Advanced Micro Devices (AMD), a leader in high-performance and adaptive computing solutions, has adopted the rFpro-powered AV Elevate simulation platform to accelerate the development of automated driving technologies. The collaboration enables AMD to leverage AV Elevate’s advanced simulation capabilities to tune and test its automated parking systems on thousands of parking scenarios while reducing reliance on physical testing.
“AV Elevate’s ability to generate precise synthetic training data and test complex parking scenarios quickly has significantly reduced our development time and cost,” said Simon George, director of embedded software – solutions engineering at AMD. “The platform allows us to more rapidly iterate and develop our automated parking systems by testing them against countless edge cases that would be impractical to recreate in the real world.”
The announcement follows the successful demonstration of the AMD-powered automated parking solution at CES 2025. The company used high-fidelity simulations from rFpro to showcase its parking assistance systems in a variety of virtual scenarios. The demonstration highlighted the technology’s ability to handle challenging parking scenarios, including tight spaces, complex maneuvers and various lighting conditions.
“It has been fascinating to collaborate with AMD, who are at the forefront of automated driving and ADAS technologies,” said Matt Daley, technical director at rFpro. “The selection of AV Elevate by AMD helps to validate the platform’s position as the industry’s most advanced simulation solution for autonomous vehicles. We are proud to be involved in helping to accelerate the development of safer, more reliable automated driving systems that will benefit drivers worldwide.”
AV Elevate is a fully integrated simulation solution that enables the tuning of sensors, the training of perception and control algorithms and testing of the full AV technology stack. It is the industry’s most advanced platform to provide closed-loop perception testing and the creation of engineering-grade synthetic training data.
The platform integrates high-fidelity sensor models for all major AV sensor types, such as cameras, lidar and radar, and includes a comprehensive library of standard sensor models alongside digital twins of commercially available sensors.
At the core of AV Elevate is rFpro’s physically modeled virtual environments and ray-tracing rendering technology. Every element in the scene has been physically modeled with realistic material characteristics and a road surface model accurate to 1mm, enabling the production of highly realistic training data.
rFpro’s library of more than 180 real-world digital twins provides a highly accurate and diverse virtual proving ground. This gives AMD access to a comprehensive range of locations for complex scenarios, including typical underground, city and rural parking locations as well extensive real-world public roads.