Skip to main content

Self-driving car safety perspectives

At yesterday’s Opening Plenary, Chris Urmson’s keynote speech dealt with the reality of driverless cars on our roads. By far and away their greatest benefit to mankind will be the potential to achieve an incredible saving of life and injury on the roads, as Urmson, director of the Google Self-Driving Car program, revealed to delegates. In response to an Associated Press article last month disclosing that self-driving cars have been involved in four accidents in the state of California, Urmson revealed th
June 2, 2015 Read time: 4 mins
At yesterday’s Opening Plenary, Chris Urmson’s keynote speech dealt with the reality of driverless cars on our roads. By far and away their greatest benefit to mankind will be the potential to achieve an incredible saving of life and injury on the roads, as Urmson, director of the 1691 Google Self-Driving Car program, revealed to delegates.

In response to an Associated Press article last month disclosing that self-driving cars have been involved in four accidents in the state of California, Urmson revealed that over the 1.7 million miles logged by Google’s self-driving cars, they had been involved in a total of 11 accidents over the six years — all of which were minor with only light damage — and in none of them was the Google self-driving car at fault. That’s 0.64 accidents per 100,000 miles driven. As a bald, single number without context, that statistic is misleading, and following the AP article, Urmson wrote and published a detailed blog to provide the necessary context. It was written from a safety perspective to share patterns that had been observed.

“A lot of this won’t be a surprise, especially if you already know that driver error causes 94% of crashes,” Urmson says.

Even if his team’s software and sensors can detect a sticky situation and take action earlier and faster than an alert human driver, Urmson points out that sometimes it just won’t be able to overcome the realities of speed and distance.

“Sometimes we’ll get hit just waiting for a light to change. And that’s important context for communities with self-driving cars on their streets. Although we wish we could avoid all accidents, some will be unavoidable.”

Inescapable truth

Urmson acknowledges an inescapable truth: if you spend enough time on the road, accidents will happen whether you’re in a car or a self-driving car.

“Rear-end crashes are the most frequent accidents in America, and often there’s little the driver in front can do to avoid getting hit. We’ve been hit from behind seven times, mainly at traffic lights but also on the freeway. We’ve also been side-swiped a couple of times and hit by a car rolling through a stop sign. And as you might expect, we see more accidents per mile driven on city streets than on freeway; We were hit eight times in many fewer miles of city driving. All the crazy experiences we’ve had on the road have been really valuable for our project. We have a detailed review process and try to learn something from each incident, even if it hasn’t been our fault.

“Not only are we developing a good understanding of minor accident rates on suburban streets, we’ve also identified patterns of driver behaviour (lane drifting, red light running) that are leading indicators of significant collisions. Those behaviours don’t ever show up in official statistics, but they create dangerous situations for everyone around them.

“Lots of people aren’t paying attention to the road. In any given daylight moment in America, there are 660,000 people behind the wheel who are checking their devices instead of watching the road. Our safety drivers routinely see people weaving in and out of their lanes. We’ve spotted people reading books, and even one playing a trumpet. A self-driving car has people beat on this dimension of road safety. With 360 degree visibility and 100% attention out in all directions at all times, our newest sensors can keep track of other vehicles, cyclist, and pedestrians out to a distance of nearly two football fields.

“Intersections can be scary places. Over the last several years, 21% of the fatalities and about 50% of the serious injuries on US roads have involved intersections. And the injuries are usually to pedestrians and other drivers, not the driver running the red light.

This is why we’ve programmed our cars to pause briefly after a light turns green before proceeding into the intersection — that’s often when someone will barrel impatiently or distractedly through the intersection.

“These experiences (and countless others) have only reinforced for us the challenges we all face on our roads today. We’ll continue to drive thousands of miles so we can all better understand the all too common incidents that cause many of us to dislike day-to-day driving — and we’ll continue to work hard on developing a self-driving car that can shoulder this burden for us.”

Related Content

  • London’s strategy to tackle air quality problems
    October 21, 2014
    Colin Sowman talks to Matthew Pencharz, the man charged with charting London’s path between catering for traveller needs, conserving ancient buildings and conforming to modern air quality standards.
  • US regulator ‘paves the way for Google’s self-driving car’
    February 11, 2016
    A letter to Google, the US federal transport regulator, National Highway Traffic Safety Administration (NHTSA), appears to pave the way for self-driving cars, but adds the proviso that the rule-making could take some time. Google had requested clarification of a number of provisions in the Federal Motor Vehicle Safety Standards (FMVSSs) as they apply to Google’s described design for self-driving vehicles (SDVs). “If no human occupant of the vehicle can actually drive the vehicle, it is more reasonable
  • The red light camera choice: 60 killed or save US$231 million a year
    June 5, 2015
    David Crawford investigates new cost-benefit analysis of red light cameras. US states can now realistically calculate the economic benefits of using red light safety cameras, alone or in combination with other measures, to cut road traffic accident levels. The results could be of material value in making the case for the cameras as a number of state legislatures continue to debate their acceptability.
  • Need for simpler urban tolling solutions
    January 10, 2013
    A common assumption, even amongst informed observers, is that there’s but a handful of urban charging schemes in operation around the world and scant prospect of that changing any time soon. Larger city-sized schemes such as Singapore, London and Stockholm come readily to mind but if we take a wider view and also consider urban access control and Low Emission Zones (LEZs) then the picture changes rather radically. There is a notable concentration of such schemes in Europe but worldwide the number is comfort