Learning-enhanced robust controller synthesis with rigorous statistical and control-theoretic guarantees
This work addresses safety-critical applications in control systems by offering a method with statistical and control-theoretic assurances, though it appears incremental as it builds on existing frameworks.
The paper tackles the challenge of providing rigorous guarantees for learning-based robust control by integrating Gaussian Process Regression with established control frameworks, demonstrating improved performance with more data while maintaining guarantees.
The combination of machine learning with control offers many opportunities, in particular for robust control. However, due to strong safety and reliability requirements in many real-world applications, providing rigorous statistical and control-theoretic guarantees is of utmost importance, yet difficult to achieve for learning-based control schemes. We present a general framework for learning-enhanced robust control that allows for systematic integration of prior engineering knowledge, is fully compatible with modern robust control and still comes with rigorous and practically meaningful guarantees. Building on the established Linear Fractional Representation and Integral Quadratic Constraints framework, we integrate Gaussian Process Regression as a learning component and state-of-the-art robust controller synthesis. In a concrete robust control example, our approach is demonstrated to yield improved performance with more data, while guarantees are maintained throughout.