RFpro has launched an integrated simulation solution that accelerates the development of autonomous vehicles (AVs) by enabling the tuning of sensors, training of perception and control algorithms, and testing of the full technology stack. The company says that its “AV elevate” is the industry’s most advanced platform to provide closed-loop perception testing and the creation of engineering-grade synthetic training data.

“AV elevate is a game-changing simulation platform,” said Matt Daley, Technical Director at RFpro. “It is the most advanced solution to enable the complete AV technology stack to be tuned, trained, and tested. For the first time, AV developers can confidently reduce their reliance on real-world testing, instead subjecting systems to AV elevate’s highly accurate synthetic data. Now, testing and development can be massively and cost-effectively scaled like never before, removing the biggest barrier to the advancement of AVs.”

A member of the AB Dynamics Group plc, RFpro provides a simulation environment for the development and testing of vehicles for the automotive and motorsport industries. The top ten OEMs that were early adopters of its technology have already launched road cars that started their development not on a test track but in its virtual environment. The company claims motorsport market leadership in professional driver-in-the-loop simulator software, and it maintains what it says is the largest library of race-circuit digital-twin models for F1, NASCAR, WEC, IMSA, Indy, Formula E, Super-GT and Australian V8 Supercars series.

To create its new solution, company engineers have integrated several new technologies into their existing platform including lidar, radar, and camera models; a new Simulation Manager to simply define the full vehicle sensor suite and create base test scenarios with thousands of iterations; and compatibility with high-performance computing (HPC) in the cloud to conduct and scale the testing rapidly.

“The purpose of AV elevate is to help OEMs reduce their reliance on testing and data collection on public roads to significantly cut costs and accelerate development,” added Daley. “We believe our fully integrated simulation solution is the most accurate available, and this gives manufacturers the confidence needed to make that move.”

AV elevate integrates high-fidelity sensor models for all major AV sensor types and enables installation choices and configurations to be tuned and optimized. The platform’s synchronous architecture allows for the evaluation of hundreds of sensors, enabling sensor fusion testing to a level of accuracy not previously possible, according to the company.

Included within the simulation solution is a comprehensive library of standard sensor models alongside digital twins of commercially available sensors. This allows development to progress before a physical sensor exists or enables OEMs to benchmark technologies against their competition.

Typically, AV developers manually annotate each frame of video, lidar point, or radar return to identify objects in the scene to create training data. This approach generally takes 20 min per frame and has a 10% error rate. AV elevate automates this process using engineering-grade synthetic training data, meaning it is 100 times faster and 150 times more cost-effective than manual annotation and is said to be completely error-free.

The Simulation Manager provides a user-friendly way to set up and execute test scenarios simply and automatically, allowing large-scale simulations with multiple sensor systems to be easily created. It can automate variations in vehicle and environment models such as changes to sensor types, positioning of sensors on the vehicle, traffic, pedestrians, time of day, weather conditions, street furniture, and obstructions. This enables the quick creation of focused variations of the base scenario, creating hundreds of edge-case scenarios for testing and connecting to large external third-party databases.

Due to AV elevate’s synchronous architecture, the time to complete tests is directly linked to the available computing power. As the platform is cloud and HPC-compatible, it allows users to flexibly and rapidly scale testing as required without significant investment in internal computing hardware.

At the core of AV elevate is RFpro’s physically modeled virtual environments and ray-tracing rendering technology. The company’s library of more than 180 real-world digital twins provides an accurate and diverse virtual proving ground with elements in the scene physically modeled with realistic material characteristics and a road surface model accurate to 1 mm.

The ray-tracing rendering technology replicates the nuances of how a vehicle’s sensor system perceives the world. The multi-path technique reliably simulates the large number of light and electromagnetic sources and reflections around a sensor. It generates the highest fidelity data for sensors and includes phenomena such as motion blur and rolling shutter effects.

To see AV elevate in action, check out the video at https://youtu.be/R7DPxp4MwSU.