A self-adaptive sliding mode control method based on Randomized Feedforward Neural Network(RFNN) is proposed to address the position and attitude tracking control issues of the rotor mode and flight mode of tiltrotor quadcopter unmanned aerial vehicles after changes in tilt angle. Firstly, the tilting quadcopter dynamics system is divided into fully actuated subsystems and underactuated subsystems. Considering the uncertainty of model parameters and external disturbances in drones, the equivalent controller obtained by sliding mode control method cannot be directly applied to drones. Therefore, a Randomized Feedforward Neural Network(RFNN) is used to estimate the equivalent controller. Then, to ensure the stability of the control system and reduce controller chattering, a new switching controller was adopted. Finally, according to Lyapunov theory, both subsystems can reach the sliding mode surface, and the effectiveness of the method was verified through comparative simulation.
Adaptive Sliding Mode Attitude and Trajectory Tracking Control of Quadrotor UAV
2024-07-26
478608 byte
Conference paper
Electronic Resource
English
Trajectory Tracking Control Based on Adaptive Sliding Mode for Quadrotor UAV
British Library Online Contents | 2018
|Adaptive Sliding Mode Trajectory Tracking Control of Quadrotor UAV with Unknown Control Direction
Springer Verlag | 2019
|Adaptive Sliding Mode Trajectory Tracking Control of Quadrotor UAV with Unknown Control Direction
British Library Conference Proceedings | 2020
|