Driverless vehicles can navigate faster and more safely through intersections than if humans were in charge, according to researchers from the Virginia Tech Transportation Research.
Ismail Zohdy, a Ph.D. student in civil engineering at Virginia Tech. and Hesham Rakha, director of the Center for Sustainable Mobility at the transportation institute and professor of civil engineering at the university, won the Best Scientific Paper Award for North America for their research on Optimizing Driverless Vehicles at Intersections.
"The paper develops a step-by-step procedure, or algorithm, for managing driverless vehicles through intersections," said Zohdy. "The proposed system considers the vehicles’ location, speed, and acceleration plus the surrounding environment, such as weather and intersection characteristics."
The idea is that autonomous vehicles turn themselves over to an automated intersection controller, which will allow the vehicles to move at the speed limit, with the controller tweaking their trajectory to prevent crashes.The intersection controller governs the vehicles within 200 meters of the intersection. The vehicles report their physical characteristics, such as power, mass, speed, location and acceleration and the controller works out the optimum speed and acceleration at each time step for every vehicle within the intersection zone by processing the input data through a real-time simulator/tool.
"The proposed intersection controller, which allows vehicles to keep moving, reduces the delay for each vehicle compared to traditional intersection control," said Rakha. "Keeping vehicles moving is also more fuel efficient and reduces emissions."
But safety is the primary motivation for driverless vehicles. "Somewhere in the future, you will not be driving your car anymore; you will be driven by your car," said Zohdy. "A driverless vehicle can much more accurately judge distances and velocities, and react instantly to situations that could cause an accident due to a delayed human reaction."
But Rakha pointed out that this is not the distant future. An article in the New York Times in May reported that after the successful test of the Google driverless vehicle, Nevada passed a law that could let self-driving cars on the road as soon as March 1, 2012.
Review: Safety is the main motivation for this research, but it’s driven by the need to make the best use of roads. Driverless cars have the potential to achieve that, leading to greater fuel efficiency and much reduced carbon emissions.
It’s a good, if more futuristic, example of IT as a green enabler. Even if reducing emissions isn’t the main driver, making cars more efficient road users has the knock-on effect of reducing the greenhouse gases they produce.
Intersection algorithms are likely to be more complex in Europe, though, where many cities are not built on a grid, but have grown over centuries into complex systems of roads going in all directions.