Skip to main content
January 11, 2024

Auto Digital Twins: deployment of Digital Twins in Industry

Digital twins are one of the most promising technologies of the moment for many sectors, and industry is one of the sectors that can benefit the most.

In our eagerness to research in this field, we have joined together in an innovation consortium to develop a project that aims to provide SMEs in the industrial sector with a tool that automates the data capture process.

The solution, called Auto Digital Twins, aims to accelerate the digitization and modernization of corporate infrastructures and continue advancing in the Industry 4.0 paradigm.

Digital Twins and Industry

Digital twins make it possible to simulate how an industrial plant behaves, even before it exists. By simulating changes in production, problems can be avoided before they occur, downtime can be minimized, or production can be customized to adapt the industry to flexible manufacturing.

Despite all their advantages, digital twins face barriers to entry in terms of the degree of digitization due to the complexity of system integration, the absence of qualified personnel, or the lack of tools to automate data tagging.

To put an end to these limiting factors, the Auto Digital Twins project was proposed to provide the industry with a tool to accelerate the implementation of digital twins and resolve one of the main bottlenecks: the high cost of obtaining and labeling the 3D elements that make up industrial infrastructures.

Phase 1

The first phase of the project has been completed and focused on a point cloud to 3D transformation tool. The Spot robot was used in conjunction with the Leica sensor to scan an industrial facility to obtain point clouds. For this purpose, a progressive rendering viewer has been developed that is able to display these large point clouds smoothly. In addition, AI algorithms have been implemented on the point cloud to recognize complex objects, and once recognized, 3D models have been obtained in industrial standard formats, such as BIM and CAD.

Phase 2

In the second phase, we are extending the capacity of the tool for object detection, in which two lines of research are being considered:

  • Synthetic data generation: a response to the major problem of AI models’ lack of data to recognize objects. To this end, a synthetic generator is being developed that is capable of creating massively labelled virtual scenarios with which to train the models. To improve the realism of the synthetic data, the different conditioning factors and variation parameters that characterize the elements found in an industrial environment are being studied in detail. The synthetic data generated will be used to retrain the unsupervised ML models used to recognize elements in industrial environments automatically.
  • Extending the tool’s capabilities for the geometric reconstruction of objects: two new mechanisms have been incorporated that improve the automation of 3D and BIM object generation, which represents one of the most outstanding advantages and innovations of the tool, saving countless hours of manual work in this process.

In the future, a third phase will be initiated in which the aim will be to extend the tool’s capacity to recognize textures and behaviors. For all these reasons, the project responds to a change in work methodology in the way 3D data is generated to create digital twins, representing a tremendously helpful tool for industrial companies that want to accelerate the digitization and modernization of their infrastructures towards a new paradigm.


If you want to know more about our innovation projects, subscribe to our newsletter!


Initiative financed by the Ministry of Industry, Trade and Tourism within the programme of support to the AEIs to contribute to the improvement of the competitiveness of Spanish industry, and with the support of the European Union through the Recovery, Transformation and Resilience Plan

logo de proyecto financiado por la unión europea
Elena Canorea
Elena Canorea
Communications Lead