Town built for driverless cars to ease driving experience

A  mocked-up set of busy streets in Ann Arbor, Michigan, will provide the sternest test yet for self-driving cars. Complex intersections, confusing lane markings, and busy construction crews will be used to gauge the aptitude of the latest automotive sensors and driving algorithms; mechanical pedestrians will even leap into the road from between parked cars so researchers can see if they trip up onboard safety systems.

The urban setting will be used to create situations that automated driving systems have struggled with, such as subtle driver-pedestrian interactions, uneven road surfaces, tree canopies, which can confuse sensors and obscure GPS signals.

“If you go out on the public streets, you come up against rare events that are very challenging for sensors,” says Peter Sweatman, Director of the University of Michigan’s Mobility Transformation Center, which is overseeing the project. “Having identified challenging scenarios, we need to re-create them in a highly repeatable way.”
Google and others have been driving automated cars around public roads for several years, albeit with a human ready to take the wheel if necessary. Most automated vehicles use accurate digital maps and satellite positioning, together with a suite of different sensors, to navigate.

Highway driving, which is less complex than city driving, has proved easy enough for self-driving cars, but busy downtown streets – where cars and pedestrians jockey for space and behave in confusing and surprising ways – are more problematic.

“I think it’s a great idea,” says John Leonard, a professor at MIT who led the development of a self-driving vehicle for a challenge run by DARPA in 2010. “It is important for us to try to collect statistically meaningful data about the performance of self-driving cars. Repeated operations can yield valuable data sets for testing and evaluating new algorithms.”

The simulation is being built on the edge of the University of Michigan’s campus with funding from the Michigan Department of Transportation and 13 companies involved with developing automated driving technology. It is scheduled to open next spring. It will consist of four miles of roads with 13 different intersections.

Speaking at an event in California this July, Chris Urmson, who leads the company’s self-driving car project, said several common urban situations remain thorny.

Such challenges notwithstanding, the first automated cars will go into production shortly. General Motors announced last month that a 2017 Cadillac will be the first car to offer entirely automated driving on highways. But it’s not yet clear how the system will work.
Another technology to be tested in the simulated town is vehicle-to-vehicle communications. The University of Michigan recently concluded a government-funded study in Ann Arbor involving thousands of vehicles equipped with transmitters that broadcast position, direction of travel, speed, and other information to other vehicles and to city infrastructure.

“One of the interesting things, from our point of view, is what extra value you get by combining” automation and car-to-car communications, Sweatman says. “What happens when you put the two together – how much faster can you deploy it?”