Google, along with other like-minded companies, are working to develop vehicles capable of autmomous navigation.
While Mountain View may not believe such vehicles will (ultimately) require major infrastructure upgrades, others see the future of autonomous travel as being tightly integrated with smart roads and intersections.
For example, Peter Stone – a computer scientist at the University of Texas at Austin – is working to model intersections of the future, which, if eventually implemented, could negate the need for conventional stop lights and stop signs.
Personally, I believe we’ll eventually see a hybrid mix of autonomous and normal vehicles on highways around the nation. Meaning, human drivers would still need traffic signs to be able to meld into autonomous traffic.
“A future where sitting in the backseat of the car reading our newspaper while it drives us effortlessly through city streets and intersections is not that far away,” says Stone.
Stone and his research team are working to create an autonomous car dubbed “Marvin,” which already successfully competed in DARPA’s Urban Challenge competition.
According to Stone, future vehicles based on Marvin’s autonomous architecture would call in to reserve a space and time at intersection. An autonomous arbiter agent known as the “intersection manager” would subsequently approve the request, as vehicles move through the intersection with little stopped traffic.
“Computers can already fly a passenger jet much like a trained human pilot, but people still face the dangerous task of driving automobiles… Vehicles are being developed that will be able to handle most of the driving tasks themselves. But once autonomous vehicles become popular, we need to coordinate those vehicles on the streets,” he added.
