Near-Optimal Design of Safe Output Feedback Controllers from Noisy Data
arXiv:2105.10280 · doi:10.1109/TAC.2022.3180692
Abstract
As we transition towards the deployment of data-driven controllers for black-box cyberphysical systems, complying with hard safety constraints becomes a primary concern. Two key aspects should be addressed when input-output data are corrupted by noise: how much uncertainty can one tolerate without compromising safety, and to what extent is the control performance affected? By focusing on finite-horizon constrained linear-quadratic problems, we provide an answer to these questions in terms of the model mismatch incurred during a preliminary identification phase. We propose a control design procedure based on a quasiconvex relaxation of the original robust problem and we prove that, if the uncertainty is sufficiently small, the synthesized controller is safe and near-optimal, in the sense that the suboptimality gap increases linearly with the model mismatch level. Since the proposed method is independent of the specific identification procedure, our analysis holds in combination with state-of-the-art behavioral estimators beyond standard least-squares. The main theoretical results are validated by numerical experiments.
arXiv commentBaiwei Guo and Andrea Martin contributed equally to this work. in IEEE Transactions on Automatic Control, 2022
References in corpus (21)
- Data-Driven Model Predictive Control with Stability and Robustness Guarantees
- Safe Reinforcement Learning Using Robust MPC
- Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator
- Linear tracking MPC for nonlinear systems Part II: The data-driven case
- Data-Driven Control of Complex Networks
- Maximum Likelihood Estimation in Data-Driven Modeling and Control
- Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems
- Non-asymptotic Identification of Linear Dynamical Systems Using Multiple Trajectories
- Improper Learning for Non-Stochastic Control
- Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems
- An Input-Output Parametrization of Stabilizing Controllers: amidst Youla and System Level Synthesis
- Learning the Globally Optimal Distributed LQ Regulator
- Certainty Equivalence is Efficient for Linear Quadratic Control
- A System Level Approach to Tube-based Model Predictive Control
- On the Equivalence of Youla, System-level and Input-output Parameterizations
- System-level, Input-output and New Parameterizations of Stabilizing Controllers, and Their Numerical Computation
- Unified Approach to Convex Robust Distributed Control given Arbitrary Information Structures
- Nonlinear Data-Enabled Prediction and Control
- Sample Complexity of Linear Quadratic Gaussian (LQG) Control for Output Feedback Systems
- Data-Driven Prediction with Stochastic Data: Confidence Regions and Minimum Mean-Squared Error Estimates
- Bridging direct & indirect data-driven control formulations via regularizations and relaxations