It\u2019s the elusive \u201ccorner cases,\u201d or rare cases that seldom occur, that can get you in trouble: for example, the sun shining directly into a car\u2019s sensors or camera, inclement weather, or even a bicyclist crossing the street at night on a dimly lit street, as was the case in an unfortunate fatal Uber crash.<\/P><\/p>\n
In this final part of our discussion, we move into further understanding comprehensive autonomous vehicle testing.<\/P><\/p>\n
Edward Bernardon: Autonomous driving requires a massive amount of validation and verification cycles. And, as you go from Level 1 to 5 in a car, it goes from 100 scenarios to many millions. If you have to collect that data on the road, say at the rate that Tesla is currently collecting, it could take dozens of years. Therefore, there seems to be an obvious value in simulation technology.<\/STRONG><\/P><\/p>\n Gwen Van Vugt: <\/STRONG>Yes, that\u2019s where simulation comes in, because there\u2019s no way you can test all these scenarios in the real world. It\u2019s not only about collecting the data once, but adapting that collected data to your system and retesting it using the same data, and that is impossible in the real world.<\/P><\/p>\n You\u2019ll never be able to redrive billions of kilometers to get to that same scenario again. You will never have all parameters under control, for instance, the weather today is cloudy, but tomorrow it\u2019s sunny. So you have to bring things to the virtual world, and that\u2019s what you\u2019re seeing.<\/P><\/p>\n At this moment, there are many virtual simulation startups. It is a clear sign that there\u2019s a big market for TASS, a market where we are a mature player with over 30 years of experience on the simulation side. We\u2019re riding the wave of automated driving.<\/P><\/p>\n It\u2019s not only about creating a virtual world. It\u2019s also about sensor modeling and simulation, and to ensure it’s as accurate as possible in different physical domains like radar, LIDAR, ultrasonic, GPS, etc.<\/P><\/p>\n Another big topic where I think we have an advantage over startups is that you have to create databases of different realistic scenarios. That\u2019s an area the TASS and Siemens combination, together with Mentor, can address.<\/P><\/p>\n Paul Van Straten:<\/STRONG> It\u2019s not just important to collect regular driving data, but you also need to collect data on dangerous situations, and this can be costly. In testing and validation of any system, what you\u2019re actually looking for is the \u201ccorner cases\u201d as we call it.<\/P><\/p>\n Gwen Van Vugt:<\/STRONG> For example, if you envision a big room where most of the space is in the middle of the room \u2013 that\u2019s not the interesting space, as you know that your system will already perform in that space. The interesting thing is how your system performs at the edges of the operating space, and that is where the corner cases come in.<\/P><\/p>\n But when you start driving, even as a human being, often you\u2019re driving before you have experienced any critical situations that could possibly happen only a few times in your entire life \u2013 at least if you drive normally.<\/P><\/p>\n Human drivers are like Google and Tesla; they\u2019re collecting massive amounts of data, but 98 percent of that data is of no interest, because it\u2019s just normal driving situations.<\/P><\/p>\n You have to either collect an enormous amount of data, or the only way to test is to bring scenarios into simulation, start varying the scenarios in a virtual world and then search for your corner cases.<\/P><\/p>\n Edward Bernardon: How do you find the corner cases?<\/STRONG><\/P><\/p>\n Gwen Van Vugt: <\/STRONG>Actually, it\u2019s like the technology you use for optimization routines. You place seeds, which can come from accident databases. There are accident databases that exist in the world. One of them is the GIDAS 3D accident database<\/A>, a German in-depth accident study. They have thousands of accidents mapped into a database, and we have an interface to that.<\/P><\/p>\n This database has a parametric description of an accident in time and space, and we download that into our virtual environment and replay that accident. But the nice thing is that when we replay it, we can change everything. We can change the speed of your vehicle or the speed of the other vehicles. We can change the weather conditions or algorithms used by a controller.<\/P><\/p>\n So then from one accident case, we can blow it up into thousands of cases by just varying different parameters in that situation, and that\u2019s basically how you build up a scenario of databases.<\/P><\/p>\n![\"Autonomous](\"http:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/19\/2019\/09\/Autonomous-vehicle-testing-1.jpg\" "\\"Autonomous")
<\/span><\/P><\/p>\n