NSF initiates the first remotely accessible, augmented-reality facility for autonomous transportation research
Cars that communicate to smooth out traffic or brake to avoid accidents have the potential to significantly improve sustainability, safety and mobility. Researchers continue to create many new technologies for connected and automated vehicles; however, most rely on limited open data sets for simulation and testing.
The U.S. National Science Foundation has awarded $5.0 million to the University of Michigan to enable academic researchers and students nationwide to access the world's first cloud-based, augmented-reality testbed for connected and automated vehicle (CAV) technologies. The award will expand the university's original CAV proving ground, known as Mcity, by integrating the physical test track with a software simulation environment.
"NSF invests in a broad array of fundamental research and new technologies for smart transportation, ranging from semiconductors and microelectronics to wireless communication, contactless electric vehicle charging, and artificial intelligence," said Susan Margulies, NSF assistant director for Engineering. "Testing these vehicle technologies in real-world scenarios is an essential step for transferring innovations to businesses, communities and drivers."
"Today, academic researchers developing connected and automated vehicle technologies have few opportunities to access physical test facilities or large-scale, real-world data, which hinders their progress," said Yueyue Fan, the NSF program officer overseeing the project.
"NSF's investment in Mcity 2.0 will provide easier and broader access to top-tier research infrastructure and accelerate the collaborative development of new vehicle technologies involving communication, sensing, control, human dimensions and more," said Robert Stone, division director of the NSF Division of Civil, Mechanical and Manufacturing Innovation.
The Mcity 2.0 augmented reality testbed will integrate three components: (1) a physical test facility including infrastructure and CAV fleet, (2) a mobility data center that collects and shares near-real-time traffic information from 21 intersections, and (3) an augmented naturalistic diving simulator that blends real and virtual vehicles. Researchers will be able to remotely configure and control the test facility infrastructure (traffic lights, crosswalk buttons, rail-crossing arms, etc.) and build test scenarios using a web-based graphical user interface.