National crash rate for conventional vehicles higher than crash rate of self-driving cars, report shows

January 11, 2016 by Cecilia Leonard, Virginia Tech
National crash rate for conventional vehicles higher than crash rate of self-driving cars, report shows
A report commissioned by Google, based on research conducted at the Virginia Tech Transportation Institute, compares national crash rates to data from Google’s Self-Driving Car program. This photo, courtesy of Google, is a prototype vehicle being tested in Texas.

A new report, "Automated Vehicle Crash Rate Comparison Using Naturalistic Data," performed by the Virginia Tech Transportation Institute and commissioned by Google, shows that the crash rates for self-driving cars are lower than the national crash rate of conventional cars.

In this first-of-its-kind study, published today on the Virginia Tech Transportation Institute website, results show that when data is adjusted for unreported and take into account accident severity, the national for conventional vehicles is higher than the crash rate of self-driving cars.

Up until now, comparisons based on existing data have been incomplete as requirements in each state for police reported crashes differ, and the majority of severe crashes that go unreported. Meanwhile, self-driving cars are required to report every crash, regardless of severity.

The report examines national crash data and data from naturalistic driving studies that closely monitors the on-road experience of 3,300 vehicles driving more than 34 million vehicle miles, to better estimate existing crash rates, and then compares the results to data from Google's Self-Driving Car program.

Key findings include:

  • Adjusted for unreported crashes and accident severity (accidents that fall within the two highest severity levels), the national crash rate estimates of 4.2 crashes per million miles is higher than the crash rates for the Self-Driving Car operating in autonomous mode (3.2 per million miles).
  • The crash rate of conventional vehicles at all levels of severity is higher than the self-driving crash rates, according to analysis of the Second Strategic Highway Research Program (SHRP 2) Naturalistic Driving Study.
  • Current data suggest that conventional vehicles may have higher rates of more severe crashes than self-driving cars, but given the small overall number of crashes for the at these levels, there is insufficient data to draw this conclusion with strong confidence.
  • However, there is statistically-significant data that suggest less severe events may happen at significantly lower rates for self-driving cars than conventional vehicles.
  • Additionally, when the Virginia Tech Transportation Institute, using methods developed for the Second Strategic Highway Research Program Naturalistic Driving Study, analyzed the Google Self-Driving Car events, none of the vehicles operating in autonomous mode were deemed at fault.
  • As self-driving cars continue to be tested and increase their exposure, the uncertainty in their event rates will decrease. This is particularly appropriate to vehicles intended for lower-speed use where less-severe events are the most likely to be encountered by the newer generation of the Self-Driving Car fleet.

Explore further: Whose fault? Self-driving vehicles in crashes studied

More information: Automated vehicle crash rate comparison using naturalistic data.

Related Stories

Kia sees autonomous cars by 2030

January 6, 2016

South Korean automaker Kia said it envisions introducing an autonomous car using its own technology by 2030 under a new initiative dubbed "drive wise."

To avoid collisions, self-driving cars must communicate

March 12, 2015

Did you know some 33,000 people die and 2.3 million are injured in vehicle crashes in the U.S. each year?1 Researchers at Intel Labs are paving the road to a crash-free future with cars that communicate with each other.

Recommended for you

Archaeologists discover Incan tomb in Peru

February 16, 2019

Peruvian archaeologists discovered an Incan tomb in the north of the country where an elite member of the pre-Columbian empire was buried, one of the investigators announced Friday.

Where is the universe hiding its missing mass?

February 15, 2019

Astronomers have spent decades looking for something that sounds like it would be hard to miss: about a third of the "normal" matter in the Universe. New results from NASA's Chandra X-ray Observatory may have helped them ...

What rising seas mean for local economies

February 15, 2019

Impacts from climate change are not always easy to see. But for many local businesses in coastal communities across the United States, the evidence is right outside their doors—or in their parking lots.

The friendly extortioner takes it all

February 15, 2019

Cooperating with other people makes many things easier. However, competition is also a characteristic aspect of our society. In their struggle for contracts and positions, people have to be more successful than their competitors ...


Adjust slider to filter visible comments by rank

Display comments: newest first

3 / 5 (2) Jan 11, 2016
But the comparison is meaningless because there are only a handful of self-driving cars on the road, and they're all in nice places like California, driving in limited environments, where they don't have to deal with a wide variety of road, weather and traffic conditions, and when they would occasionally have to deal with something extraordinary, they simply don't go because they're still in testing and not in any serious use, so they don't have to risk it.

Meanwhile, ordinary cars with real drivers have to occasionally deal with torrential rains, or sudden snowfall and extremely slippery conditions - something at which the robot would just say "nope" and hand controls over to the human driver.

It's exactly the same bias that puts all airline accidents down to "human error" - of course it's down to human error, because the computer isn't even capable of operating in the situations that ultimately lead to the accident. The person is always the last one to touch the controls.
3 / 5 (2) Jan 11, 2016
Point in case, from another recent article of Google cars:

"After a multi-year drought, we're finally starting to get some rain in California. It's not only a welcome relief for farmers and gardeners, but an opportunity for our cars to get more time learning in cold and rainy weather."

These cars have rarely even been driven in anything but nice weather.

Comparing crash rates between what's basically "sunday driving" and everyone across the US is a huge sampling bias in favor of self-driving cars. It's just lying to yourself.
2.3 / 5 (3) Jan 11, 2016
Automated driving is going to happen. If you think otherwise, "It's just lying to yourself."
3 / 5 (2) Jan 11, 2016
something at which the robot would just say "nope"
Sounds like you think these things will never happen.

"Google says the latest version of its LiDAR sensors (light and radar) are able to detect rain, as well as clouds of exhaust on cold mornings... the company's self-driving prototypes can tell the difference between a drizzle and a downpour, and can adjust their speed and technique accordingly...

"For now, if it's particularly stormy, our cars automatically pull over and wait until conditions improve [like many humans do, or should do]... "To explore even more challenging environments, we're beginning to collect data in all sorts of rainy and snowy conditions as we work toward the goal of a self-driving car that will be able to drive come rain, hail, snow or shine!"

"To date, Google's 53 autonomous vehicles have logged 1,372,111 mi without human involvement. The company says it's currently averaging 10,000-15,000 miles driven on public streets per week"

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.