In 2003, Eric Horvitz, president of the Association for the Advancement of Artificial Intelligence, was trying to avoid traffic jams by using his satnav to negotiate the back streets of Seattle. "The result was a nightmare," reports The New York Times. "It was awful," he said. "Everything seemed to be backed up."
Since Horvitz worked at Microsoft Research, he decided to do something about it. The result is Clearflow:
an ambitious attempt to apply machine-learning techniques to the problem of traffic congestion. The system is intended to reflect the complex traffic interactions that occur as traffic backs up on freeways and spills over onto city streets.
The Clearflow system will be freely available as part of the company's Live.com site (maps.live.com) for 72 cities in the United States. Microsoft says it will give drivers alternative route information that is more accurate and attuned to current traffic patterns on both freeways and side streets.
The story ends:
"I consider this to be the moon mission of our machine-learning research," Mr. Horvitz said. "I'm still buzzing with the glow that this is actually possible."
How well it works, of course, remains to be seen....
Horvitz has a paper on Machine Learning, Reasoning, and Intelligence in Daily Life (PDF).
