An intelligent robust disturbance rejection controller is designed for Unmanned Aerial Vehicle (UAV) which is highly nonlinear, and uncertain model, strong coupling and affected by variable interference. In order to design Linear Extended State Observer (LESO), the system is extended by one dimension. Design LESO to estimate the internal and external disturbances of the system. Since the LESO estimation error of the total disturbance cannot be compensated, an intelligent robust disturbance rejection controller is proposed. H∞ control theory proves the stability of the designed intelligent robust disturbance rejection control system. What is more, a Deep Reinforcement Learning (DRL) algorithm is incorporated to strengthen the transient performance of the system. A simulation example verifies the adaptability of the control strategy.
Intelligent Robust Disturbance Rejection Control via Deep Reinforcement Learning
Lect. Notes Electrical Eng.
International Conference on Autonomous Unmanned Systems ; 2021 ; Changsha, China September 24, 2021 - September 26, 2021
Proceedings of 2021 International Conference on Autonomous Unmanned Systems (ICAUS 2021) ; Kapitel : 218 ; 2203-2212
18.03.2022
10 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Intelligent Robust Disturbance Rejection Control via Deep Reinforcement Learning
British Library Conference Proceedings | 2022
|Deep Reinforcement Learning-Based Wind Disturbance Rejection Control Strategy for UAV
DOAJ | 2024
|Intelligent Robust Disturbance Rejection Control of UAV Based on Deep Q Network
Springer Verlag | 2024
|DISTRIBUTED ACCELERATION SENSING FOR ROBUST DISTURBANCE REJECTION
Europäisches Patentamt | 2020
|