article · IEEE Access
Quadrotor unmanned aerial vehicles often face operational challenges from wind, external disturbances, and internal parameter changes. To improve flight stability, an intelligent control framework combines Model Reference Adaptive Control with artificial neural networks. The system relies on a singularity-free dynamic model formulated through Newton-Quaternion mathematics. Training data generated from conventional adaptive control is used to train a feed-forward neural network for position estimation and a recurrent neural network for attitude control. An online learning algorithm continuously updates these network parameters during flight. Numerical simulations testing nominal conditions, matched and unmatched disturbances, and parametric shifts demonstrated superior trajectory tracking and disturbance rejection compared to standard linear quadratic regulators and conventional adaptive systems. The control signals remained smooth and minimal, suggesting strong potential for practical, real-time quadrotor operations.
Unmanned aerial vehicles must navigate unpredictable environments such as gusty winds without losing stability or consuming excessive power. By combining neural networks with adaptive flight control, quadrotors can self-adjust to sudden physical disturbances and internal variations. This delivers more dependable, efficient autonomous flight, which is essential for safely operating drones across complex operational conditions.
This controller could benefit commercial drone manufacturers, flight software developers, and autonomous inspection operators seeking robust autonomous flight in unstable weather. Because the findings are currently demonstrated solely through numerical simulations rather than hardware flight tests, the technology remains at an early, applied simulation stage. Further real-world validation on physical quadrotor platforms is necessary before integration into commercial flight management systems.
AI-generated from the published abstract. Always read the original work before citing.
In this paper, an intelligent Model Reference Adaptive Control (MRAC) based on a neural network is proposed for robust tracking control of quadrotor UAV under external disturbances and parameter variations. First, the singularity-free dynamic model of the quadrotor is developed using Newton-Quaternion formalism. Then, conventional MRAC is designed to generate training data. With the generated data, the Feed Forward Neural Network (FFNN) and Recurrent Neural Network (RNN) are trained offline to get an initial set of network parameters for position controller parameters estimation and attitude control of the quadrotor, respectively, and an online learning algorithm is developed to update those network parameters in real-time. Finally, the performance of the designed Neural network-based MRAC has been evaluated using a numerical simulation in a nominal scenario and by introducing parametric variation and external disturbances as matched and unmatched uncertainties into the system. The simulation results show that the proposed controller has a better tracking performance and disturbance rejection capability compared with the Linear Quadratic Regulator (LQR) and conventional MRAC. Furthermore, the utilized control efforts are minimal and smooth proving functional safety and economical use of the controller. Therefore, the suggested controller is feasible for real-time implementation of the quadrotor UAV.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/access.2024.3374894
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
