Simulation software specialist, rFpro, has developed what it says is a highly accurate digital model of an expansive network of roads in Los Angeles, California, to support the development of autonomous vehicles (AV) and automated driving technologies. The virtual environment is designed to enable engineers to conduct extensive representative testing of AVs in a simulated environment before progressing to the public road.
The Los Angeles model features a 36km loop (22 miles), making it the largest public road model developed by rFpro to date. It is navigable in both directions and offers engineers a real-world-based environment for conducting testing. Capturing the intricate layout of Los Angeles’ roads, the model includes diverse configurations, such as highways, split-dual carriageways, and single carriageway sections.
“LA is one of the leading cities globally for developing and trialling autonomous vehicle technologies,” said Matt Daley, technical director at rFpro. “Our model provides OEMs with the ability to thoroughly train and test perception systems in a safe and repeatable environment before correlating these simulated results on the public road.
“One of the key benefits of our technology is enabling real-world events and conditions to be recreated in a highly accurate simulation. This provides a better understanding of what happened in that particular scenario, and allows new perception systems and control algorithms to be exhaustively tested in the same situation before deploying it on a vehicle.”
The digital model has been created using survey-grade LiDAR scan data to create a vehicle-dynamics-grade road surface, claimed to be accurate to within 1mm in height across the entire 36km route.
The digital twin features 12,400 buildings, 40,000 pieces of vegetation, and more than 13,600 other pieces of street furniture, including street lights, traffic lights, road signs, road markings, walls and fences. All of these objects have been physically modelled with appropriate material characteristics, which is critical for testing sensor systems.
The twin also incorporates aspects that challenge automated driving technologies, such as roadside parking, islands separating carriageways, drop kerbs in residential areas, rail crossings, bridges, tunnels, and a large number of junctions with varying complexity.
The breadth of coverage, varied road configurations and vehicle-dynamics-grade road surface model cater to a wide range of use cases, including testing vehicle dynamics, ADAS, human factors, and headlight development.
