Synthesis of Data-Driven LightGBM Controller for Spacecraft Attitude Control

The attitude dynamics of spacecraft are highly nonlinear, which makes it challenging to design control algorithms that can handle these nonlinearities. This study presents a novel data-driven synthesis method for using the LightGBM controller. controller is designed by supervised machine learning methodologies. training and testing datasets generated from input-output data closed-loop system under an exact feedback linearization-based We show some realistic conditions, even though we not guarantee asymptotic stability controller, but have kind practical stability, i.e., smaller bounded ball designing with bound error. Furthermore, simulation results additional interesting phenomenon still produces good performance there uncertainty in satellite parameters disturbance.