Michigan Researchers Reveal New Way to Test Driverless Cars
Researchers at the University of Michigan have devised a new way to test driverless vehicles that bypasses the millions (or billions) of miles they would need to log for them to be ready for public roads.
This is according to new white paper published by Mcity, a public-private partnership to accelerate advanced mobility vehicles and technologies.
"Even the most advanced and largest-scale efforts to test automated vehicles today fall woefully short of what is needed to thoroughly test these robotic cars,"
said Huei Peng, director of Mcity and the Roger L. McCarthy Professor of Mechanical Engineering at the University of Michigan.
The new accelerated evaluation process breaks down difficult real-world driving situations into components that can be tested or simulated repeatedly, exposing automated vehicles to a condensed set of the most challenging driving situations. In this way, just 1,000 miles of testing can yield the equivalent of 300,000 to 100 million miles of real-world driving.
As the race to get driverless cars on the road heats up this research could prove extremely valuable in increasing the consumers confidence in these driverless vehicles.
One interesting part of this research is that it did not come from Tesla, GM, Uber or any other large company trying to get driverless cars on the road, rather it come from a public university. It will be interesting to see what other state institutions are willing to make an investment in driverless vehicles.
Image credit: University of Michigan