Some of the new products on show
Revolutionary approach to AV training and testing
rFpro will showcase the latest version of its groundbreaking autonomous vehicle training and testing simulation software, Data Farming, at the ADAS & Autonomous Vehicle Technology Expo 2022.
Data Farming has been developed to accelerate the creation of high-quality, high-volume data that is necessary to train autonomous vehicle systems. The simulation software removes the industry’s dependence on manual annotation of test data, such as video, lidar point or radar return, to identify the objects in the scene (for example, vehicles, pedestrians and road markings).
“This new approach from rFpro provides a digital, cost-effective way of creating error-free data 10,000 times quicker than manual annotation, which takes around 30 minutes per frame,” said Matt Daley, rFpro’s operations director. “This step-change will enable deep learning to fulfill its potential because it significantly reduces the cost and time of generating useful training data.”
Data Farming enables manufacturers and technology providers to build complete data sets that cover the full vehicle system where every sensor is simulated at the same time. The data is synchronized across all sensors, even with the most complex hardware designs. This is essential where customers are employing sensor fusion to bring together data, for example from multiple 8K HDR stereo cameras, lidar and radar sensors at the same time.