Robotaxi operator Waymo says its partnership with Nexar, a machine learning technology company dedicated to improving road safety, has produced the largest data set of its kind in the US that will help drive its own automated vehicles influence.
In its latest research with Nexar, Waymo reconstructed hundreds of crashes involving so-called “vulnerable road users” (VRUs), such as pedestrians crossing crosswalks, cyclists on city streets, or speeding motorcyclists on highways.
“By leveraging over 500 million miles of Nexar driving data, we have 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 7,522 pedestrians were killed and more than 67,000 injured in the United States in 2022 alone
However, according to Waymo, there is still little data on collisions involving VRUs compared to collisions between vehicles, as many incidents are not reported to police or insurance companies.
In addition to its own vehicle fleet, Waymo says other autonomous driving companies can also use the collected data set to evaluate the performance of an automated system in simulations before deployment.
So far, Alphabet-owned Waymo operates the only functioning robotaxi service in the US, with a fleet of around 700 self-driving vehicles already operating in Phoenix, Los Angeles and San Francisco.
Competing services still in development include General Motors' Cruise, Amazon's Zoox and Tesla's Robotaxi.
Cruise was forced to suspend 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 full self-driving (FSD) software after three reported collisions and one fatal accident.
Tesla's self-driving technology relies on multiple onboard cameras to power machine learning models, which in turn help the car make decisions.
Meanwhile, Waymo's technology is based on pre-mapped roads, sensors, cameras, radar and lidar (a laser light radar).
Comments are closed.