Digital twins as self-models for intelligent structures

Abstract A self-model is an artificial intelligence that is able to create a continuously updated internal representation of itself. In this paper we use an agent-based architecture to create a ‘digital twin self-model’, using the example of a small-scale three-story building. The architecture is ba...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaoxue Shen, David J. Wagg, Matthew Tipuric, Matthew S. Bonney
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-14347-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849226431382421504
author Xiaoxue Shen
David J. Wagg
Matthew Tipuric
Matthew S. Bonney
author_facet Xiaoxue Shen
David J. Wagg
Matthew Tipuric
Matthew S. Bonney
author_sort Xiaoxue Shen
collection DOAJ
description Abstract A self-model is an artificial intelligence that is able to create a continuously updated internal representation of itself. In this paper we use an agent-based architecture to create a ‘digital twin self-model’, using the example of a small-scale three-story building. The architecture is based on a set of heterogeneous digital components, each managed by an agent. The agents can be orchestrated to perform a specific workflow, or collaborate with a human user to perform requested tasks. The digital twin architecture enables multiple complex behaviors to be represented via a time-evolving dynamic assembly of the digital components, that also includes the encoding of a self-model in a knowledge graph as well as producing quantitative outputs. Four operational modes are defined for the digital twin and the example shown here demonstrates an offline mode that executes a predefined workflow with five agents. The digital twin has an information management system which is coordinated using a dynamic knowledge graph that encodes the self-model. Users can visualize the knowledge graph via a web-based user interface and also input natural language queries. Retrieval augmented generation is used to give a response to the queries using both the local knowledge graph and a large language model.
format Article
id doaj-art-7b949a59d2904a1aa7a4e5bd87c8e215
institution Kabale University
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-7b949a59d2904a1aa7a4e5bd87c8e2152025-08-24T11:21:35ZengNature PortfolioScientific Reports2045-23222025-08-0115111110.1038/s41598-025-14347-8Digital twins as self-models for intelligent structuresXiaoxue Shen0David J. Wagg1Matthew Tipuric2Matthew S. Bonney3The Alan Turing InstituteThe Alan Turing InstituteThe Alan Turing InstituteSchool of Aerospace, Civil, Electrical and Mechanical Engineering, Swansea UniversityAbstract A self-model is an artificial intelligence that is able to create a continuously updated internal representation of itself. In this paper we use an agent-based architecture to create a ‘digital twin self-model’, using the example of a small-scale three-story building. The architecture is based on a set of heterogeneous digital components, each managed by an agent. The agents can be orchestrated to perform a specific workflow, or collaborate with a human user to perform requested tasks. The digital twin architecture enables multiple complex behaviors to be represented via a time-evolving dynamic assembly of the digital components, that also includes the encoding of a self-model in a knowledge graph as well as producing quantitative outputs. Four operational modes are defined for the digital twin and the example shown here demonstrates an offline mode that executes a predefined workflow with five agents. The digital twin has an information management system which is coordinated using a dynamic knowledge graph that encodes the self-model. Users can visualize the knowledge graph via a web-based user interface and also input natural language queries. Retrieval augmented generation is used to give a response to the queries using both the local knowledge graph and a large language model.https://doi.org/10.1038/s41598-025-14347-8Digital twinSelf-modelAgentStructure
spellingShingle Xiaoxue Shen
David J. Wagg
Matthew Tipuric
Matthew S. Bonney
Digital twins as self-models for intelligent structures
Scientific Reports
Digital twin
Self-model
Agent
Structure
title Digital twins as self-models for intelligent structures
title_full Digital twins as self-models for intelligent structures
title_fullStr Digital twins as self-models for intelligent structures
title_full_unstemmed Digital twins as self-models for intelligent structures
title_short Digital twins as self-models for intelligent structures
title_sort digital twins as self models for intelligent structures
topic Digital twin
Self-model
Agent
Structure
url https://doi.org/10.1038/s41598-025-14347-8
work_keys_str_mv AT xiaoxueshen digitaltwinsasselfmodelsforintelligentstructures
AT davidjwagg digitaltwinsasselfmodelsforintelligentstructures
AT matthewtipuric digitaltwinsasselfmodelsforintelligentstructures
AT matthewsbonney digitaltwinsasselfmodelsforintelligentstructures