Slashdot Mirror


New AI Algorithm Beats Even the World's Worst Traffic (vice.com)

"Computer scientists at Nanyang Technological University in Singapore have developed a new intelligent routing algorithm that attempts to minimize the occurrence of spontaneous traffic jams -- those sudden snarls caused by greedy merges and other isolated disruptions -- throughout a roadway network," reports Motherboard. "It's both computationally distributed and fast, requirements for any real-world traffic management system. Their work is described in the April issue of IEEE Transactions on Emerging Topics in Computational Intelligence." From the report: The Nanyang researchers' algorithm starts off by just assuming that, given enough traffic density, shit is going to happen. Someone is going to make a greedy merge -- something is going to cause enough of a traffic perturbation to result in a network breakdown. Breakdown in this context is a technical-ish term indicating that for some period of time the traffic outflow from a segment of roadway is going to be less than the traffic inflow. "We assume that the traffic breakdown model has already been given, and the probability of traffic breakdown occurrence is larger than zero (meaning that traffic breakdowns would occur), and our goal is to direct the traffic flow so that the overall traffic breakdown probability is minimized," Hongliang Guo and colleagues write. Put differently, "our objective is to maximize the probability that none of the network links encounters a traffic breakdown." So, the goal of the algorithm is this maximization, which reduces to a fairly tidy equation. It then becomes a machine learning problem. Things get pretty messy at this point, but just understand that we're taking the current traffic load, adding an unknown additional load that might enter the network at any time, and then coming up with probabilities of network breakdown at each of the network's nodes or intersections. Crunch some linear algebra and we wind up with optimal routes through the network. Crucially, Guo and co. were able to come up with some mathematical optimizations that make this kind of calculation feasible in real-time. They were able to demonstrate their algorithm in simulations and are currently working on a further analysis with BMW, which is providing a vast trove of data from its Munich car-sharing fleet. This may not be as distant a technology as it might seem. As it turns out, only 10 percent of cars in a network need to be driving according to the optimizations for those optimizations to have a positive effect on the entire network.

22 of 130 comments (clear)

  1. Says them by lucm · · Score: 2

    They were able to demonstrate their algorithm in simulations

    So they don't beat the world's worst traffic, they beat simulations. Unless someone previously mastered the art of making immensely accurate traffic simulations this is useless.

    --
    lucm, indeed.
    1. Re:Says them by lucm · · Score: 2

      Maybe instead of hiding behind insults you can explain how a simulation qualifies as "beating the world's worst traffic"?

      See, history keeps showing over and over and over and over (etc) that men are unable to make accurate simulations of complex systems. Case in point: LTCM, which had two Nobel prize winners and the former head of the biggest bond trading desk on its board. They went bust. That was in 1998, and obviously people don't learn because the same kind of shit happened 10 years later. And seeing how the idiots at the Fed are driving the economy into the ground, soon we'll probably have another documented example.

      The point here is that those traffic guys didn't beat nothing. All they did was a thought experiment that, if implemented (which will never happen) will at best cause more traffic problems. Ergo: useless.

      --
      lucm, indeed.
    2. Re:Says them by lucm · · Score: 2

      Years ago there was a fascinating study/experiment. They would put the subject in charge of maintaining the temperature of a room within a specific range, and the only action the person could do would be to press a button to cause an increase or decrease of the temperature; they could press as often as they wanted, but the change would only occur 5 minutes later. What happened? Basically everyone failed, consistently overcompensating one way or the other when they would see the temperature go up or down based on decisions made 5 minutes earlier. The more it went, the more people used the button, and they only made things worse.

      Same thing would happen with this kind of solution. Decisions take time to be implemented, and by the time the side effects are known, more decisions are already in the pipeline.

      For instance when you start sending traffic in local streets, local people react; they leave earlier or later, causing changes in the rush hour patterns. Or they fight back, getting the local authorities to convert one-ways to two-ways, or to reverse traffic flow. Thru traffic is slowed down, this causes new bottlenecks, sending more cars on other streets. Rinse and repeat. And while this happens does the computer model take the big picture into account? No, it keeps rerouting people in a progressively more frantic way until the whole area is a gridlock.

      --
      lucm, indeed.
  2. Re:Does it account for greedy homeowners? by omnichad · · Score: 4, Insightful

    publicly funded streets

    Funded and built for a certain capacity and maintenance schedule. Side streets are not built for heavy traffic flow and they require more frequent maintenance if they are used that way. It's not just a homeowner issue - it's a city planning and infrastructure issue.

  3. Re:Does it account for greedy homeowners? by gurps_npc · · Score: 4, Insightful

    The city is responsible for ALL of the traffic, including the snarls that force people off the main roads into the side roads.

    If they fail to fund the improvements for the main roads, it becomes their responsibility to pay for the increased maintance for the side roads.

    No different than if you personally refuse to pay for a sidewalk and then get upset when you have to re-seed your front lawn after people walk on it to the point of creating a path.

    In other words, yes, the greedy, short sighted city planners have to pay one way or the other.

    And they should be yelling at the home owners to stop making things worse.

    --
    excitingthingstodo.blogspot.com
  4. Re:Does it account for greedy homeowners? by Joe_Dragon · · Score: 2

    or about the kids that all most get killed by cars zipping by at 40-55 on a local street at some GPS thinks is an short cut? That is why some local streets have speed bumps.

  5. Re:Does it account for greedy homeowners? by Lumpy · · Score: 3, Informative

    Sounds like someone is pissy he cant fly through a residential area at 50mph instead of the 25mph he is supposed to go. Speed bumps around here are no problem at all if you take them at or below the posted speed limit. The only people that hate them are the self righteous greedy assholes that speed through a residential area.

    --
    Do not look at laser with remaining good eye.
  6. Just goes to show ya. by slick7 · · Score: 2

    Human stupidity will always overcome artificial intelligence.

    --
    The mind conceives, the body achieves, the spirit manifests.
  7. Re:Does it account for greedy homeowners? by Anonymous Coward · · Score: 3, Funny

    Kids make really efficient speed bumps.

  8. It doesn't matter by phantomfive · · Score: 2

    If you find a way to drive more efficiently, politicians will use it to put off road repair even longer, until the traffic jams are just as bad. For some reason roads are the things that residents get most frustrated about (and indeed, are even willing to pay extra taxes to fix, as seen in elections in California), and yet they are the thing that politicians most would like to delay fixing. I guess that goes for transportation in general.

    --
    "First they came for the slanderers and i said nothing."
  9. Re:Does it account for greedy homeowners? by JanneM · · Score: 2

    A speed bump is no obstruction if you're driving within the legal speed limit.

    Sounds like they should put up a speeding camera or radar trap in that neighbourhood of yours.

    --
    Trust the Computer. The Computer is your friend.
  10. Re:Does it account for greedy homeowners? by Pretzalzz · · Score: 2

    The main roads are usually state (or even possibly federal) highways which the state is responsible for, not the city/borough/township.

  11. Nice. Add to Waze. by _Shorty-dammit · · Score: 2

    Nice. Add to Waze. Next.

  12. will believe when .. by kamathln · · Score: 2

    .... It fixes Bangalore Traffic.

  13. Re:Does it account for greedy homeowners? by Zaelath · · Score: 2

    Wish our speed bumps were like that. Most of them have a hemispherical cross section and there's no way you can go over them at more than 10mph without complaint from passengers.

  14. Re:Does it account for greedy homeowners? by Zaelath · · Score: 2

    I mean semicircular...

  15. Re:Does it account for greedy homeowners? by Zaelath · · Score: 4, Funny

    Sorry, what? I was putting my phone away once the light turned green and forgot I was in neutral with the park brake on, so by the time I dealt with all that I barely got through the intersection myself! Phew!

  16. Re:Does it account for greedy homeowners? by Antique+Geekmeister · · Score: 2

    It is a difficulty, even at leal speeds, if you have an awkward or delicate load. I've occasionally driven quite expensive equipment through back alleys and parking lots where speed bumps risked breaking my company's, or our client's hardware..

  17. Re:Does it account for greedy homeowners? by Aighearach · · Score: 2

    Where I live we call them "traffic calmers" and they come in a bunch of varieties including speed bumps and sections of the road that have narrow winding lanes lined with noise strips and cement barricades, planters in the middle of regular-sized intersections, etc. What is replacing speed bumps are ramps where you can take it at up to 25mph in most cars, but you smash up the bottom going faster. Much better than traditional speed bumps that require a much lower speed.

    Most people like them. But another demographic that hates them are people that can barely drive.

  18. Re: Does it account for greedy homeowners? by Z00L00K · · Score: 2

    Given the right suspension the bumps are less noticeable at higher speeds.

    --
    If builders built buildings the way programmers wrote programs, then the first woodpecker would destroy civilization.
  19. Computer networks by homb · · Score: 4, Insightful

    I wonder how well this would work for computer networks. Handling flash congestions is a very big issue in networks. Those congestions propagate and bring down whole swathes of network areas, just like traffic jams.

    I've always made it a rule to keep node usage below 30% capacity to handle such congestions gracefully, but with a more optimal system we could increase that number and thus make the whole system more cost efficient.

  20. Re:Traffic Normalization by reboot246 · · Score: 4, Informative

    One of the main causes of traffic jams, at least in heavy traffic on interstates and major four-lanes, is somebody simply touching his brakes. Then the car behind him, not knowing how hard the car ahead is braking, has to hit his brakes. The reaction continues back with each car having to brake a little bit harder until traffic just a dozen cars back traffic comes to a complete stop. I've seen it hundreds of times. Your solution helps, but it really helps if nearly everybody does it.

    Just never touch your brakes without a damned good reason. Turn off the cruise control with the button, not by tapping your brake. Don't ride your brake to control your speed.

    It helps a lot if you know where you're going. I've seen traffic jams started by people who have no idea which lane they should be in and no idea where their next turn is.