The University of Michigan’s Mcity Test Facility, a hub for testing connected and autonomous vehicle technologies, now offers an open-source digital twin. This virtual model is available globally, providing researchers with a cost-effective, safe tool for simulating and testing autonomous driving technologies. Developed with the National Science Foundation’s support, the Mcity digital twin is the pioneering open-source tool for mobility systems testing, offering a new avenue for researchers worldwide.
A digital twin is a virtual counterpart of a physical space that exchanges data with the real environment, allowing for enhanced simulation and testing. Mcity’s digital twin replicates road materials, markings, signals, and intersections, enabling autonomous algorithm testing without visiting Ann Arbor.
“This takes our almost 10-year-old track and puts the digital replica directly over it,” said Greg Stevens, Mcity’s director of research. “That’s a living, breathing manifestation of that physical track where people can do mixed reality testing and development.”
Utilizing TeraSim, a traffic simulator by Mcity researchers, the digital twin introduces varied road users and simulates critical events like potential collisions. This tool leverages real-world data to recreate both everyday and riskier driving scenarios.
Autonomous and connected vehicles promise safer, efficient, and equitable transport, but more research is needed for widespread usage. Virtual testing offers a safe, efficient way to advance these technologies before real-world deployment.
“You can drive millions of miles in your AV in a digital twin built off of a real-world environment before your AV actually touches the real world,” said Darian Hogue, an Mcity software engineer who helped develop the digital twin. “With this, we can control all kinds of factors. That includes controlling and manipulating simulated pedestrian traffic — a factor that is random in the real world. This focuses and accelerates simulated testing.”
Since its 2015 opening, the Mcity Test Facility has been a key site for connected and automated vehicle testing. It features urban streets, a straightaway, varied road surfaces, traffic signals, and more. Continuous enhancements aim to broaden access for researchers.
In 2022, a $5.1 million NSF grant supported Mcity’s digital infrastructure development, facilitating remote access, dubbed Mcity 2.0. This funded the creation of the digital twin, launching remote capabilities in October. Through cloud-based infrastructure and 5G, researchers can test their algorithms remotely, maintaining proprietary data security.
“What differentiates the Mcity digital twin is that it supports virtual testing, while remote use involves testing a physical vehicle at our physical test track from a remote location,” said Mcity Director Henry Liu, the Bruce D. Greenshields Collegiate Professor, professor of civil and environmental engineering and of mechanical engineering, and research professor in engineering systems at the College of Engineering.
“As an open-source tool, the Mcity digital twin lowers barriers to use of the test facility by technology developers and researchers. The digital twin could also help developers better prepare for on-site testing at Mcity.”
—
Read More Michigan News
