rFpro’s ray tracing engine is a next-generation, highly-realistic simulation rendering technology that has been designed specifically to accurately replicate the world as perceived by vehicle sensor systems. As a result, the data generated by the simulation can be used to train and develop ADAS and autonomous systems, significantly reducing the industry’s dependence on gathering real-world data.
Our ray tracing engine uses multiple light rays through the scene to accurately capture all the nuances of the real world. As a multi-path technique, it can reliably simulate the huge number of reflections that happen around a sensor. This is critical for low-light scenarios or environments where there are multiple light sources to accurately portray reflections and shadows. Examples include multi-storey car parks and illuminated tunnels with bright ambient daylight at their exits, or urban night driving under multiple street lights.
Ray tracing provides such high-quality simulation data that it enables sensors to be trained and developed before they physically exist. As a result, it removes the need to wait for a real sensor before collecting data and starting development. This will significantly accelerate the advancement of AVs and sophisticated ADAS technologies and reduce the requirement to drive developmental vehicles on public roads.
Vehicle sensors, such as camera systems, ‘see’ the world differently to the human eye and it is critical that these nuances are replicated in simulation in order to create highly correlated training data. For example, the varying exposures captured by modern HDR (High Dynamic Range) cameras contain blurring, caused by fast vehicle motions or road vibrations. Our multi-exposure camera API ensures that this phenomenon is accurately replicated and includes a physically modelled rolling shutter effect.
Contact one of the team if you’d like to learn more about rFpro’s ray tracing technology and how it could revolutionise your development projects.