ANN ARBOR – Combining virtual reality and real world scenarios makes connected and automated vehicle testing faster, safer and cheaper, according to a new white paper published Monday by University of Michigan's Mcity.
Augmented reality technology can expedite testing of driverless vehicles by 1,000 to 100,000 times, drastically reducing additional testing costs.
Mcity, located on University of Michigan's north campus, is a public-private research facility that develops connected and automated vehicle technology both independently and with some of the world's largest companies.
"In order for the public to accept and widely adopt driverless vehicles, we must be able to prove they are safe and trustworthy," Henry Liu, professor or civil and environmental engineering at U-M and an author of the paper, said in a statement.
Recommended Videos
"This requires rigorous and extensive testing that would otherwise take more than a decade to accomplish. Augmented reality testing is not only more efficient, it is safer and will allow us to ensure driverless vehicles operate dependably with the ability to prevent and avoid crashes."
During testing, Liu and his team sourced virtual and video-gaming technologies to create an augmented reality environment at U-M's Mcity Test Facility, where real vehicles interact with computer-generated vehicles through connected vehicle communications in real time.
The facility features more than 16 acres of traffic infrastructure and roads. It has realistic urban and suburban streets with intersections, sidewalks, traffic signs and signals, lane configurations, simulated buildings, bike lanes and more to challenge driverless cars with real-world scenarios.
Researchers at the Michigan Traffic Laboratory at the University of Michigan Transportation Research Institute are able to create testing scenarios between vehicles from the control center.
This, Liu says, eliminates the risk for researchers.
"Our new procedure shows great potential to speed up and reduce the cost of testing," Liu said. "It also has the added benefit of allowing us to build a virtual library of computer-generated traffic scenarios that can be practiced without risk of damage or human injuries."
Now, researchers use three methods when testing fully automated vehicles:
- Closed-course testing
- Computer-generated simulations
- Operating vehicles or components on public roads
Testing within the facility is one thing, but once researchers drive out onto real roads, risks -- from legal to public safety -- arise.
According to the white paper, 26 crashes were reported by 11 suppliers while testing self-driving cars on public streets in California from 2014 to 2017.
This year, a fatality made national headlines when an Arizona woman was killed by an autonomous vehicle operated by Uber as she crossed the street with her bicycle.
"Most strategies for testing automated vehicles today fall short of what is needed to ensure the safety necessary to make driverless technology viable," Huei Peng, director of Mcity and the Roger L. McCarthy Professor of Mechanical Engineering at U-M, said in a statement. "The augmented reality environment at the Mcity Test Facility brings us a step closer by offering comprehensive, limitless testing scenarios that can be accomplished in a shorter period of time. That means testing is faster, cheaper, and safer."
Read the white paper, titled "Real World Meets Virtual World: Augmented Reality Makes Driverless Vehicle Testing Faster, Safer and Cheaper."
Like what you're reading? Sign up for our email newsletter here!
All About Ann Arbor is powered by ClickOnDetroit/WDIV.