An adaptive data sampling strategy for stabilizing dynamical systems via controller inference

TL;DR

This paper introduces an adaptive data sampling method that stabilizes dynamical systems during data collection, enabling efficient controller inference with fewer samples and improving stability in challenging scenarios.

Contribution

The paper presents a novel adaptive sampling scheme that stabilizes systems during data collection, reducing data requirements for controller inference and handling edge cases effectively.

Findings

Controller inference with adaptive sampling uses up to ten times fewer data samples.

The approach provably generates informative and minimal data sets for stabilization.

Numerical experiments confirm improved stability and data efficiency.

Abstract

Learning stabilizing controllers from data is an important task in engineering applications; however, collecting informative data is challenging because unstable systems often lead to rapidly growing or erratic trajectories. In this work, we propose an adaptive sampling scheme that generates data while simultaneously stabilizing the system to avoid instabilities during the data collection. Under mild assumptions, the approach provably generates data sets that are informative for stabilization and have minimal size. The numerical experiments demonstrate that controller inference with the novel adaptive sampling approach learns controllers with up to one order of magnitude fewer data samples than unguided data generation. The results show that the proposed approach opens the door to stabilizing systems in edge cases and limit states where instabilities often occur and data collection is inherently difficult.