Luminary Cloud, a California-based startup with a scalable simulation platform, has released an open-source aerodynamic simulation model of an SUV. The first in a series foundational models called SHIFT, the SUV model was developed in collaboration with Honda and NVIDIA.
In the announcement, Luminary Cloud said, “This foundation model, combined with Luminary’s Physics AI virtual wind tunnel, addresses a critical need in the automotive industry by bridging the gap between design aesthetics and engineering performance. Currently designers and engineers are inhibited by the inability to quickly make performance-based decisions in early stage development.”
Luminary Cloud was founded in 2019 by Jason Lango, an expert in high-performance computing, cloud-based infrastructure, and cloud security, and Juan Alonso, the founder of Stanford’s Aerospace Design Laboratory and former director of NASA Aeronautics research programs.
“This project represents a fundamental shift in automotive design methodology,” said Pete Schlampp, CEO at Luminary Cloud. “By providing instantaneous, physics-informed aerodynamic feedback, our open-source foundation model enables designers and engineers to collaborate more effectively at the earliest stages of development, saving time and money—while also advancing innovation.”
The newly launched SUV model was trained on approximately one thousand simulations, with a goal of advancing to 25,000 by the end of the year, according to Luminary Cloud. The company plans to roll out new data every month, with a staged release of pre-trained models at specific dataset size milestones. The dataset within Luminary Cloud’s model will be open-source.
During NVIDIA GTC, Luminary Cloud demonstrated an interactive virtual wind tunnel using its cloud-native NVIDIA CUDA-X-accelerated CFD technology with the NVIDIA Omniverse Blueprint for real-time computer-aided engineering digital twins.
“The AI-powered virtual wind tunnel demonstrates how design engineers of physical products in the automotive, aerospace and industrial manufacturing fields can rapidly analyze, optimize and perform real-time interactive design. This new technology will enable companies to significantly accelerate their design cycles, reduce costs, and bring more innovative and optimized products to market faster than ever before,” said Luminary Cloud.
Alonso explained, “Our GPU-native method enables us to do simulations about 100 times faster than the equivalent CPU-based solver technology.”
Over time, as the physics in its technology get more robust, Luminary Cloud is expected to compete with the current CFD software vendors. The company is also adding natural language support, allowing users to set up simulation using an AI assistant. “We’re not pursuing AI just to put an AI stamp on Luminary Cloud. We’re pursuing AI to make a difference in the engineering workflows for analysis and for design optimization,” said Alonso.