Guided Multi-Fidelity Bayesian Optimization for Data-driven Controller Tuning with Digital Twins

Mahdi Nobar

doi:10.1109/LRA.2026.3671557

Guided Multi-Fidelity Bayesian Optimization for Data-driven Controller Tuning with Digital Twins

2026-03-09

0

PRE

AI

DOI：10.1109/LRA.2026.3671557

Original

Original request for help

Save

Abstract

En 中文

We propose a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">guided multi-fidelity Bayesian optimization</i> framework for data-efficient controller tuning that integrates corrected digital twin simulations with real-world measurements. The method targets closed-loop systems with limited-fidelity simulations or inexpensive approximations. To address model mismatch, we build a multi-fidelity surrogate with a learned correction model that refines digital twin estimates using real data. An adaptive cost-aware acquisition function balances expected improvement, fidelity, and sampling cost. Our method ensures adaptability as new measurements arrive. The digital twin accuracy is re-estimated, dynamically adapting both cross-source correlations and the acquisition function. This ensures that accurate simulations are used more frequently, while inaccurate simulation data are appropriately downweighted. Experiments on robotic drive hardware and supporting numerical studies demonstrate that our method enhances tuning efficiency compared to standard Bayesian optimization and multi-fidelity methods.

Keywords:

Multi-fidelity Bayesian optimization

Gaussian processes

adaptive learning control

smart manufacturing

Guided Multi-Fidelity Bayesian Optimization for Data-driven Controller Tuning with Digital Twins

Abstract

Journal

Organization