Embodied Intelligent Digital Twin for autonomous operations: concept and implementation guidelines

To support autonomous equipment operations in complex and dynamic scenarios, this paper proposes the concept of an Embodied Intelligent Digital Twin (EIDT) and its implementation guidelines. By adapting and integrating digital twin (DT) technology with a domain-specific foundation model (DSFM), the EIDT links physical entities’ mechanistic characteristics and dynamic states with operational domain knowledge, establishing a task cognition and autonomous operation mechanism jointly driven by mechanism, data, and knowledge. In addition, the EIDT integrates information about Operation Tasks, Operation Performers, Operation Environments, and Operation Targets to support dynamic perception, task understanding, and adaptive decision-making. A unified EIDT representation paradigm comprising a mechanistic model unit (MU), a data model unit (DU), a DSFM, and an interaction interface (I) is proposed, together with an integrated construction solution. Implementation routes are developed for task-driven autonomous operation, adaptation across tasks and scenarios, and continuous evolution across lifecycle stages. Human-robot collaborative assembly of a rotary vector (RV) reducer is used to demonstrate EIDT construction, collaborative work-system formation, autonomous operation, and application extension for collaborative manufacturing tasks. The proposed EIDT provides a theoretical framework and implementation guidelines for integrating foundation models with DTs to support perception, planning, decision-making, and execution in dynamic operational scenarios.

Authors

Institutions

Publication Details

Journal
Digital Twin
Published
2026-11-17
DOI
https://doi.org/10.1080/27525783.2026.2760625
Primary Topic
Digital Transformation in Industry
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Embodied Intelligent Digital Twin for autonomous operations: concept and implementation guidelines

Tianliang Hu, Tongjia Zhang, Jingkai Li, Tianyi Sun et al.
2 links
Digital Twin
Digital Transformation in Industry
article

Embodied Intelligent Digital Twin for autonomous operations: concept and implementation guidelines

Tianliang Hu, Tongjia Zhang, Jingkai Li, Tianyi Sun, Lili Dong
article en

Abstract

To support autonomous equipment operations in complex and dynamic scenarios, this paper proposes the concept of an Embodied Intelligent Digital Twin (EIDT) and its implementation guidelines. By adapting and integrating digital twin (DT) technology with a domain-specific foundation model (DSFM), the EIDT links physical entities’ mechanistic characteristics and dynamic states with operational domain knowledge, establishing a task cognition and autonomous operation mechanism jointly driven by mechanism, data, and knowledge. In addition, the EIDT integrates information about Operation Tasks, Operation Performers, Operation Environments, and Operation Targets to support dynamic perception, task understanding, and adaptive decision-making. A unified EIDT representation paradigm comprising a mechanistic model unit (MU), a data model unit (DU), a DSFM, and an interaction interface (I) is proposed, together with an integrated construction solution. Implementation routes are developed for task-driven autonomous operation, adaptation across tasks and scenarios, and continuous evolution across lifecycle stages. Human-robot collaborative assembly of a rotary vector (RV) reducer is used to demonstrate EIDT construction, collaborative work-system formation, autonomous operation, and application extension for collaborative manufacturing tasks. The proposed EIDT provides a theoretical framework and implementation guidelines for integrating foundation models with DTs to support perception, planning, decision-making, and execution in dynamic operational scenarios.

Digital Twin
Shandong University (CN), Shandong Jianzhu University (CN)
National Natural Science Foundation of China, Natural Science Foundation of Shandong Province
Industry, innovation and infrastructure
Digital Transformation in Industry
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon