Waymo: The future of autonomous driving with Vincent Vanhoucke

“In some ways, the autonomous driving problem is the simplest robotics problem. You have basically two things you need to do. You have to know if you're going to turn left or right. That's one number. And then you have to know if you're going to accelerate or decelerate. That's two numbers. In most robotics problems, you have to predict hundreds of numbers to figure out all the degrees of freedom of your robot. This is the simplest robot that has only two degrees of freedom. But that hides all the complexity of the actual problem.”

“Safety really comes from taking different sources of information, never entirely trusting them 100% and merging the evidence based on the different pieces of hints of information that you get, such that you can have an overall system that you can trust that has a much higher degree of fidelity. We often say there's only one way to be right. There is many ways to be wrong. If your different sensors are wrong in different ways, you know that there is something not right about the information that you get.”

“The rate of accidents that lead to severe injury is about 88% lower with Waymo cars. And that gap really we can attain by not just doing what every human would do, not by hitting the average, but also having a more conservative safety posture.”

“What's interesting is that we tend to model those interactions as little bits of conversations. Literally, it's visual movement conversations. I move forward. What will this other car do? This car stops. Okay, I can go. Or this car goes, then I'm going to have to stop. It's literally modeled as a visual or motion conversation. It's very similar to what you would do in a conversational agent. So there are lots of parallels between the conversational AI and the autonomous driving problem that we can leverage and learn from.”

“So one cheat is that we can do all of that in the Cloud first. So we can build essentially a very large driver in the Cloud, very large model that incorporates all that information, all the sensor information, all the experience that we have from driving millions of miles, all the data that comes from various sources that provides us with world knowledge. But once you have that teacher driver, you can use that to teach the onboard system based on that supervision that you provide from the cloud-based driver and distill all that information onto the onboard system.”

“One thing that we've learned over the years is that you want to be basically the most normal car on the road. You don't necessarily want to be more timid than other drivers on the road because then people will pick up on that difference and actually abuse the car. If on the opposite side you're more aggressive than the average driver, then you're disruptive to the flow of traffic or you violate other people's expectations. So the sweet spot is really if you act like the most boring, normal driver on the road, it turns out it's also the safest.”

“In fact, what we find is that very often humans are not very good at risk analysis. They will do things that if you do the math are not necessarily safe. A lot of people will tailgate at distances that are much smaller than what is recommended by people who've done the analysis. People also don't necessarily reason about what could happen when it's not in their eye. So, you have a big truck occluding a pedestrian crossing. You have to think about it's very possible that a pedestrian will be crossing through there.”

“Snow is a typical example of, here is something that is big, massive, potentially on the roads, but you have to reason about and say, okay, this is snow, so the right thing for me to do is to drive through it, unless it's a big pile of snow and you can't. But if it's a reasonable pile of snow, just that you experience in normal driving, you want to cross through that snow. If it were a rock, you wouldn't do that. So categorizing things at a fine grain like this and understanding what you can or cannot do is really part of the equation.”

“I don't think there is any need for any fundamentally new breakthroughs. I think we're in the right generation of technology. I'm not saying we have solved it. I'm saying autonomous driving has a history that dates back 30 years. It has to have gone through, I want to say, five different generations of technology along the way. I feel that today is the day. We are in the right moment. I don't think we need another job for it to become practical in the real world.”