This paper investigates the optimal performance control problem for the trajectory tracking control for a stratospheric airship with external disturbance. A reinforcement learning adaptive tracking control for a stratospheric airship is proposed. First, according to the knowledge of dynamics and kinematics, we establish the model of a stratospheric airship used in this paper. Then, to solve external disturbance problem and enhance the system performance, a controller is proposed by means of a reinforcement learning (RL) method that is primarily based on two neural networks (NNs). In the last place, the stability analysis and numerical simulations are given to verify that the designed controller is effective.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Reinforcement Learning Adaptive Tracking Control for a Stratospheric Airship


    Additional title:

    Lect. Notes Electrical Eng.


    Contributors:
    Jia, Yingmin (editor) / Zhang, Weicun (editor) / Fu, Yongling (editor) / Wang, Kang (author) / Liu, Yang (author) / Zheng, Zewei (author) / Zhu, Ming (author)

    Conference:

    Chinese Intelligent Systems Conference ; 2020 ; Shenzhen City, China October 24, 2020 - October 25, 2020



    Publication date :

    2020-09-24


    Size :

    14 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    Reinforcement Learning Adaptive Tracking Control for a Stratospheric Airship

    Wang, Kang / Liu, Yang / Zheng, Zewei et al. | British Library Conference Proceedings | 2021



    Fin of stratospheric airship and stratospheric airship

    JIANG JING / GAO JUN / CHEN CHAOQUN et al. | European Patent Office | 2024

    Free access

    Airship capsule and stratospheric airship

    DUAN YI / JIANG JING / FU GONGYI et al. | European Patent Office | 2023

    Free access

    TRANSFORMABLE STRATOSPHERIC AIRSHIP

    ZHOU MENG / TAN BAIHE / XU ZHONGXIN et al. | European Patent Office | 2021

    Free access