Industry Perspectives


 
 
tri.jpg
“It’s the prediction piece that’s still the great unknown. Humans are very good at predicting human behavior on the road. Machines will need to be able to predict and anticipate human behavior much better.”
— Gill Pratt, CEO of Toyota Research Institute, March 2018
“The road, more than simply a system of regulations and designs, is a place where many millions of us, with only loose parameters for how to behave, are thrown together daily in a kind of massive petri dish in which all kinds of uncharted, little-understood dynamics are at work. Whether or not we realize it, we are always making subtle adjustments in traffic. A kind of nonverbal communication is going on.”
— Tom Vanderbilt, Traffic - Why We Drive The Way We Do
nycdot.png
“Traffic is as much an emotional problem as it is a physical and mechanical one. As time goes on the technical problems become more automatic, while the people problems become more surrealistic.”
— Henry Barnes, Legendary New York City Traffic Commissioner in the 1960s
argo.png
“A self-driving car has to understand how humans behave. It needs to know the difference between a car that is idling in the right-hand lane and one that is about to parallel park. It needs to predict that the jogger running toward the corner will stop for traffic, but that the kid running to chase a basketball might not. It needs to be able to navigate a four-way stop, which in polite parts of the country involves lots of eye contact and you-first hand gestures. This goes beyond just seeing and understanding the world - it means understanding what each of the actors in the world is going to do. Driving isn’t just a mechanical task — it’s a social act.”
— Bryan Salesky, Co-Founder of Argo
Aurora-Logo.jpg
“The choices made by driverless cars are critically dependent on understanding and matching the expectations of human drivers. This is the heart of the problem going forward.”
— Chris Urmson, April 2017
waymo.png
“How can we make the autonomous vehicle adapt to the drivers that it’s sharing the road with? How do you tailor it to be more comfortable or drive more naturally? You really need a system that fricking works. Autonomous vehicles need reasoning to understand intentions of other drivers and pedestrians.”
— Anca Dragan, Waymo, 2017
lyftlogo.png
“One of the biggest challenges is that the habits of robots and humans are not the same. Robots will do things that humans consider completely unreasonable and those unreasonable things will condemn self-driving cars.”
— David Lu, Director of AV @Lyft, Former Product Manager @Waymo, March 2018
zoox-300x300.png
“Part of driving well in a city is not being so conservative that you don’t move. People are just gonna honk at you, and you won’t have a product.”
— Jesse Levinson, CTO & Co-Founder of Zoox, July 2018
vergelogo.png
“Anyone can buy a bunch of cameras and LIDAR sensors, slap them on a car, and call it autonomous. But training a self-driving car to behave like a human driver [...] is on the bleeding edge of artificial intelligence research. Waymo’s engineers are modeling not only how cars recognize objects in the road, for example, but how human behavior affects how cars should behave.”
— The Verge, Inside Waymo’s Strategy to Grow the Best Brains for Self-Driving Cars, May 2018
“As a driver approaches a given cyclist, they can make an individual judgment on that person’s perceived needs. They are judging each person as individuals. They’re not just invoking some default behavior for passing cyclists.”
— Ian Walker, Professor of Traffic Psychology, University of Bath, UK, and Max Planck Institute for Human Cognitive and Brain Sciences
mittechreview.jpg
“Neither the cool look of the shuttle nor the fact that the first stop was a doughnut shop could offset how sick sitting in it made me feel. Caution is great, but its jerky stop-and-start movements made me want to hurl.”
— Rachel Metz, MIT Technology Review, January 2018
“Merges, do I go ahead of you, do I go behind you? There’s a lot of signaling, there’s feedback of your behavior and my behavior. It gets into this problem of deeply understanding the intent of other actors in the world, making predictions about how they are going to behave and then reacting in a way that is socially acceptable.”
— Dmitri Dolgov, Waymo CTO, Aug 2018
“Driving requires a lot more than perception and vehicle operating skills. They require deep understanding of local rules and expectations. They also require constant communication and coordination with other drivers, including signals, gestures and so on. This kind of deep reasoning is key to numerous edge cases and improving the general abilities of driverless cars.”
— Sacha Arnoud, Director of Engineering @Waymo, Feb 2018