With the help of Cloud computing, analytics and Google's predictive software, the car of the future can learn a driver's habits and help improve vehicle performance.

Ford researchers are testing whether a car can be made smart enough to independently change its performance to deliver optimal driving characteristics and fuel efficiency. They presented some of their findings at this week's Google I/O developers conference in San Francisco.

In the project, Google's predictive software interface is combined with more than two years of Ford's own predictve driver research and analysis. The Google API can convert inforrmation such as historical driving data into a useable real-time prediction of, for example, where a driver is headed.

“The Google Prediction API allows us to utilize information that an individual driver creates over time and make that information actionable,” said Ryan McGee, a senior Ford researcher.

Ford hopes that its data, which are stored in the Cloud, will make it possible for a car to optimize itself. In San Francisco, the Ford researchers presented ascenario in which an on-board computer would welcome a driver saying "Good morning, are you going to work?" If the answer is yes, an optimized powertrain control strategy would be created for the trip using predictive technology based on already available data.

“Once the destination is confirmed, the vehicle would have instant access to a variety of real-time information so it can optimize its performance, even against factors that the driver may not be aware of, such as an EV-only zone,” said McGee.

Such a system would need to use the Cloud because of the large amoung of computing power necessary to make the predictions, Ford said.