Event-Triggered Learning for Linear Quadratic Control

IEEE Transactions on Automatic Control, vol. 66, pp. 4485–4498

Abstract

When models are inaccurate, the performance of model-based control will degrade. For linear quadratic control, an event-triggered learning framework is proposed that automatically detects inaccurate models and triggers the learning of a new process model when needed. This is achieved by analyzing the probability distribution of the linear quadratic cost and designing a learning trigger that leverages Chernoff bounds. In particular, whenever empirically observed cost signals are located outside the derived confidence intervals, we can provably guarantee that this is with high probability due to a model mismatch. With the aid of numerical and hardware experiments, we demonstrate that the proposed bounds are tight and that the event-triggered learning algorithm effectively distinguishes between inaccurate models and probabilistic effects, such as process noise. Thus, a structured approach is obtained that decides when model learning is beneficial.

Authors 3

1. Henning Schlüter

   Max Planck Society · University of Stuttgart

   Affiliation as printed

   Institute for Systems Theory and Automatic Control, University of Stuttgart, Stuttgart, Germany

   Max-Planck-Society

2. Friedrich Solowjow

   Max Planck Institute for Intelligent Systems · University of Stuttgart

   Affiliation as printed

   Intelligent Control Systems Group, Max Planck Institute for Intelligent Systems, Stuttgart, Germany

   Univ. of Stuttgart#TAB#

3. Sebastian Trimpe Aachen Institute for Data Science in Mechanical Engineering

   RWTH Aachen University · Max Planck Institute for Intelligent Systems

   Affiliation as printed

   Institute for Data Science in Mechanical Engineering, RWTH Aachen University, Aachen, Germany

   Intelligent Control Systems Group, Max Planck Institute for Intelligent Systems, Stuttgart, Germany

   RWTH Aachen University