New Simulation Approach to Autonomous Vehicle Training and Testing
UK-based driving simulation company, rFpro, has developed a means to slash the hardware costs associated with large-scale simulation – a development the company says has the potential to remove dependence on manual annotation of test data that is created frame-by-frame, which is both time-consuming and error-prone.
“Currently, many players in the autonomous vehicle field employ an army of people to manually annotate each frame of a video, LiDAR point or radar return to identify objects in the scene (such as other vehicles, pedestrians, road markings and traffic signals) to create training data,” said Matt Daley, rFpro Managing Director.
“This new approach from rFpro provides a digital, cost-effective way of creating the same data completely error-free and 10,000 times quicker compared to manual annotation, which takes around 30 minutes per frame with a 10 per cent error rate. This step-change will enable deep learning to fulfil its potential because it significantly reduces the cost and time of generating useful training data.”
rFpro calls the new approach Data Farming. It enables customers to build complete datasets that cover the full vehicle system where every sensor is simulated at the same time. The data is synchronised 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.
9 July 2020