The Province

Autonomous cars still need that human touch

Rate of potential collision ‘not terribly high, but certainly not trivial’

-

Futuristic self-driving cars travelling along California roads have needed plenty of oldfashion­ed human interventi­on to stay safe.

The reports show wildly different levels of success since on-road testing started in September 2014. Experts in the technology said Google, whose cars drove the most by far, performed relatively well, though they also cautioned the testing typically happened during good weather. Other companies reported frequent instances in which the person who is required to be in the front seat — just in case — had to grab the wheel.

Nissan, for example, tested just 1,485 miles in public, but reported 106 cases where the driver had to take control. The automaker has said it plans to have “commercial­ly viable autonomous-drive vehicles” by 2020. A spokeswoma­n did not return a request for comment.

Google said its cars needed human help 341 times over 424,000 miles. That would be the equivalent of about 10 times per year, given the 12,000 miles the average U.S. vehicle travels annually. In 11 of the 341 instances, Google said its cars would have ended up in a crash.

The head of the company’s self-driving car project said that while the results are encouragin­g, they also show the technology has yet to reach its goal of not needing someone behind the wheel.

“There’s none where it was like, ‘Holy cow, we just avoided a big wreck,’ ” said Chris Urmson, Google’s self-driving car project leader. “We’re seeing lots of improvemen­t, but it’s not quite ready yet. That’s exactly why we test our vehicles with a steering wheel and pedals.”

The California Department of Motor Vehicles, which is writing new regulation­s for the technology, said it was still reviewing the reports.

Google reported 272 cases in which the cars’ software or on-board sensors failed. Though Google did not release detailed scenarios, the problems included issues with the self-driving cars seeing traffic lights, yielding to pedestrian­s or committing traffic violations. There were also cases where interventi­on was needed because other drivers were reckless and several dozen instances of an “unwanted manoeuvre” by Google’s car.

Bryant Walker Smith, a professor at the University of South Carolina who closely follows self-driving car developmen­ts, said Google’s rate of potential collisions was “not terribly high, but certainly not trivial.” He said it remains difficult to gauge how self-driving cars compare to accident rates among human drivers since even the best data under-report minor collisions that are never reported to authoritie­s.

While Google’s problem rate is “impressive­ly low,” a trained safety driver should remain in the front seat, said Raj Rajkumar, an engineerin­g professor at Carnegie Mellon University who specialize­s in self-driving cars. According to data in Google’s report, a driver typically took control within one second of the car asking for help.

Drivers at other companies often reacted quickly as well, according to their reports, though Volkswagen Group of America reported in one case it was more than 12 minutes before the person took control. A spokesman did not have immediate comment.

John Simpson, a frequent critic of Google who focuses on privacy issues for the nonprofit group Consumer Watchdog, said the company’s report “underscore­s the need for a driver behind the steering wheel capable of taking control of the robot car.”

Google has argued to California regulators that once the company concludes the cars are ready for the public to use, they should not need a steering wheel or pedals because human interventi­on would actually make them less safe.

Google released its report Jan. 12 before the agency posted reports from other companies in what Google described as an effort to be transparen­t about its safety record. The company had lobbied against having to report disengagem­ents in the first place, saying the data could be misinterpr­eted.

Other companies testing self-driving cars in California include Tesla and Mercedes-Benz, along with parts suppliers Bosch and Delphi. Google’s testing mostly involves driving around the company’s Silicon Valley headquarte­rs or the streets of Austin, Texas. The company’s rate of human interventi­on has improved in recent months, according to data, but Urmson cautioned the rate might again rise as Google subjects the cars to more challengin­g environmen­ts and weather conditions.

Google said its cars would have been responsibl­e in eight of the 11 avoided accidents, according to computer modelling the company performed later. In two other cases, its cars would have hit a traffic cone.

Google cars have been involved in nine collisions since September 2014. In each case, the other car was responsibl­e, according to Virginia Tech University analysis.

“It’s not quite ready yet. That’s exactly why we test our vehicles with a steering wheel and pedals.” — Google project leader Chris Urmson

 ?? — THE ASSOCIATED PRESS FILES ?? Self-driving cars needed some old-fashioned human interventi­on to avoid crashes during testing on California roads, Google revealed Jan. 12. The results, it says, are encouragin­g but show the technology has yet to reach its goal.
— THE ASSOCIATED PRESS FILES Self-driving cars needed some old-fashioned human interventi­on to avoid crashes during testing on California roads, Google revealed Jan. 12. The results, it says, are encouragin­g but show the technology has yet to reach its goal.

Newspapers in English

Newspapers from Canada