Imitation Learning for Satellite Attitude Control under Unknown Perturbations

2025-07-01

AI Summary

To address insufficient robustness of satellite attitude control under unknown disturbances—such as actuator faults and sensor noise—this paper proposes an end-to-end reinforcement learning framework integrating Soft Actor-Critic (SAC) with Generative Adversarial Imitation Learning (GAIL). Expert demonstrations guide policy learning, substantially reducing sample complexity and enhancing generalization and stability against parametric uncertainty and multi-source composite disturbances. Key innovations include: (i) the first application of GAIL to satellite attitude control for model-free, robust policy transfer; and (ii) differentiable reward shaping to optimize control performance. Experimental results demonstrate stable target pointing under both single and composite disturbances; the GAIL learner accurately replicates expert behavior, validating the method’s effectiveness, autonomy, and engineering practicality.

Technology Category

• Machine Learning: Imitation Learning & Inverse Reinforcement Learning
• Intelligent Robots: Behavior Learning & Control
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

This paper presents a novel satellite attitude control framework that integrates Soft Actor-Critic (SAC) reinforcement learning with Generative Adversarial Imitation Learning (GAIL) to achieve robust performance under various unknown perturbations. Traditional control techniques often rely on precise system models and are sensitive to parameter uncertainties and external perturbations. To overcome these limitations, we first develop a SAC-based expert controller that demonstrates improved resilience against actuator failures, sensor noise, and attitude misalignments, outperforming our previous results in several challenging scenarios. We then use GAIL to train a learner policy that imitates the expert's trajectories, thereby reducing training costs and improving generalization through expert demonstrations. Preliminary experiments under single and combined perturbations show that the SAC expert can rotate the antenna to a specified direction and keep the antenna orientation reliably stable in most of the listed perturbations. Additionally, the GAIL learner can imitate most of the features from the trajectories generated by the SAC expert. Comparative evaluations and ablation studies confirm the effectiveness of the SAC algorithm and reward shaping. The integration of GAIL further reduces sample complexity and demonstrates promising imitation capabilities, paving the way for more intelligent and autonomous spacecraft control systems.

Problem

• Robust satellite attitude control under unknown perturbations
• Overcoming limitations of traditional model-dependent control methods
• Reducing training costs via imitation learning from expert demonstrations

Innovation

• SAC reinforcement learning for robust control
• GAIL imitation learning to reduce training costs
• Integration of SAC and GAIL for spacecraft control