Online Regulation of Unstable LTI Systems from a Single Trajectory

by   Shahriar Talebi, et al.

Recently, data-driven methods for control of dynamic systems have received considerable attention in system theory machine learning as they provide a mechanism for feedback synthesis from the observed time-series data. However learning, say through direct policy updates, often requires assumptions such as knowing a priori that the initial policy (gain) is stabilizing, e.g., when the open-loop system is stable. In this paper, we examine online regulation of (possibly unstable) partially unknown linear systems with no a priori assumptions on the initial controller. First, we introduce and characterize the notion of ”regularizability” for linear systems that gauges the capacity of a system to be regulated in finite-time in contrast to its asymptotic behavior (commonly characterized by stabilizability/controllability). Next, having access only to the input matrix, we propose the Data-Guided Regulation (DGR) synthesis that–as its name suggests–regulates the underlying states while also generating informative data that can subsequently be used for data-driven stabilization or system identification (sysID). The analysis is also related in spirit, to the spectrum and the ”instability number” of the underlying linear system, a novel geometric property studied in this work. We further elucidate our results by considering special structures for system parameters as well as boosting the performance of the algorithm via a rank-one matrix update using the discrete nature of data collection in the problem setup. Finally, we demonstrate the utility of the proposed approach via an example involving direct (online) regulation of the X-29 aircraft.


page 1

page 11

page 14


Non-Episodic Learning for Online LQR of Unknown Linear Gaussian System

This paper considers the data-driven linear-quadratic regulation (LQR) p...

Online Control for Linear Dynamics: A Data-Driven Approach

This paper considers an online control problem over a linear time-invari...

Data-driven pattern identification and outlier detection in time series

We address the problem of data-driven pattern identification and outlier...

Data-Driven System Level Synthesis

We establish data-driven versions of the System Level Synthesis (SLS) pa...

Convergence Guarantees of Policy Optimization Methods for Markovian Jump Linear Systems

Recently, policy optimization for control purposes has received renewed ...

D3PI: Data-Driven Distributed Policy Iteration for Homogeneous Interconnected Systems

Control of large-scale networked systems often necessitates the availabi...

Combining Parameter Identification and Trajectory Optimization: Real-time Planning for Information Gain

Robotic systems often operate with uncertainties in their dynamics, for ...

Please sign up or login with your details

Forgot password? Click here to reset