Data-Driven Linear Quadratic Regulator using LightGBM for Quadcopter Control

A quadcopter is an unmanned aerial vehicle that requires a control system to stabilize it during flight. In this paper, a data-driven control algorithm, Light Gradient Boost Machine (LightGBM) is proposed to improve the quadcopter control system. The input and output data we use for the LightGBM algorithm are obtained from a closed-loop quadcopter system with a linear quadratic regulator (LQR) controller. With the expectation that the LightGBM control algorithm can replace the LQR controller on the quadcopter. Simulations have been carried out in this study, and the results of the simulations show that the proposed algorithm has similar response results as LQR control, so that the proposed algorithm can be used as a control system in the quadcopter system.