ConstructionComputer Vision

How Bouygues Construction Drives Sustainable Building Innovation With Digital Twins

Bouygues Construction· FranceNVIDIA Omniverse · NVIDIA Isaac · NVIDIA Isaac Sim +2

Bouygues Construction, a global construction and infrastructure company based in France, built custom digital twin applications on NVIDIA Omniverse using the OpenUSD framework to unify 3D data from Revit, SolidWorks, and Cesium into a single collaborative environment. Using NVIDIA Isaac Sim, the company generates photorealistic synthetic training data for AI-based computer vision models covering rare or hazardous jobsite scenarios, and uses NVIDIA RTX PRO GPUs for real-time ray tracing. The approach delivered a 5x improvement in data integration speed and enabled safer job site planning through AI-driven construction site simulations and predictive scenario testing.

Overview

Bouygues Construction, a global construction and infrastructure company based in France, built custom digital twin applications on NVIDIA Omniverse using the OpenUSD framework to unify 3D data from Revit, SolidWorks, and Cesium into a single collaborative environment. Using NVIDIA Isaac Sim, the company generates photorealistic synthetic training data for AI-based computer vision models covering rare or hazardous jobsite scenarios, and uses NVIDIA RTX PRO GPUs for real-time ray tracing. The approach delivered a 5x improvement in data integration speed and enabled safer job site planning through AI-driven construction site simulations and predictive scenario testing.

This entry has 13 published fields tied to exact passages in an immutable source capture.

Inspect the highlighted source

The challenge

The construction industry deals with highly complex projects that involve massive 3D models, large volumes of data, and diverse data sources—from CAD models of manufacturing lines to BIM models of buildings. These models often come from different software tools, making interoperability a real challenge. Digital workflows are traditionally sequential and fragmented, limiting collaboration and slowing down the design-review process. Construction sites are also dynamic environments, and digital tools must adapt to real-world conditions to support better decision-making around safety.

The solution

By merging various complex 3D data sources and applications into a unified OpenUSD environment using Omniverse, Bouygues Construction developed integrated solutions that can interact with extensive multidisciplinary datasets in real time, including buildings modeled in Revit, equipment designed in SolidWorks, and terrain imported from Cesium. The company also uses NVIDIA Isaac Sim (built on Omniverse) to generate photorealistic synthetic 3D training data for AI-based computer vision models, particularly for rare or hazardous jobsite scenarios, with real-time ray tracing powered by NVIDIA RTX PRO GPUs.

Computer Vision

Reported business value

Adopting OpenUSD and Omniverse-based workflows delivered a 5x improvement in data integration speed. The approach also enabled safer job site planning through AI-driven construction site simulations and predictive scenario testing using Isaac Sim, and supports real-time collaboration across disciplines by unifying 3D models from Revit, SolidWorks, and Cesium into a single Omniverse workspace.

Sources

Open any source and check the claim yourself — that is the point of the register.

This record was researched and written with AI assistance, and its claims were checked against the sources above. (EU AI Act art. 50 transparency notice.)

Related entries

Other construction entries in the register.

All entries
ConstructionGenerative AIUnknown

Balfour Beatty invests 7.2 million pounds in Microsoft 365 Copilot and AI 'smart agents' for construction quality checks

Balfour Beatty announced a 7.2 million pound investment in Microsoft 365 Copilot, one of the largest AI investments of its kind in UK construction and infrastructure. Balfour Beatty is also partnering with Microsoft to develop AI-powered 'smart agents' to improve Quality, Health & Safety and Assurance processes; the first trial is on the A9 Dualling: Tomatin to Moy project in Scotland, automating early-stage reviews of Inspection and Test Plans that traditionally took several hours.

92/100HighPrimary source
Balfour Beatty· United KingdomMicrosoft 365 Copilot
ConstructionComputer VisionPublic Cloud

Colas uses AI on unified Databricks data platform to assess road maintenance needs from video footage

Colas Group worked with Databricks and OpenValue to unify data from hundreds of subsidiaries across 50 countries onto a single cloud platform combining Databricks, Microsoft Azure and open source technologies. Beyond helping reduce energy consumption and optimize industrial equipment efficiency, Colas is piloting a tool that uses AI to assess video footage of roads and determine maintenance requirements.

96/100HighPrimary source
Colas GroupDatabricks Lakehouse platform combined with Microsoft Azure and open source technologies, including Databricks Notebooks and Scheduler
ConstructionComputer VisionPublic Cloud

Reducing visual documentation time by 90% using AI on AWS with PlanRadar

PlanRadar, a Vienna-based construction and real estate software company, built SiteView, a visual documentation add-on that uses 360-degree image capture and Amazon Nova Foundation Models in Amazon Bedrock to map site photos onto floor plans. Running on Amazon EKS and Amazon S3, the GDPR-compliant solution lets users document 500 square meters of a construction site in about 5 minutes, a 90% reduction in time versus manual photography, with 97% positioning accuracy.

96/100HighPrimary source
PlanRadar· AustriaAmazon Nova · Amazon Bedrock · Amazon EKS +1
ConstructionConversational AIPublic Cloud

Tetra Tech gains natural language access to complex finance data with Oracle AI

Tetra Tech, a global engineering and infrastructure consulting firm, consolidated over 100 ERP systems into Oracle E-Business Suite on OCI, then built an interactive analytics platform using Oracle Autonomous AI Lakehouse and OCI Generative AI. Using Oracle Digital Assistant's text, chat, and voice interfaces plus open-source large language models (Cohere and Llama) in Oracle Generative AI, finance and project teams pose conversational-language questions about profitability and performance and get natural-language answers that are correct almost 100% of the time, per the company. Tetra Tech is also working with Oracle to make the chatbot proactively flag risks like potential project budget overruns and plans to deploy AI agents to automate tasks such as fixing transaction errors and streamlining field-staff time entry.

86/100HighPrimary source
Tetra Tech· United StatesOracle Autonomous AI Lakehouse · OCI Generative AI · Oracle Digital Assistant

Was this helpful?

Your feedback helps us improve our use case database