Ball and Beam Control using Adaptive PID based on Q-Learning

The ball and beam system is one of the most used systems for benchmarking the controller response because it has nonlinear and unstable characteristics. Furthermore, in line with the increasing of computation power availability and artificial intelligence research intensity, especially the reinforcement learning field, nowadays plenty of researchers are working on a learning control approach for controlling systems. Due to that, in this paper, the adaptive PID controller based on Q-Learning (Q-PID) was used to control the ball position on the ball and beam system. From the simulation result, Q-PID outperforms the conventional PID and heuristic PID controller technique with the swifter settling time and lower overshoot percentage.