Learning Robust Satellite Attitude Dynamics with Physics-Informed Normalising Flow

TL;DR

This paper explores integrating physics-informed neural networks with normalising flows to improve the robustness and accuracy of satellite attitude dynamics models used in model predictive control.

Contribution

It introduces a novel approach combining PINNs with Real NVP architectures for spacecraft attitude modeling, demonstrating significant performance improvements.

Findings

Physics-informed models reduce mean relative error by 27.08%.

PINN-based models outperform purely data-driven models in control accuracy and robustness.

Control performance improves by up to 62% in settling times under noise and friction conditions.

Abstract

Attitude control is a fundamental aspect of spacecraft operations. Model Predictive Control (MPC) has emerged as a powerful strategy for these tasks, relying on accurate models of the system dynamics to optimize control actions over a prediction horizon. In scenarios where physics models are incomplete, difficult to derive, or computationally expensive, machine learning offers a flexible alternative by learning the system behavior directly from data. However, purely data-driven models often struggle with generalization and stability, especially when applied to inputs outside their training domain. To address these limitations, we investigate the benefits of incorporating Physics-Informed Neural Networks (PINNs) into the learning of spacecraft attitude dynamics, comparing their performance with that of purely data-driven approaches. Using a Real-valued Non-Volume Preserving (Real NVP) neural network architecture with a self-attention mechanism, we trained several models on simulated data generated with the Basilisk simulator. Two training strategies were considered: a purely data-driven baseline and a physics-informed variant to improve robustness and stability. Our results demonstrate that the inclusion of physics-based information significantly enhances the performance in terms of the mean relative error with the best architectures found by 27.08%. These advantages are particularly evident when the learned models are integrated into an MPC framework, where PINN-based models consistently outperform their purely data-driven counterparts in terms of control accuracy and robustness, and achieve improved settling times when compared to traditional MPC approaches, yielding improvements of up to 62%, when subject to observation noise and RWs friction.