Skip to main content

An analysis of real-world crashes involving self-driving vehicles

A study by the University of Michigan performed a preliminary analysis of the cumulative on-road safety record of self-driving vehicles for three of the ten companies that are currently approved for such vehicle testing in California (Google, Delphi, and Audi). The analysis compared the safety record of these vehicles with the safety record of all conventional vehicles in the US for 2013 (adjusted for underreporting of crashes that do not involve a fatality).
October 30, 2015 Read time: 2 mins
A study by the University of Michigan performed a preliminary analysis of the cumulative on-road safety record of self-driving vehicles for three of the ten companies that are currently approved for such vehicle testing in California (1691 Google, 7207 Delphi, and 2125 Audi).

The analysis compared the safety record of these vehicles with the safety record of all conventional vehicles in the US for 2013 (adjusted for underreporting of crashes that do not involve a fatality).

Taking into account the fact that the distance accumulated by self-driving vehicles is still relatively low compared with conventional vehicles and that the vehicles were driven only in limited conditions, the study came up with some interesting results.

These, including the facts that self-driving vehicles may have a higher crash rate per million miles travelled than conventional vehicles, and self-driving vehicles were not at fault in any crashes they were involved in, are available in the report abstract on the university’s website. (link %$Linker: 2 External <?xml version="1.0" encoding="utf-16"?><dictionary /> 0 0 0 oLinkExternal http://www.umich.edu/~umtriswt/PDF/UMTRI-2015-34_Abstract_English.pdf Visit Umich false http://www.umich.edu/~umtriswt/PDF/UMTRI-2015-34_Abstract_English.pdf false false%>).

Related Content

  • November 27, 2015
    Call for papers for ITS Glasgow and ITS Melbourne
    Ertico-ITS Europe has issued a call for papers for the 11th European ITS Congress 2016 to be held in Glasgow on 6-9 June 2016 and the 23rd ITS World Congress, to be held in Melbourne on 10-14 October 2016. Deadline for submissions for ITS Europe is 13 January 2016. More information is available on the website. (link http://glasgow2016.itsineurope.com/) Deadline for submission for the ITS World Congress is 13 January 2016. More information is on the ITS World Congress website. (link http://www.itsworld
  • November 25, 2014
    ATRI seeks input on truck platooning
    Working in collaboration with two FHWA-sponsored project teams, the American Transportation Research Institute (ATRI) is conducting research to explore trucking industry perspectives on the use of automated truck platooning, also known as Driver Assistive Truck Platooning. This concept is based on a system that controls inter-vehicle spacing based on information from forward-looking radars and direct vehicle-to-vehicle communications. Braking and other operational data is constantly exchanged between th
  • December 11, 2017
    Call for Contributions still open, ITS World Congress 2018
    The Call for Contributions are still open for the ITS World Congress 2018, in Copenhagen. Through ITS, it aims to find answers to climate, air pollution, urbanization, congestion, and traffic safety through its main theme Quality of Life. The deadline for the submission of papers is 15 December 2017. Next year’s event is expected to attract over 10,000 visitors, 4,000 delegates and 400 exhibitors and will be held in the Bella Center from 12-21 September 2018. More information in the Call for Contribution
  • December 7, 2012
    ITS America free webinar series: Connected vehicles and the environment
    The third webinar of the AERIS autumn/winter 2012-2013 webinar series will take place on Wednesday, 12 December 2012 at 1:00 pm EST. The webinar will provide an overview of the draft concept of operations for the dynamic low emissions zones transformative concept. As part of the AERIS program's efforts to develop ways in which real-time transportation system data could improve the operation of the surface transportation network, six transformative concepts, or bundles of applications, were identified. Each