Unsettled Topics in Automated Vehicle Data Sharing for Verification
and Validation Purposes EPR2020007
Unsettled Topics in Automated Vehicle Data Sharing for Verification and
Validation Purposes discusses the unsettled issue of sharing the
terabytes of driving data generated by Automated Vehicles (AVs) on a daily
basis. Perception engineers use these large datasets to analyze and model the
automated driving systems (ADS) that will eventually be integrated into future
“self-driving” vehicles. However, the current industry practices of collecting
data by driving on public roads to understand real-world scenarios is not
practical and will be unlikely to lead to safe deployment of this technology
anytime soon. Estimates show that it could take 400 years for a fleet of 100 AVs
to drive enough miles to prove that they are as safe as human drivers.
Yet, data-sharing can be developed – as a technology, culture, and business – and
allow for rapid generation and testing of the billions of possible scenarios
that are needed to prove practicality and safety of an ADS – resulting in lower
research and development costs to the industry.
Unsettled Topics in Automated Vehicle Data Sharing for Verification and
Validation Purposes explores how this could lead to better regulation,
insurance, public acceptance – and finally, shorter technology development
cycles. Finding a business case and changing to an open data culture are not
going to be easy tasks, but data sharing is the only way forward for the whole
industry to move to the next phase of deployment after nearly a decade of
intense research.
