Autonomous cars are already cruising down the streets on the road. Self-driving vehicles from Waymo, for example, are picking up riders in Phoenix, Arizona, and a company called Drive.ai is running an autonomous car system that carries people around a part of Frisco, Texas.
Time on the actual road is so valuable as of now. But engineers who work on self-driving cars have another tool at their disposal: they can test their software by just running simulations, throwing scenarios at their cars in the digital scenario of world to see how they might perform on the asphalt of the real life world.
“Ultimately, we try to make it as fast as possible,” he says. Or they can slow it down. “We do all this by bending that sim-time dimension.” They also want to make sure that what they see in simulation is an accurate reflection of what would actually happen in the real world.
And there’s no need to run one simulation at a time; they can do thousands. “We can do a million miles a week,” he says. This isn’t to say that simulation is more important than the real-world cruising, but driving the route virtually allows the car’s software to experience something that it might not encounter in the 2-mile-long route in Frisco, Texas, where Drive.ai is conducting its self-driving pilot.
“The main purpose is to make sure that we can test the edge cases, and the boundaries of our system,” he says, “and ensure we can safely handle all these scenarios before they appear in the real world.” Since self-driving cars are likely to play a bigger role in our lives—even doing things like delivering groceries—it’s important for them to get all the experience they can, whether it’s simulated or real.
There’s another way to test a self-driving car: force it to encounter something in the real world, but in a controlled way in a non-public place. In California, Waymo—whose autonomous cars have on the whole has racked up more than 8 million physical, non-simulated miles—uses a former Air Force base for testing.