Neural network-based prescribed performance control for spacecraft formation reconfiguration with collision avoidance

Abstract

This article investigates neural network (NN)-based prescribed performance control with collision avoidance for spacecraft formation systems in the presence of space perturbations and thruster faults. First, an artificial potential function is constructed to maintain spacecraft within communication range and avoid collisions. A prescribed performance function is then employed to constrain position errors within a preset boundary. Furthermore, a learning non-singular terminal sliding mode control (LNTSMC) law is developed to ensure that both the steady-state and transient performance of position tracking errors meet the prescribed performance constraints. A novel learning NN model is incorporated to estimate and compensate for the synthesized perturbations, utilizing an iterative learning algorithm to update the weights of the NN, thereby reducing computational complexity. The proposed LNTSMC scheme effectively addresses issues of inter-spacecraft collision avoidance, prescribed dynamic and steady-state control performance, and robust fault tolerance without imposing additional constraints on thruster faults. A rigorous stability analysis is provided, and the effectiveness and applicability of the proposed method are validated through simulation comparisons.