policy converges to flocking formation without parameter tuning and has good generalization ability for different UAVs.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Deep Reinforcement Learning for Flocking Control of UAVs in Complex Environments


    Beteiligte:


    Erscheinungsdatum :

    19.11.2021


    Format / Umfang :

    4979577 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Deep Reinforcement Learning Attitude Control of Fixed-Wing UAVs

    Zhen, Yan / Hao, Mingrui / Sun, Wendi | IEEE | 2020


    Deep reinforcement learning as control method for autonomous UAVs

    Kersandt, Kjell | BASE | 2018

    Freier Zugriff

    Flocking Control of UAV Swarms with Deep Reinforcement Leaming Approach

    Yan, Peng / Bai, Chengchao / Zheng, Hongxing et al. | IEEE | 2020


    Induction Radius-Based Hierarchical Flocking Algorithm for UAVs Clustering

    Qiao, Xuhui / Xu, Ziqiang / Luo, Yanhong et al. | IEEE | 2019