While automakers and suppliers with big marketing budgets tout their self-driving escapades (Audi, Delphi, Daimler, Tesla) in the Silicon Valey and beyond, the University of Michigan (U-M) is testing self-driving cars in the real-life situations with the support of DSRC (Dedicated Short Range Communications) infrastructure in a simulated city “Mcity” at the Mobility Transformation Center.
The university’s 32-acre life-like test area is now operational and supported by major automakers, suppliers and affiliated companies. The sponsors plan to share their resources, knowledge and engineering to develop new self-driving technology at the “one-of-a-kind” test facility that will have a formal opening in July.
While other self-driving testers adapt cars by added sensors and cameras, the U-M adds the additional communication of V2V (vehicle-to-vehicle) and V2I (vehicle-to-infrasctructure). Therefore, the vehicle doesn’t have to wait to see if the traffic is changing, it knows exactly when the traffic light is changing.
Mcity includes approximately five lane-miles of roads with intersections, traffic signs and signals, sidewalks, benches, simulated buildings, street lights, and obstacles such as construction barriers.
The MTC is also developing on-roadway deployments of more than 20,000 cars, trucks and buses across southeastern Michigan to to evaluate consumer driving behavior and other experiments.
U-M is working to cover all of Ann Arbor with DSRC and 9,000 vehicles. DSRC transponders are being placed on major highways, traffic lights and street lights.
The program is funded by Leadership Circle partners (Bosch, Econolite, Ford, General Motors, Toyota, Denso, Honda, Nissan, Bosch, Verizon, State Farm, Xerox , Qualcomm and Iteris) and Affiliate members.
Meanwhile, researchers are exploring new ways for self-driving cars to work. Lidar scanners are very expensive, as much as $10,000. Ryan Wolcott, a doctoral candidate in computer science and engineering, is using video game technology to reduce the need for scanners. The technology enables them to navigate using a single video camera, delivering the same level of accuracy as laser scanners at a fraction of the cost. His paper detailing the system recently was named best student paper at the Conference on Intelligent Robots and Systems in Chicago.
Wolcott’s software system converts the map data into a three-dimensional picture much like a video game. The car’s navigation system then compares these synthetic pictures with the real-world pictures streaming in from a conventional video camera.
The team has successfully tested the system on the streets of downtown Ann Arbor. While they kept the car under manual control for safety, the navigation system successfully provided accurate location information. Further testing will be completed on U-M’s new Mobility Transformation Facility test track this summer.