Researchers helping autonomous vehicles learn to react to bad drivers, adverse conditions
Autonomous vehicles are very much a part of our transportation future. However, AVs reacting to unpredictable situations on the roadways is a challenge. But researchers at the University of Michigan have made progress on that front.
The engineers at the autonomous vehicle campus at MCity are using a new virtual testing environment. This simulates unexpected situations, like a car cutting you off, or a vehicle stopping in a roundabout.
Henry Liu is the director of MCity. He says now these AVs can learn from these simulated situations and adverse weather conditions that they will encounter in real life.
“In the snow situation, a vehicle might be sliding and approaching an autonomous vehicle or an autonomous vehicle might be experiencing some kind of situation, then we want to see how an autonomous vehicle will be able to handle that.”
Liu says one of the byproducts of this potentially improved safety is an increase in the public’s confidence in AVs. It will also dramatically reduce the amount of time spent on safety testing for developers and regulators.
Non-commercial, fact based reporting is made possible by your financial support. Make your donation to WEMU today to keep your community NPR station thriving.
Like 89.1 WEMU on Facebook and follow us on Twitter
Contact WEMU News at 734.487.3363 or email us at firstname.lastname@example.org