Heavy rain and blizzards aren’t the only forms of severe weather Waymo’s self-driving vehicles encounter on the regular. In a blog post published this morning, the Alphabet subsidiary laid out the ways its cars in over 25 cities tackle fog, dust, smoke, and other dangerous conditions that trip up even human drivers.
“Challenging [environmental] conditions, which affect human driver and vehicle performance, are one of the leading contributors to crashes on our roads … Poor perception creates significant risk for other road users including pedestrians, cyclists, and other vehicle occupants,” wrote Waymo chief safety officer Debbie Hersman. “Waymo is working hard to master a variety of weather scenarios as part of our mission to improve road safety.”
To this end, Waymo says its autonomous vehicles are designed to detect sudden extreme weather changes, such as a snowstorm, that could impact their ability to drive safely. If conditions deteriorate below a certain threshold, they come to a safe stop until things improve.
Some experts believe this sort of situational awareness will play a critical role in the safe deployment of driverless cars globally. For its part, Waymo rival and GM subsidiary Cruise is testing computer vision and sound detection AI to help driverless vehicles pause for passing police cars, fire trucks, ambulances, and other emergency vehicles.
That said, Waymo’s cars are remarkably robust. In Arizona, where intense dust storms (known as haboobs) aren’t uncommon, its cars’ systems tap radar and lidar to spot other road users even when camera visibility is extremely limited. (Waymo’s sensor stack includes five custom-designed lidars that bounce light off of objects to map them three-dimensionally, along with five front- and side-facing cameras and the aforementioned radars.)
“While self-driving cars and human drivers alike are limited by the performance capabilities of the vehicle itself, and there are environmental conditions that no driver, human or technology, should drive in, AVs have the potential to improve one of the greatest performance limitations: visibility,” added Hersman.
It’s been a newsy week for Waymo, which on Tuesday announced it’d expand its driverless car testing to Florida, first on a private track and in the coming months on public roads. On Wednesday, the company released an open source corpus containing sensor data collected over the course of the millions of miles its cars have driven to date.
Over six months ago, Waymo launched Waymo One, its commercial driverless taxi fleet of over 600 cars with safety drivers behind the wheel, and the company says the fleet has grown to serve over 1,000 riders in that time. Separately, Waymo recently revealed that its cars have driven 10 billion autonomous miles in simulation and 10 million real-world autonomous miles in 25 cities, and it announced last year that it would add up to 62,000 minivans to its fleet and equip 20,000 Jaguar I-Pace electric SUVs with its autonomous systems by 2020.
Waymo has competition in Yandex, Tesla, Zoox, Aptiv, May Mobility, Pronto.ai, Aurora, Nuro, and GM’s Cruise Automation, to name just a few. Daimler last summer obtained a permit from the Chinese government that allows it to test autonomous cars powered by Baidu’s Apollo platform on public roads in China. Beijing-based Pony.ai, which has raised $214 million in venture capital, in early April launched a driverless taxi pilot in Guangzhou. And startup Optimus Ride this month built out a small autonomous shuttle fleet in New York City, becoming the first to do so there.
According to marketing firm ABI, as many as 8 million driverless cars will be added to the road in 2025, and Research and Markets anticipates that there will be some 20 million autonomous cars in operation in the U.S. by 2030.