🤖 AI Summary
To address the insufficient robustness of conventional PID controllers for quadrotor UAVs under model uncertainties and external disturbances, this paper proposes an online self-tuning incremental PID controller based on a model-free Actor-Critic framework. The method innovatively unifies dynamic PID gain adaptation and neural system identification within a hybrid Actor-Critic architecture—featuring dual hidden layers and sigmoid activation—enabling joint optimization of parameter tuning and system identification. Training employs the ADAM optimizer and backpropagation, ensuring real-time capability and lightweight deployment. Experimental results demonstrate that, compared to fixed-gain PID, the proposed approach significantly enhances robustness against mass variations and wind disturbances, achieving faster response, reduced overshoot, higher trajectory tracking accuracy, and efficient training convergence.
📝 Abstract
Proportional-Integrator-Derivative (PID) controller is used in a wide range of industrial and experimental processes. There are a couple of offline methods for tuning PID gains. However, due to the uncertainty of model parameters and external disturbances, real systems such as Quadrotors need more robust and reliable PID controllers. In this research, a self-tuning PID controller using a Reinforcement-Learning-based Neural Network for attitude and altitude control of a Quadrotor has been investigated. An Incremental PID, which contains static and dynamic gains, has been considered and only the variable gains have been tuned. To tune dynamic gains, a model-free actor-critic-based hybrid neural structure was used that was able to properly tune PID gains, and also has done the best as an identifier. In both tunning and identification tasks, a Neural Network with two hidden layers and sigmoid activation functions has been learned using Adaptive Momentum (ADAM) optimizer and Back-Propagation (BP) algorithm. This method is online, able to tackle disturbance, and fast in training. In addition to robustness to mass uncertainty and wind gust disturbance, results showed that the proposed method had a better performance when compared to a PID controller with constant gains.
