IN THE near future, you may have to share the road with a robot. Or perhaps we should say that a robot will have to share the road with you.
At the University of California, Berkeley, engineers are preparing autonomous cars to predict what we impulsive, unreliable humans might do next. A team led by Katherine Driggs-Campbell has developed an algorithm that can guess with up to 92 per cent accuracy whether a human driver will make a lane change. She is due to present the work next month at the Intelligent Transportation Systems conference in Las Palmas de Gran Canaria, Spain.
Enthusiasts are excited that self-driving vehicles could lead to fewer crashes and less traffic. But people aren’t accustomed to driving alongside machines, says Driggs-Campbell. When we drive, we watch for little signs from other cars to indicate whether they might turn or change lanes or slow down. A robot might not have any of the same tics, and that could throw us off.
“A robot might not have any of the same driving tics as us, and that could throw us off”
“There’s going to be a transition phase,” she says. “How do you ensure the autonomous vehicle is clearly communicating with the humans, and how do you know the human is understanding what they’re doing?”
Past algorithms have tried to predict what a human driver will do next by keeping tabs on body movements. If someone seems to be looking over their shoulder a lot, say, that might be a sign that they’re thinking of moving lane.
Driggs-Campbell and her colleagues wanted to see if they could forecast a driver’s actions by monitoring only outside the car.
To see how human drivers do this, they asked volunteers to drive in a simulator. Each time the driver decided to make a lane change, they pushed a button on the steering wheel before doing so. The researchers could then analyse data from the simulator for patterns at the time of lane changes: Where were all of the cars on the road? How fast was each one going, and had it recently moved or slowed down? Was there sufficient room next to the drivers’ car?
They used some of the data to train the algorithm, then put the computer behind the wheel in re-runs of the simulations. The algorithm could predict accurately when the driver would attempt a lane change.
Such algorithms would help a self-driving car make smarter decisions in the moment. They could also be used to teach the cars to mimic human driving tics, says Driggs-Campbell.
It’s good work, but teaching a car to understand others is only the beginning, says Raúl Rojas at the Free University of Berlin in Germany. “Humans are very creative about breaking the rules,” Rojas says. “Computers are programmed to never break the rules.”
DOT grant to get cars to talk to one another
Stepping off a curb in Manhattan can be a frightening experience: buzzing cabs, fast buses, hoards of tourists. But the Department of Transportation and New York City are investing in technology that might make it a slightly less terrifying one.
Today, Secretary of Transportation Anthony Foxx announced a new pilot program that will give up to $42 million to the city, along with Tampa and the state of Wyoming, to invest in technology that lets vehicles talk to one another and to their surroundings in order to reduce congestion, prevent accidents, and cut emissions. The hope is that such technology might help slash the unimpaired vehicle crash rate by as much as 80 percent.
The "vehicle to vehicle" and "vehicle to infrastructure" technology in question could be a dramatic step forward for safety on the roads. So-called "connected vehicles" talk to one another, as well as to signs, lights, and data-collection points, often over dedicated wireless channels via special hardware.
That means that a truck, for instance, could convey its direction and speed to the road, helping cities with things like stoplight timing to alleviate congestion. It could also convey its direction and speed to a pedestrian or bicyclist with a smartphone app, warning him of the potential collision. And drivers could get alerts when they exceeded the speed limit, or warnings about avoiding traffic jams.
Signing up for the pilot might help aid in Mayor Bill de Blasio’s plan to eliminate traffic deaths in the city. Last year there were 248 traffic fatalities in New York, including 132 pedestrians, 20 bicyclists, 37 motorcyclists, and 59 people in motor vehicles. De Blasio’s administration is treating all such deaths as preventable, pushing initiatives to lower speed limits and increase enforcement.
The new technology might also help improve safety. “You’ll probably experience fewer fender benders,” Foxx told me, describing what the technology’s real-world effects might be in midtown. “You’d probably have fewer collisions with pedestrians. You’d also notice more coordinated signalization,” he said, helping to “ease traffic flows in a very congested part of America.”
New York City will use the money to install “vehicle to vehicle” tech in 10,000 cars, buses, taxis, and limousines that often travel in midtown. It chose particularly dangerous and congested parts of the road for “vehicle to infrastructure” technology, using traffic and fatality data from 2009 to 2014. It expects that all of the traffic signals on First, Second, Fifth, and Sixth avenues between 14th and 66th streets will get an upgrade, as will traffic signals on Flatbush Avenue between Grand Army Plaza and Tillary Street in Brooklyn. There will also be roadside units installed on FDR Drive between 50th and 90th streets.
Foxx said that the government and private firms have spent more than a billion dollars developing this kind of technology, and that an early connected-vehicle pilot in Michigan had shown great promise in making the roads safer. “We’re trying to draw in local communities and private businesses that could benefit,” he said, “and to engage them in early adoption.” The department plans to issue rules requiring "vehicle to vehicle" tech in cars soon.
Such connected-vehicles programs also might help cities get more bang for their buck from their existing infrastructure, saving money in the long run, he said. “We’re going to have 70 million more people in this country over the next 30 years,” he said, “so getting as much capacity of the road network is the goal. And the safety benefits aren’t to be understated.”
Many a New York pedestrian has her fingers crossed that he is right.