Neural Power-Optimal Magnetorquer Solution for Multi-Agent Formation and Attitude Control

This paper presents an efficient algorithm for finding the power-optimal currents of magnetorquer, a satellite attitude actuator in Earth orbit, for multi-agent formation and attitude control. Specifically, this study demonstrates that a set of power-optimal solutions can be derived through sequential convex programming and proposes a method to approximate these solutions using a deep neural network (DNN). The practicality of this DNN model is demonstrated through numerical simulations of formation and attitude control.