Data-driven Estimator Synthesis with Instantaneous Noise

2025/04/11 by Felix Brändle, Frank Allgöwer, Brändle, Felix +1 · 1 citation
Computer Science · Engineering · #Neural Networks and Applications #Control Systems and Identification

paper · pdf · doi:10.48550/arxiv.2504.08299

Abstract

Data-driven controller design based on data informativity has gained popularity due to its straightforward applicability, while providing rigorous guarantees. However, applying this framework to the estimator synthesis problem introduces technical challenges, which can only be solved so far by adding restrictive assumptions. In this work, we remove these restrictions to improve performance guarantees. Moreover, our parameterization allows the integration of additional structural knowledge, such as bounds on parameters. Our findings are validated using numerical examples.

Citations

• A System Parameterization for Direct Data-Driven Estimator Synthesis
• Guarantees for data-driven control of nonlinear systems using semidefinite programming: A survey
• Learning Robust Data-based LQG Controllers from Noisy Data
• Data-Based Moving Horizon Estimation for Linear Discrete-Time Systems
• Data-driven inference on optimal input-output properties of polynomial systems with focus on nonlinearity measures
• Data-Driven Inference on Optimal Input–Output Properties of Polynomial Systems With Focus on Nonlinearity Measures
• Combining Prior Knowledge and Data for Robust Controller Design
• From noisy data to feedback controllers: non-conservative design via a matrix S-lemma
• Data informativity: a new perspective on data-driven analysis and control
• Data-Enabled Predictive Control: In the Shallows of the DeePC
• A note on persistency of excitation

Related

• A System Parameterization for Direct Data-Driven Estimator Synthesis
• Controller Synthesis from Noisy-Input Noisy-Output Data
• Data-Driven System Level Synthesis
• Data-driven control of continuous-time systems: A synthesis-operator approach
• Robust Data-Driven Control for Systems with Noisy Data