The accuracy of simulation technologies is currently a limiting factor in the development of autonomous vehicles, with the industry still heavily dependent on collecting and processing real-world physical data for the training and testing of systems. This process is expensive, time-consuming and doesn’t cover the variety and quantity of edge cases necessary to provide manufacturers with confidence in the systems performance.

rFpro’s new ray-traced simulation rendering technology can deliver high fidelity engineering-grade synthetic training data. It has been developed in partnership with a leading sensor manufacturer to integrate and improve the accuracy of virtual camera models as well as validate and correlate the results.

During the presentation, rFpro will showcase how this technology is helping to advance vehicle perception development and discuss the requirements and challenges associated with developing high-quality training data.

rFpro will also highlight the value of massively scaling the production of this data using the customer’s own High Performance Computing (HPC) and utilising their private cloud resources. This approach offers a highly flexible and instantly scalable way of adjusting data production volumes, whilst still maintaining complete control of IP protection.