Autonomous Cooking with Digital Twin Methodology

TL;DR

This paper presents a Digital Twin-based approach for autonomous cooking that combines physics-based simulations with data-driven system identification, enabling real-time device-level operation without cloud reliance.

Contribution

It introduces a hybrid Digital Twin methodology for autonomous cooking, achieving fast, accurate simulations suitable for on-device implementation.

Findings

Faster-than-real-time simulations on device level.

Low-error physics-based and data-driven hybrid modeling.

Universal applicability to various physical processes.

Abstract

This work introduces the concept of an autonomous cooking process based on Digital Twin method- ology. It proposes a hybrid approach of physics-based full order simulations followed by a data-driven system identification process with low errors. It makes faster-than-real-time simulations of Digital Twins feasible on a device level, without the need for cloud or high-performance computing. The concept is universally applicable to various physical processes.