Self-driving cars are leading people in highway safety. Adding to mounting evidence lurching towards a unanimous conclusion, Google conducted some more in-house number crunching and found that autonomous vehicles end up in one less crash per million miles driven than people controlled vehicles, according to an Engadget report. That is, a self-driving vehicle is 27-percent more likely to stay in one piece over an extended period of time.
The exercise focused exclusively on Google’s self-driving test fleet, and by Google’s estimates, has never taken blame in an accident. The data reveals that conventional drivers end up in 4.2 crashes for every million miles driven, whereas peopleless cars result in 3.2 crashes per million miles. Although convincing, studies have only been observed in select states without considering the number of miles people drive over a long course of time—several billion miles—compared to the short duration of Google cars.
Nonetheless, life imitating art initially suggests that it’s not as ominous as feared.
“We’re working toward vehicles that take you where you want to go at the push of a button,” Google describes the technology on its website. “We started by adding components to existing cars like our Lexus SUVs, then began designing a new prototype from the ground up to better explore what should go into a fully self-driving vehicle. We removed the steering wheel and pedals, and instead designed a prototype that lets the software and sensors handle the driving.
“With fully self-driving technology, the car is designed to do all the work of driving and the human ‘driver’ is never expected to take control of the vehicle at any time,” Google added in its FAQ. “The National Highway Traffic Safety Administration (NHTSA) calls this full self-driving automation (level 4). This is the type of technology Google is working on.”