A new report has revealed that self-driving cars are involved in less crashes when compared to human driven vehicles.
The Virginia Tech Transportation Institute (VTTI) carried out the study, which was commissioned by Google.
VTTI looks at both national crash data and information from naturalistic driving studies to better estimate existing crash rates.
The results were then compared to data from Google’s Self-Driving Car programme, which included written reports, video, and vehicle kinematic information.
The report found that the national crash rate estimate is 4.2 crashes per million miles, while the crash rate for the self-driving car is 3.2 per million miles.
The uncertainty in the event rates of self-driving cars will decrease due to continuous testing and an increase in exposure, the report said.
According to the report, existing data indicates that self-driving cars may have low rates of more-severe crashes when compared to national rates, however there is currently too much uncertainty in self-driving rates to get to a conclusion with strong confidence.
Google’s self-driving car has been involved in 11 minor accidents since the inception of the project seven years ago.