Computer Vision News - July 2019

He explains how MSC Software addresses these challenges: “ We need to create a population of scenarios that represents the operational design domain of the vehicles. There is safety standard ISO 26262 and SOTIF that specifically have requirements. SOTIF, for example, would say that it categorises all the scenarios between known safe, known unsafe, unknown safe, and unknown unsafe. What we want to do is increase the number of known safe scenarios at the expense of the unknown unsafe scenarios. We want to do probabilistic interpretation based on scenario population, based on the behaviour of the car. As a scientist, I would like to build AI that does this. ” He says another challenge is if you have an AI sensor that is 99 per cent accurate – which is very generous – and you have to drive a billion miles and every mile has multiple frames. For example, 10 frames per second, 100 seconds per mile, that’s 1012 frames on a single camera. With multiple cameras, you can easily have 1014 or more frames and you want to have one fatal crash for every 1012 frames. How do you use an algorithm that has an error rate of 10-2, and build a system that is reliable to 10-14? How do you build a system which is 10 billion times safer than the components? Edward tells us that MSC Software do this better than anybody else. They can generate scenarios and quantify the probability density that certain adverse events happen such as crashes or going over a cliff. He concludes by saying that it is very important to be able to go from the physical road, to the digital twin of the physical road, to millions of simulations with a population of scenarios, and to take the result back to the physical world and make it credible. “ How do you build a system which is 10 billion times safer than the components?” 25 DAILY CVPR Wednesday MSC Software