Friday 15 July 2011

Ford Use API Technology (Google) To Predict Driving Behaviour

Ford and Google are teaming up to try and predict driver behaviour and optimise performance for their EV’s and Hybrids. Using Google’s Prediction API, Ford aim to increase efficiency and decrease commuting times by tracking regular routes that drivers embark on on a daily basis.



The API technology which was released last year by Google, can convert information on a driver’s actions in the past into real-time predictions, such as where they’re likely to be headed at a particular time of day. The predictive API will be exclusively focused on the driver, logging and analysing driving history. By studying a car owner's driving patterns, the system tries to predict where the driver is going and then optimise the upcoming trip with respect to electric driving zones. Data is collected remotely by Ford and transferred to dedicated server hardware as the history logging and route analysis is quite intensive, in terms of storage and processing power.

Ryan McGee, a Ford Technical Expert said "The Google Prediction API allows us to utilise information that an individual driver creates over time and make that information actionable. Between Google Prediction and our own research, we are discovering ways to make information work for the driver and help deliver optimal vehicle performance"

Apparently the system will work as soon as the driver starts the vehicle. Making a note of what time the driver has switched on the vehicle will determine what regular routes they would normally take at this particular time of the day. When the vehicle starts, Google Prediction would use historical driving behaviour to predict the most likely destination, check with the driver that it's correct and then optimise driving performance for the journey. When drivers start using the service, an encrypted driver data usage profile could be built, based on routes and time of travel.

A plug-in hybrid vehicle could program itself to optimise energy usage over the total distance of the route, in order to preserve enough battery power to switch to all-electric mode when travelling within an EV-only zone. McGee goes on to explain that "Once the destination is confirmed, the vehicle would have instant access to a variety of real-time information so it can optimise its performance, even against factors that the driver may not be aware of". 

Ford and Google are keen to assure drivers that their privacy will be protected. "We realise that the nature of this research includes the use of personal data and location awareness, something we are committed to protecting for our customers in everything we do," says System Architect, Johannes Kristinsson. 

"A key component of this project is looking at how to develop secure personal profiles that will ensure appropriate levels of protection and specific data use only by the driver and the vehicle to deliver the best driving experience."

Watch a video that goes into more detail about this here:



No comments:

Post a Comment