By on May 3, 2011

One of the worst things about traffic is that it’s so unpredictable. You can be whizzing along one minute, and crawling with the snails the next. Even the real-time traffic information that a few companies, notably Google, now provide, can be obsolete by the time you’re on your way.But a small cadre of lucky San Franciscans will soon be finding out where the traffic will be before it happens, thanks to a joint project by the California Center for Innovative Transportation (CCIT) at the University of California, Berkeley (my alma mater) the California Department of Transportation, aka Caltrans, and IBM.

The principle behind the system is that when accidents happen, the traffic jams up in a predictable manner, “like a shock wave in a fluid,” Alexandre Bayen of CCIT tells New Scientist Magazine. By combining these patterns with real-time traffic data, the system is able to predict congestion up to 40 minutes before it even happens.

The hardware for this initiative consists of “inductive loop sensors” in the roadways. The data so-gathered is fed into IBM’s Traffic Prediction Tool. Data from users’ GPS units and smartphones on their usual routes and travel times completes the circle, enabling the system to provide alternative routes. And it’s getting more sophisticated all the time, learning to relieve congestion without creating new chokepoints, a skill requiring the ability to predict the effects of congestion-relieving redirections.

Get the latest TTAC e-Newsletter!

11 Comments on “Are You Ready To: Avoid Traffic Before It Happens?...”

  • avatar

    Interesting article. I know math modelling was used in the decision to have variable speed limits on sections of the M25 (London ringroad), especially near Heathrow airport. Reducing speeds to 50mph can decrease journey times compared to stop-start traffic jams and occasional 70mph driving.

  • avatar

    One would think that if X% of cars were using adaptive cruise control linked to this system one could perhaps modify the flow of traffic to mitigate the wave? Sort of like how noise canceling technology works?

  • avatar

    You are not IN traffic, you ARE traffic.

  • avatar

    “Even the real-time traffic information that a few companies, notably Google, now provide, can be obsolete by the time you’re on your way.”

    That’s not true. It’s not obsolete. Real-time data means you get live data as it happens as you drive. My experience with Both Google and INRIX in the Boston area is that it’s usually pretty accurate. I think prediction is available as well.

    • 0 avatar


      When I shut down for the day, the last thing I’ll do before arriving to my car is pull up GMaps on my Droid with the traffic layer enabled.

      And while it isn’t real-time, it certainly is up to the minute. Hell I had a report who was stuck behind an over-turned tractor trailer that I used Gmaps/traffic to help her get into the office.

  • avatar

    Till the system can predict an accident, it will have the same problem. It will just give you alternate routes. If I leave, and an accident happens, how quickly will its system update? Honestly, that is what is holding other real time traffic systems back right now. If it takes 10 minutes to update the system, it maybe too late in many cases.

  • avatar

    This reminds me of a spoof advertisement in a Monty Python book (back in the 70s).
    It advertised the Secret Welsh ART of SELF DEFENCE that requires NO INTELLIGENCE, STRENGTH or PHYSICAL courage.

    The main concept was to attack an assailant before it has even occurred to him to attack you.

    I just found a website for it, so it must still be practiced somewhere in the world.

  • avatar

    Apple is also working on this, as the part of the data collection everyone was so worked up about last week on the intertubes:

    The idea is if a bunch of iPhones on a given road suddenly slow down there must be a reason (like an accident) and so an alternate route can be plotted. I’m surprised OnStar, MyTouch and other such systems haven’t joined the party yet. My guess is like alot of other technologies there is no standard for how this data gets communicated and filtered thru a central system. In theory a “hive mind” concept like this would work really well. If all GPS equipped cars could report on current location and speed then traffic reports would be VERY accurate.

    Of course those with tin foil hats would freak out knowing that their car is telling some supercomputer database what speed they are going.

    • 0 avatar

      You should freak out, and for a very good reason – its guaranteed that said data would then be fed to the DMV and insurance companies and voila, real-time speeding tickets for everyone! There’d be no need for traffic cameras or radar guns.

      And you can bet the data would also be stored in central govt databases and made available (without warrants, mind you) to anyone wishing to know your whereabouts.

      Does that not concern you? The only way this could be avoided is if the data sent was completely anonymized, and you know there’s no way in hell that’s ever happening.

      I would love for this to happen, but the companies involved will never standardize since its not in their best interests to do so.

Read all comments

Recent Comments

  • thornmark: Why All Those EV-Battery ‘Breakthroughs’ You Hear About Aren’t Breaking Through In the superheated market...
  • Goatshadow: Can always count on this site for the delusional whackjobs to show up in the comments. Disappointed there...
  • Mike Beranek: The article is based on a false premise. There is no reason to believe that batteries that don’t...
  • Jeff S: Agree we will have ICE for at least a few more decades and even if manufacturers stop making ICE eventually...
  • redapple: EB> – Elect generating capy will need to grow by 60-65% by 2030. (closing coal plants 25% elec gen...

New Car Research

Get a Free Dealer Quote

Who We Are

  • Adam Tonge
  • Bozi Tatarevic
  • Corey Lewis
  • Jo Borras
  • Mark Baruth
  • Ronnie Schreiber