General Motors’ self-driving unit Cruise said its test vehicles experienced a rapid rate of improvement in the second half of 2019, enabling it to edge past Google affiliate Waymo in data reported to California’s Department of Motor Vehicles.
Data released last week by California showed Waymo and Cruise had the greatest number of test miles between “disengagements,” when a human driver must intervene to take control from a self-driving system during testing on public roads.
The disengagement data is widely used as a yardstick to compare companies testing self-driving vehicles on California roads, and is often cited as evidence that Waymo leads the sector.
Both companies last week criticized the disengagement data. Waymo tweeted that the disengagement metric “does not provide relevant insights” nor does it distinguish Waymo’s “performance from others in the self-driving space.”
While the annual data showed that Waymo had the greatest average number of miles between disengagements for the full year, Cruise showed a greater rate of improvement in the second half.
Cruise said the data is more useful for showing an individual company’s performance. It said its miles between disengagements in the second half jumped to 20,110, compared with 7,635 in the first half.
Focused on improvement
Cruise, which tests its self-driving vehicles mainly on the streets of San Francisco, noted that it is “intensely focused on rate of improvement.”
“Focusing our testing in a dense urban environment has allowed us to improve at a much faster rate than in a simpler suburban setting,” said Cruise spokesman Ray Wert.
Waymo did not respond immediately to a request for comment.
Waymo also saw its miles between disengagements improve from 11,887 in the first half to 14,819 in the second half.
As the annual California data was released last week, Waymo said that much of its real-world system validation data comes from Phoenix, where the company has been testing self-driving vehicles for several years and operates a small commercial ride sharing fleet.
The company’s self-driving performance in Phoenix “is largely unrelated to our California testing,” which Waymo said is mainly for engineering development.
“We don’t think (California) disengagement data should be used to compare performance, or judge readiness or competency,” Waymo said.