Autodesk and NVIDIA accelerate engineering feedback loop for automotive designers

Autodesk announced plans to integrate NVIDIA technologies at NVIDIA's GTC Berlin.

Autodesk is extending Autodesk NavPack, which helps automotive designers bring predictive engineering insights into the vehicle design process. The planned integration will connect NavPack with NVIDIA PhysicsNeMo and NVIDIA Warp to develop additional AI model architectures and GPU-accelerated workflows. In automotive workflows, designers use Autodesk Alias to create and refine vehicle geometry. NavPack uses predictive AI models trained on a customer's existing simulation data to help designers understand how design changes could impact vehicle performance. This means a designer can evaluate aerodynamic implications while continuing to explore and iterate on a vehicle's shape in Alias, while full-fidelity simulation remains part of model training and final validation. "Designers make better decisions when engineering insight comes in the ideation phase, not the final product state," said Thomas Heermann, vice president, Automotive Design at Autodesk. "Aerodynamic prediction is just the beginning. With NavPack, we can transform Alias into an environment where critical engineering and manufacturing knowledge informs design from the very start. By bringing downstream insight upstream-while designers are still exploring and shaping ideas-we enable teams to make better-informed decisions faster, reduce iteration costs, and create designs increasingly optimized for real-world performance and production." This is industrial AI in practice: bringing predictive engineering insight earlier into the design process so teams can make more informed decisions about the products they design and make for the physical world. Autodesk's planned integration of NVIDIA libraries is intended to help advance that vision by expanding the model architectures supported by NavPack and enabling GPU-accelerated parts of the workflow for customers with compatible NVIDIA hardware.