Probabilistic robust linear quadratic regulators with Gaussian processes

05/17/2021
by   Alexander von Rohr, et al.
0

Probabilistic models such as Gaussian processes (GPs) are powerful tools to learn unknown dynamical systems from data for subsequent use in control design. While learning-based control has the potential to yield superior performance in demanding applications, robustness to uncertainty remains an important challenge. Since Bayesian methods quantify uncertainty of the learning results, it is natural to incorporate these uncertainties into a robust design. In contrast to most state-of-the-art approaches that consider worst-case estimates, we leverage the learning method's posterior distribution in the controller synthesis. The result is a more informed and, thus, more efficient trade-off between performance and robustness. We present a novel controller synthesis for linearized GP dynamics that yields robust controllers with respect to a probabilistic stability margin. The formulation is based on a recently proposed algorithm for linear quadratic control synthesis, which we extend by giving probabilistic robustness guarantees in the form of credibility bounds for the system's stability.Comparisons to existing methods based on worst-case and certainty-equivalence designs reveal superior performance and robustness properties of the proposed method.

READ FULL TEXT

page 1

page 2

page 3

page 4

02/19/2022

Safe Control Synthesis with Uncertain Dynamics and Constraints

This paper considers safe control synthesis for dynamical systems in the...
05/13/2022

Robustness of Control Design via Bayesian Learning

In the realm of supervised learning, Bayesian learning has shown robust ...
03/18/2019

A Control Lyapunov Perspective on Episodic Learning via Projection to State Stability

The goal of this paper is to understand the impact of learning on contro...
06/01/2018

Learning convex bounds for linear quadratic control policy synthesis

Learning to make decisions from observed data in dynamic environments re...
09/20/2017

On the Design of LQR Kernels for Efficient Controller Learning

Finding optimal feedback controllers for nonlinear dynamic systems from ...
07/28/2022

Improving the Performance of Robust Control through Event-Triggered Learning

Robust controllers ensure stability in feedback loops designed under unc...
10/04/2017

On the Sample Complexity of the Linear Quadratic Regulator

This paper addresses the optimal control problem known as the Linear Qua...

Code Repositories

prlqr

Supplementary material for the paper "Probabilistic robust linear quadratic regulators with Gaussian processes"


view repo