More intelligence on the streets
01 June 2009
We are all thinking more carefully about our impact on the environment, and this applies to one of the biggest sources of CO2 emissions in particular – the traffic on our streets. Different approaches show how traffic flows can be improved, and all have in common the application of information and communication technologies to the benefit of the environment.
How do you understand a city?
It began with a jam. Back in 2003, Eric Horvitz found himself stuck on the freeway while looking for a new restaurant in Seattle. Thinking that he might avoid the traffic jam, he did what most people with satnav in their car would do: he instructed it to route him via side streets.
The result was a nightmare. “It was awful,” he said. “Everything seemed to be backed up.” Nothing unusual there, you might think. But Horvitz is an artificial-intelligence researcher at Microsoft, and the nightmare set him thinking. “It hit me that we had to do all the side streets,” said Horvitz, who is the current president of the Association for the Advancement of Artificial Intelligence. “We really needed to understand the whole city.” In April 2008, Horvitz's idea bore fruit as Microsoft introduced a Web based service for driving directions that helps drivers avoid traffic jams. The new technology, called Clearflow, was developed over the last five years by a group of artificial-intelligence researchers at the company's Microsoft Research laboratories. It is an ambitious attempt to apply machinelearning 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.
Traffic updates have recently become a standard feature offered by the major Web portals as well as a number of specialised services that send the information to cars or to smartphones and other portable devices. However, the new service will on occasion plan routes that might not be intuitive to a driver. For example, in some cases Clearflow will compute that a trip will be faster if a driver stays on a crowded highway, rather than taking a detour, because side streets are even more backed up by cars that have fled the original traffic jam.
Microsoft researchers began trying to do just that by building software algorithms that modelled traffic behaviour and by collecting trip data from Microsoft employees who volunteered to carry GPS units in their cars. In the end they were able to build a model for predicting traffic based on four years of data and 16,500 discrete trips covering about 100,000 kilometres. The system effectively created individual “personalities” for over 819,000 road segments in the Seattle region.
After creating the Clearflow simulation for Seattle, the Microsoft researchers were able to transfer the model by using the algorithms they had developed and then applying them to other cities. The city models are combined with live traffic data generated by networks of highway sensors to create about 60 million road segments, allowing the system to predict congestion based on time of day, weather and other variables like sporting events.
“I consider this to be the Moon mission of our machine-learning research,” Horvitz said. “I'm still buzzing with the glow that this is actually possible.” The Clearflow system is freely available as part of the maps.live.com site, initially for 72 cities in the United States. It will give drivers alternative route information that is more accurate and is attuned to current traffic patterns on both freeways and side streets.
Who is out there?
Infotainment is becoming a key element of automotive technology. This trend is fuelled by the rapidly progressing consumer electronics world which offers better information access, more mobile entertainment and new business models.
When Ford asked truck owners which new functions they wanted to organise their daily work more efficiently, the response was a wish list for added value, going beyond infotainment we have seen today. To translate this into new in-vehicle features, Ford Motor Company teamed up with leading suppliers, spearheaded by Magneti Marelli and Microsoft, to build a solution upon the extensible software platform Microsoft Auto which is at the core of FIAT Blue&Me and FORD Sync. The result is Ford Work Solutions, a set of applications that cover computing, navigation, fleet tracking and security with the overall target of increased work productivity.
With the Crew Chief solution, vehicles transmit data on vehicle location, speed, idle time, fuel usage, next required vehicle maintenance and diagnostic data to the fleet manager in real-time. The fleet manager, who can access the data with any computer on the Internet, can analyse every vehicle of his complete fleet at any time and may re-sequence or re-assign jobs on the basis of his fleet vehicle performance analysis, avoiding unnecessary detours and reducing CO2 emissions.
The eco:Drive application makes recommendations for a better driving style.
Tell me how to drive
FIAT has taken another approach addressing how to reduce CO2 emission with an innovation called eco:Drive. eco:Drive is an easy-to-use computer application that will help people to drive more efficiently. It analyses individuals' driving style and thus helps each driver to use less fuel, reducing CO2 emissions and saving money, up to 15 per cent if used effectively. Users just download the application from the FIAT website onto their computer. Then they plug in any USB stick into the Blue&Me port of their FIAT car. Blue&Me is the in-car entertainment system that is built upon Microsoft Auto platform. Information on how a user drives will be saved automatically. Then the stick is plugged back into the user's computer. The information uploads into the eco:Drive application. Technology then gets to work, converting the data into useful facts and figures.
It is completely anonymous, so nobody else sees each other's details. Eco:Drive analyses the user's driving technique and it shows how efficiently one has driven, based on acceleration, deceleration, gear changes and speed. Clever step-by-step tutorials then help improve the driving style, with information from the user's own journeys.
Users can monitor their total CO2 emissions and the money they have saved. They are also part of an online community, called Ecoville, that is populated by all the FIAT eco:Drive members around the world. As more drivers join, the community grows and so the savings we all achieve together.
Hopefully Ecoville will encourage drivers to be more sensitive. Each driver is making just a few small changes, but together they will create a world of difference.