Browsing by Author "Kotze, Henry"

Now showing 1 - 1 of 1
  • Thumbnail Image
    Item
    Neural disturbance rejection for a multirotor
    (Stellenbosch : Stellenbosch University, 2021-03) Kotze, Henry; Jordaan, Hendrik Willem; Stellenbosch University. Faculty of Engineering. Dept. of Electrical and Electronic Engineering.
    ENGLISH ABSTRACT: The thesis addresses the problem of multirotors experiencing various disturbances such as wind, payloads and ground effects. These disturbances introduce challenges during specific application uses such a s delivery, capturing images and line following. The project models these disturbances as unknown and attempts to implement a controller architecture which rejects them to provide a general solution for all application uses. The project has a particular focus on using neural networks as a solution to the problem because of the recent advances the technique has made in fields which share common attributes. Existing approaches mostly attempt to replace the controller entirely with neural networks, because of its ability to learn nonlinear behaviour, which many classical controllers ignore. This project rather focuses on augmenting the classical controller with neural networks to account for disturbances and nonlinear behaviour. Specifically, the project uses a disturbance rejection architecture using a neural network as its observer for disturbances. The neural network estimates the disturbances which are then rejected by feeding it back into the classical controller output signal. Synthetic labelled data is generated using the Gazebo simulation environment wherein disturbances of a specific nature occur with domain randomisation applied for Sim2Real transfer. The flight controllers used is PX4 which provides the Software-in-the-Loop functionality to fly a multirotor along a specific trajectory. The neural network estimation for practical flights shows good Sim2Real transfer with its ability to estimate payloads being carried by a multirotor and ground effects during landing. The neural network disturbance rejection is also compared to two other classical observers, namely the Extended Kalman Filter (EKF) and the Extended State Observer (ESO). The neural network shows superior disturbance rejection over the EKF and ESO when the multirotor is experiencing force disturbances. For torque disturbances, the ESO performed the best. From the disturbance rejection results, it is evident that for torque disturbances which influence the faster dynamics of the multirotor, observers should execute alongside the controllers such as the ESO. For disturbances which influence the slower dynamics of the multirotor, algorithms which execute on a companion board are sufficient and better. Specifically, the use of a neural network as an observer in a disturbance rejection architecture shows compelling evidence as the method for rejecting unknown disturbances influencing a multirotor.