Trade-offs in learning controllers from noisy data

Abstract

In data-driven control, a central question is how to handle noisy data. In this work, we consider the problem of designing a stabilizing controller for an unknown linear system using only a finite set of noisy data collected from the system. For this problem, many recent works have considered a disturbance model based on energy-type bounds. Here, we consider an alternative more natural model where the disturbance obeys instantaneous bounds. In this case, the existing approaches, which would convert instantaneous bounds into energy-type bounds, can be overly conservative. In contrast, without any conversion step, simple arguments based on the S-procedure lead to a very effective controller design through a convex program. Specifically, the feasible set of the latter design problem is always larger, and the set of system matrices consistent with data is always smaller and decreases significantly with the number of data points. These findings and some computational aspects are examined in a number of numerical examples.

References in corpus (6)

• Robust data-driven state-feedback design
• Combining Prior Knowledge and Data for Robust Controller Design
• Data-based stabilization of unknown bilinear systems with guaranteed basin of attraction
• Data-based Receding Horizon Control of Linear Network Systems
• Controller design for robust invariance from noisy data
• Data-driven Stabilization of SISO Feedback Linearizable Systems

Cited by in corpus (16)

• Data-driven control via Petersen's lemma
• Combining Prior Knowledge and Data for Robust Controller Design
• Data-driven analysis and control of continuous-time systems under aperiodic sampling
• On data-driven control: informativity of noisy input-output data with cross-covariance bounds
• Data-driven design of safe control for polynomial systems
• Data-based Transfer Stabilization in Linear Systems
• Controller synthesis for input-state data with measurement errors
• Synthesizing Safety Controllers for Uncertain Linear Systems: A Direct Data-driven Approach
• The Non-Strict Projection Lemma
• Learning controllers for performance through LMI regions
• Direct data-driven control of LTV systems
• Data-driven input-to-state stabilization with respect to measurement errors
• Data Informativity for Quadratic Stabilization under Data Perturbation
• Online Stochastic Optimization for Unknown Linear Systems: Data-Driven Synthesis and Controller Analysis
• Data-driven input-to-state stabilization
• Setpoint control of bilinear systems from noisy data