Rune Aero has revolutionized its aircraft development process using an interactive virtual wind tunnel powered by Physics AI, achieving an 80% reduction in early design costs while doubling payload capacity and cutting fuel consumption by 50%.
The groundbreaking digital twin technology combines Luminary Cloud’s Nvidia CUDA-X-accelerated CFD simulations with an Nvidia Omniverse Blueprint for real time computer-aided engineering digital twins. Ultimately engineers can observe aerodynamic effects instantly as they modify designs. This transformative approach has compressed what traditionally required months of iterative physical testing into a continuous, real-time optimization process for the autonomous cargo aircraft startup.
The company made the announcement at Nvidia’s GTC 2025 in San Jose, California.
AI Physics Transforms Aircraft Economics with Real-Time Design Optimization
Founded in 2023, Rune Aero is developing a sustainable and autonomous aircraft for the growing middle-mile air cargo market. As a new startup, they are embracing Physics AI, a modern approach to rapid design exploration. Rune Aero’s adoption of the virtual wind tunnel demonstrates how aerospace design engineers can quickly analyze many aircraft design prototypes, iterate designs, and visualize the impact in real time.
By performing virtual wind tunnel testing earlier in the design process, Rune Aero dramatically reduces future technical risk and costs compared to relying solely on conventional physical wind tunnel tests.
The company said the results are transformative: 70% reduction in operating costs for cargo operators through optimized aerodynamics and fuel efficiency, doubled payload capacity, and 50% lower fuel consumption. For operators, this translates to double-digit profitability increases that fundamentally change air freight economics.
Luminary Cloud developed the interactive virtual wind tunnel by combining its GPU-native CFD solvers leveraging Nvidia CUDA-X libraries, the PhysicsNeMo AI training framework, and Omniverse visualization API to create digital twin environments that deliver immediate design feedback. This technology stack makes other digital twin environments possible, with the ability to incorporate real-world data into the Physics AI platform.
“AI Physics models are essential for real-time interactive engineering analysis and design, but require tremendous amounts of data,” said Tim Costa, senior director CAE EDA and quantum at Nvidia, in a statement. “Luminary Cloud’s accelerated CFD solver allows customers to generate the high-fidelity data needed to train the underlying AI physics model in Nvidia PhysicsNeMo in a matter of hours.”
“It is exciting to work with aerospace companies like Rune Aero that are willing to adopt new design optimization techniques. By quickly running a large database of simulations and creating Physics AI models, Rune Aero engineers can arrive at a feasible design faster to solve important regional air transportation problems,” said Juan J. Alonso, CTO Luminary Cloud, in a statement.
“At the early stages of aircraft development, getting fast, accurate, and cost-effective design feedback is essential. Luminary’s virtual wind tunnel allows Rune Aero to test configurations earlier in the process, reducing our early development costs by over 80% compared to traditional wind tunnels and enabling faster, smarter design decisions,” said Nadine Auda, cofounder of Rune Aero, in a statement. “Rune’s optimized aircraft configuration resulting from these tests improves aerodynamic lift-to-drag ratio, combined with advanced propulsion, this doubles payload and range while cutting fuel burn by 50%, ultimately lowering operating costs for our customers.”
Luminary Cloud and nTop today also announced a new integration with Nvidia PhysicsNeMo that reduces physics-based AI design optimization from weeks or months to mere hours. By seamlessly connecting nTop’s parametric geometry generation, Luminary’s GPU-native simulation and simulation management platform, and Nvidia PhysicsNeMo via NIM microservices, engineers can now create and analyze hundreds of design variations in a single day—a process that previously took weeks to months of manual effort across disconnected systems.
