How Nvidia’s Omniverse Can Unlock Building Innovation with IFC

Years ago, the construction industry started working on Industry Foundation Classes (IFC) – a data model for describing architecture, engineering, construction and operations (AECO) data. The specification has made it easier to export data between tools. A major bottleneck, however, is that IFC only tells construction software vendors what kind of data to include, not how to display it in a particular file format, which can lead to ambiguity and significant manual effort to share data between tools.

However, now Nvidia is implementing IFC on top of the universal scene description file (USD) that underlies the Nvidia Omniverse. This complements Nvidia’s broader efforts to: developing connectors for various 3D authoring tools for the AEC industry, including Autodesk Alias, Autodesk Civil, Siemens JT, SimScale and Open Geospatial Consortium formats.

The USD implementation for IFC is still in its early stages, but once the effort kicks in, it promises to streamline construction workflows with multiple tools from different vendors. It will make it easier for engineers to take advantage of Nvidia’s rich AI tooling to analyze 3D data, simulate the impact of various design decisions, and automatically generate a 3D inventory to improve maintenance and operations.

“Ensuring cross-platform consistency has been a difficult task for several software companies,” George Matos, Omniverse AECO senior product manager at Nvidia, told VentureBeat. “The earlier development of standardized and open file formats created bridges between different AECO authoring applications. As technology and its features advance in AECO, we are looking at more extensible formats to enable full cross-platform collaboration as well as extended functionality on the open file format. This means, as it were, enabling an open dialogue between the design applications and USD. While the technology is constantly evolving, we strive for complete reliability and consistency between the authoring applications and formats and Nvidia Omniverse, as well as allowing proprietary features and computing at the authoring source or within Omniverse.”

Matos sees these efforts as planting the seed for leveraging construction data in more processes. For example, an automaker can build a physically accurate digital twin of its factories and cars and then use the same ground truths in their sales, marketing and customer configurators. This requires that all of the AECO data from the company’s factories, CAD data from the assembly lines, design data from the manufacturing models and even the autonomous robots that operate these facilities all contribute to a single virtual model. These workflows require a standardized data format and framework to keep all 3D assets and data synchronized with high resolution and fidelity.

IFC helps with transfer

In the late 1990s, there was no easy way to move data across various engineering and design tools. So AECO companies and software vendors came together to simplify the process. Instead of focusing on a specific file format, such as GIF for images and MP3 for audio, they developed a data standard, leaving it to each vendor to implement it in a file format. IFC makes it suitable for understanding how different elements in a building interact, such as how a stool, door, wall and space fit together in a structure.

This made sharing data easier, but with limits.

“For the most part, IFC is used as a kind of one-way transfer mechanism,” said Greg Schleusner, director of design technology at HOK and co-director of the engineering space at BuildingSmart, which manages the IFC standard.

This one-way flow helps teams export data for analysis, detecting scheduling issues, or simulation. But organizations generally reverted to the original tool when changes were needed.

An underlying challenge is that the different CAD tools can use different ways to represent 3D data. For example, some use a mesh approach, while others view the world as solids.

“All of these tools have a separate view of the world and how to represent geometry, and that’s where interoperability is the hardest,” Schleusner said.

As a result, the tools end up being linked to the data for reference rather than doing a design transfer, allowing teams to take the data into a new tool and develop it further.

“It’s certainly possible and technically capable, it’s just not used very often,” he explained.

USD to modularize data

Nvidia’s implementation promises to make it easier to display IFC and other data about the built world in a more consistent format. In addition, it becomes easier to extract information for specific use cases. Schleusner believes this will make sharing a subset of information with a contractor easier. This could also make it easier to implement suggestion systems that recommend specific types of door assemblies for a given project, in the same way GitHub’s Copilot tool does coding recommendations.

Nvidia is betting USD will become the dominant format for collaboration, computation, AI workflows and design across industries. Omniverse is built entirely on USD. Matos said they are working with AECO leaders, including Autodesk, Bentley Systems and Graphisoft, to build connectors to the Omniverse platform.

Nvidia is actively developing capabilities internally and with its ecosystem partners to connect more integrated systems and data types, including IoT, BOM data, piping and instrumentation diagrams (P&ID) and more, to Omniverse.

“Simulating real-world and virtual data together allows facilities to be used optimally,” Matos says. “This is one of the main drivers behind the open data format approach to using USD with Omniverse.”

Later, Matos expects that this could enable the AECO industry to move from building several static independent models to building live extended digital twins. This provides a live, single-source virtual representation of buildings, environments and cities. This could help train AI agents in thousands of scenarios before deploying them live in the real world.

“I’m thrilled that Nvidia, Unity and Unreal are finally entering the built environment arena. Better late than never,” said Steve Holzer, director of HolzerTime, an architectural and planning consultancy and member of the infrastructure working group of the Digital Twin Consortium. “As the novelty of these tools wears off, it will uncover the incredible value of engagement in their physical space to a wide audience.”

He believes one of the biggest opportunities is to make it easier to contextually parse data for specific use cases. He believes that IFC is a very heavy data structure. Only a few groups have found ways to leverage it in different domains, such as COBie for operations, SPARKie for electricity, HVACie for HVAC, and WSie for water. USD could make it easier to develop new AI models for parsing the structure the way NLP tools parse medical entities from health records.

“AI/ML will exponentially increase the value of data in all dimensions when the industry understands how to use it beyond new,” said Holzer.

Barry Bassnet, a technical expert on digital twins, has been using photogrammetry techniques to capture 3D models of the built environment for 43 years. He is excited about the potential for USD to transform the construction industry.

“USD gives us a language to emulate to some extent how our brain works and apply it to new processes, especially AI,” he said.

The missing link, he says, is a tool that automatically gives the built environment meta tags. Today, people have to manually create links across and between spatial entities to other types of documentation, such as PDFs and their content. The combination of USD and auto-tagging capabilities would make it easier to specify a lock for a window and then link to a 3D repair manual or get a replacement key.

Bassnet watched with excitement as VRML came and then faded due to bandwidth overhead.

“USD is the best opportunity to find a way to make the metaverse and concept of digital twins work,” he said.

Schleusner believes the AEC industry can learn from USD’s success in entertainment. The entertainment industry is increasingly making improvements to USD rather than proprietary file formats. As a result, entertainment workflows can exchange data directly between tools rather than through more complex transformations via APIs. Schleusner believes the AEC industry should take a similar approach to achieve the kind of innovation promised by digital twins for the built environment.

“The most instructive thing for the built world to take off from USD is that it’s much easier to talk to one dataset than it is to many application APIs,” says Schleusner. “The new IFC implementation for USD will shift the needle towards more of an exchange approach rather than an interoperability approach. Only then will we be much closer to success.”