Neural network-based control for the on-orbit assembly of heterogeneous spacecraft cluster based on Vicsek fractal

Abstract

On-orbit assembly is a highly effective technique for building large space structures. This paper presents the dynamics and control of an on-orbit assembly of a large space structure based on a heterogenous spacecraft cluster comprising both rigid and flexible spacecraft. The topology of the large space structure is inspired by the Vicsek fractal. A distributed assembly strategy is proposed for the spacecraft team. Radial Basis Function neural networks (RBFNNs) are utilized to approximate the bounded uncertain terms in translational and attitude dynamics. To avoid collisions during the pre-assembly phase, a neural network (NN)-based controller with collision avoidance force is designed for relative position motion. During the assembly phase, only proportional-derivative (PD) law is employed for relative position control. In addition, an NN-based controller is designed for relative attitude control for both rigid and flexible spacecraft. To estimate the unmeasured flexible vibrations, modal coordinate observers are introduced for the flexible spacecraft. The stability of the closed-loop system is proved via Lyapunov functions. Moreover, numerical results are presented to validate the effectiveness of the proposed controllers and assembly strategy.