Study finds self-driving cars are mostly safer than humans

Which is safer, self-driving cars or human drivers? New research analysed by a team from the University of Central Florida, US shows that self-driving cars were involved in fewer accidents than humans in most scenarios.

The team focused their study on California, where the bulk of autonomous vehicles testing is being conducted in the US.

The research team referenced 2,100 reports of accidents and used an approach called “matched case-control analysis” in which they attempted to find pairs of crashes involving humans and self-driving cars that otherwise had similar characteristics.

The team found 548 such matches, and when they compared the two groups, they found self-driving cars were safer than human drivers in most of the accident scenarios they looked at. One of the main arguments for shifting to autonomous vehicles is the prospect of taking human error out of driving. 

Self-driving cars have had blots on their records in recent years, which have led to questions about their safety. A US report recently published found that Tesla’s Autopilot system was involved in at least 13 fatal crashes but added that drivers misused the system in ways the vehicle maker should have foreseen and done more to prevent.

The researchers also discovered that autonomous vehicles were about five times more likely to be involved in an accident at dawn or dusk and nearly twice as likely when making a turn.

Autonomous vehicles were roughly half as likely to be involved in a rear-end accident and just one-fifth as likely to be involved in a broadside collision. The research also found the chance of a self-driving vehicle crashing in rain or fog was roughly a third of that for a human driver thanks to radar sensors that are largely immune to bad weather.

How much can be read into these results is a matter of debate. The authors admit there is limited data on autonomous vehicle crashes, which limits the scope of their findings. Nonetheless, the study is an important first step in quantifying the potential safety benefits of autonomous vehicle technology and has highlighted some important areas where progress is still needed.