Michigan Universitys Mcity Unveils Cutting Edge Digital Twin For Autonomous Vehicle Testing

The University of Michigan’s Mcity Test Facility has taken its testing capabilities to the next level with the launch of its first open-source digital twin. This groundbreaking innovation promises to transform the way researchers develop and test autonomous vehicle software, making it faster, safer, and significantly cheaper.

Developed in collaboration with the National Science Foundation (NSF), the Mcity digital twin is a virtual representation of the physical facility that enables simulation and testing from anywhere in the world. By leveraging this cutting-edge technology, researchers can access a vast array of features, including various road materials, markings, signals, and intersections, to test their autonomous driving algorithms without having to physically visit Ann Arbor, Michigan.

“We’re thrilled to introduce our open-source digital twin, which represents a significant leap forward in mobility research,” said Greg Stevens, Mcity’s director of research. “By harnessing the power of this virtual environment, researchers can conduct mixed reality testing and development with unprecedented precision and accuracy.”

The digital twin is integrated with TeraSim, an open-source traffic simulator developed by Mcity researchers. This powerful tool introduces various road users, such as pedestrians, cyclists, and other drivers, and generates safety-critical events like potential collisions. Using calibrated real-world data, TeraSim can simulate both normal and high-risk driving scenarios, allowing researchers to test their algorithms in a highly realistic and immersive environment.

One of the key advantages of the digital twin is its ability to replicate the complexities of real-world driving conditions. By incorporating factors such as traffic behavioral models and simulated pedestrian traffic, researchers can fine-tune their algorithms to better respond to unexpected events on the road. As Darian Hogue, an Mcity software engineer who helped develop the digital twin, noted, “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.”

The launch of the Mcity digital twin marks an exciting new chapter in the development of autonomous vehicles. With its ability to accelerate testing, improve safety, and reduce costs, this innovation has the potential to bring connected and automated vehicle technologies to a wider audience more quickly.

Mcity’s journey towards remote testing began with a $5.1 million grant from the NSF in 2022, which funded the development of its digital infrastructure and enabled researchers to access the facility from anywhere in the world. The Mcity Test Facility itself was opened in 2015 and features an extensive range of physical environments, including a simulated downtown area, a straightaway, and various road surfaces.

As mobility officials continue to tout the benefits of autonomous vehicles and connected infrastructure, this latest development brings us closer to realizing the promise of safer, more efficient, and equitable transportation for all. By embracing the power of open-source technology and collaboration, Mcity is helping to shape the future of mobility research and drive progress towards a more sustainable transportation system.