A Unified Bayesian Framework for Data-Driven Smoothing, Prediction, and Control

TL;DR

This paper introduces a Bayesian framework that unifies data-driven smoothing, prediction, and control for linear systems, systematically handling stochastic data with a probabilistic approach.

Contribution

It presents a general Bayesian method that integrates trajectory knowledge with data-driven models for stochastic tasks, extending Willems' lemma-based algorithms.

Findings

The framework effectively handles correlated uncertainties with elliptical distributions.

Numerical examples show improved performance over existing methods.

The approach generalizes several data-driven prediction and control algorithms.

Abstract

Extending data-driven algorithms based on Willems' fundamental lemma to stochastic data often requires empirical and customized workarounds. This work presents a unified Bayesian framework for linear systems that provides a systematic and general method for handling stochastic data-driven tasks, including smoothing, prediction, and control, via maximum a posteriori estimation. This framework formulates a unified trajectory estimation problem for the three tasks by specifying different types of trajectory knowledge. Then, a Bayesian problem is solved that optimally combines trajectory knowledge with a data-driven characterization of the trajectory from offline data for correlated input-output uncertainties with elliptical distributions. Under specific conditions, this problem is shown to generalize existing data-driven prediction and control algorithms. Numerical examples demonstrate the performance of the unified approach for all three tasks against other data-driven and system identification approaches.