TrafficSignals
Latest
Scientists investigating AI-based traffic control, so we can only blame the jams on ourselves
Ever found yourself stuck at the lights convinced that whatever is controlling these things is just trying to test your patience, and that you could do a better job? Well, turns out you might -- at least partly -- be right. Researchers at the University of Southampton have just revealed that they are investigating the use of artificial intelligence-based traffic lights, with the hope that it could be used in next-generation road signals. The research uses video games and simulations to assess different traffic control systems, and apparently us humans do a pretty good job. The team at Southampton hope that they will be to emulate this human-like approach with new "machine learning" software. With cars already being tested out with WiFi, mobile connectivity and GPS on board for accident prevention, a system such as this could certainly have a lot of data to tap into. There's no indication as to when we might see a real world trial, but at least we're reminded, for once, that as a race we're not quite able to be replaced by robotic overlords entirely.
iPhone camera being used for traffic light testing
A group of researchers at MIT and Princeton University are testing to figure out how to best save fuel when stopping and re-starting cars at traffic lights, and they're using the iPhone to do so. The smartphone is mounted on the car's dashboard, and uses the camera and GPS information in a system called SignalGuru that tells the driver when it's best to slow the car down in order to save fuel (so you're not always revving up the engine and then having to put on the brakes when the next light pops up). The system works, apparently, and in Cambridge, MA testing, fuel consumption was cut down by 20 percent. The system was also tested in Singapore, where most traffic lights change the length they're displayed based on the traffic around them. In that area, as opposed to the US (where lights are generally on fixed schedules), the prediction mechanism didn't work quite as well. It was off by up to two seconds, say the researchers. It sounds like any indication can be helpful. It's hard to see if this is something that could eventually make its way to the consumer market -- more likely it would be used in commercial vehicles as a solution. But you never know -- if the system works on an iPhone and there's an in-car mount that's standardized enough to work at the right angles, your phone could be telling you when to slow down on the road, and saving you money at the same time. [via Engadget]
Thieves damage South African traffic lights, reach for the juicy SIM card innards
Johannesburg, South Africa had six hundred high-tech traffic signals, each with a cellular modem and GPS chip. The idea was, if one malfunctioned, they'd call home immediately. Well, that plan isn't working out so well, because only two hundred are still in working order -- vandals ripped apart the rest to get at their SIM cards, causing traffic jams and accidents. Apparently, the government-provided cards are a ticket to unlimited free phone calls for the thieves -- at least until the individual devices are identified and their permissions revoked. The Johannesburg Roads Agency told the Mail & Guardian that the crime looks like an inside job, because only the SIM-equipped signals seem to have been targeted so far, despite looking visually identical. The damages are piling up, with the agency figuring it will require ZAR 8.8 million (roughly $1.26 million) to repair the four hundred signals currently out of order. Needless to say, the agency is looking at ways to better secure the traffic lights. We're guessing that switching to CDMA is probably off the table. Embedded SIMs, perhaps?
