The micro co-axial rotor UAV has the advantages of high hovering efficiency and compact structure in various applications, but its attitude control system has the characteristics of strong nonlinearity and coupling, and the design of the controller is the most difficult point in the design of this type of aircraft. In this paper, a control system is designed based on reinforcement learning algorithm for a micro co-axial rotor UAV that uses aerodynamic rudder surface for attitude control. Firstly, according to the reinforcement learning theory and the characteristics of the UAV, the main formulas of the control system is designed. Secondly, digital model of the UAV and training environment are established, the controller basically meets the control requirements after the training experiments were conducted. Judging by the performance of the reinforcement learning controller, it effectively improved the control accuracy and efficiency comparing with the existing PID controller. This research implements the combination of reinforcement learning algorithm and the controller of micro co-axial rotor UAV, and provides an idea to build an intelligent controller for complex micro-aircraft.
Research on Flight Control Method of Micro Co-axial Rotor UAV Based on Reinforcement Learning
Lect. Notes Electrical Eng.
International Conference on Autonomous Unmanned Systems ; 2022 ; Xi'an, China September 23, 2022 - September 25, 2022
Proceedings of 2022 International Conference on Autonomous Unmanned Systems (ICAUS 2022) ; Chapter : 119 ; 1308-1320
2023-03-10
13 pages
Article/Chapter (Book)
Electronic Resource
English
RESEARCH ON FLIGHT CONTROL METHOD OF MORPHING UCAV BASED ON REINFORCEMENT LEARNING
British Library Conference Proceedings | 2010
|An Optimum Coaxial Rotor System for Axial Flight
Online Contents | 2008
|An optimum coaxial rotor system for axial flight
Tema Archive | 2008
|Stability Analysis of Helicopter Rotor Wakes in Axial Flight
Online Contents | 2000
|