Robotaxi operator Waymo says its partnership with Nexar, a machine-learning tech firm dedicated to improving road safety, has yielded the largest dataset of its kind in the U.S., which will help inform the driving of its own automated vehicles.
As part of its latest research with Nexar, Waymo has reconstructed hundreds of crashes involving what it calls ‘vulnerable road users’ (VRUs), such as pedestrians walking through crosswalks, biyclists in city streets, or high-speed motorcycle riders on highways.
“By leveraging over 500 million miles of Nexar’s driving data, we’ve been able to capture a wide range of driving events and environments, providing a more comprehensive picture of VRU safety than ever before,” Waymo says in a blog on its website.
The National Highway Traffic Safety Administration estimates that in 2022 alone, 7,522 pedestrians were killed and more than 67,000 were injured in the U.S.
Yet, Waymo says data on collisions with VRUs remains scarce compared to vehicle-to-vehicle collisions, as many incidents do not get reported to the police or insurance companies.
Besides its own driving fleet, Waymo says other autonomous driving companies can use the collected dataset to evaluate an automated system’s performance in simulations ahead of deployment.
So far, Alphabet-owned Waymo operates the only functioning robotaxi service in the U.S., with a fleet of about 700 self-driving vehicles already on the road in Phoenix, Los Angeles and San Francisco.
Rival services still under development include General Motors’ Cruise, Amazon’s Zoox, and Tesla’s Robotaxi.
Cruise had to stop operations last year after one of its vehicles struck a pedestrian. And in October, regulators opened an investigation into 2.4 million Tesla vehicles equipped with its full-self driving (FSD) software following three reported collisions and a fatal crash.
Tesla’s self-driving technology relies on multiple onboard cameras to feed machine-learning models that, in turn, help the car make decisions.
Meanwhile, Waymo’s technology relies on premapped roads, sensors, cameras, radar, and lidar (a laser-light radar).