Foundation Models for the Digital Twin Creation of Cyber-Physical Systems

TL;DR

This paper explores how foundation models can be utilized to enhance the creation, effectiveness, and specialization of digital twins for cyber-physical systems, with a focus on autonomous driving as a case study.

Contribution

It provides a comprehensive perspective on applying foundation models to digital twins in CPSs, highlighting benefits, challenges, and future research directions.

Findings

Foundation models can improve digital twin development efficiency.

Fine-tuned foundation models can serve as digital twins.

Discussion of challenges in applying foundation models to CPSs.

Abstract

Foundation models are trained on a large amount of data to learn generic patterns. Consequently, these models can be used and fine-tuned for various purposes. Naturally, studying such models' use in the context of digital twins for cyber-physical systems (CPSs) is a relevant area of investigation. To this end, we provide perspectives on various aspects within the context of developing digital twins for CPSs, where foundation models can be used to increase the efficiency of creating digital twins, improve the effectiveness of the capabilities they provide, and used as specialized fine-tuned foundation models acting as digital twins themselves. We also discuss challenges in using foundation models in a more generic context. We use the case of an autonomous driving system as a representative CPS to give examples. Finally, we provide discussions and open research directions that we believe are valuable for the digital twin community.