Posted on 10/12/2023 2:41:49 PM PDT by libh8er
It's been two years since Google first debuted Project Green Light, a novel means of addressing the street-level pollution caused by vehicles idling at stop lights. At its Sustainability ‘23 event on Tuesday, the company discussed some of the early findings from that program and announced another wave of expansions for it.
Green Light uses machine learning systems to comb through Maps data to calculate the amount of traffic congestion present at a given light, as well as the average wait times of vehicles stopped there. That information is then used to train AI models that can autonomously optimize the traffic timing at that intersection, reducing idle times as well as the amount of braking and accelerating vehicles have to do there. It's all part of Google's goal to help its partners collectively reduce their carbon emissions by a gigaton by 2030.
When the program was first announced in 2021, it had only been pilot tested in four intersections in Israel in partnership with the Israel National Roads Company but Google had reportedly observed a "10 to 20 percent reduction in fuel and intersection delay time" during those tests. The pilot program has grown since then, spreading to a dozen partner cities around the world, including Rio de Janeiro, Brazil; Manchester, England and Jakarta, Indonesia.
“Today we're happy to share that… we plan to scale to more cities in 2024,” Yael Maguire, Google VP of Geo Sustainability, told reporters during a pre-brief event last week. “Early numbers indicate a potential for us to see a 30 percent reduction in stops. We believe green light is unique because it is more scalable and cost effective for cities than alternative options.” Ideally, cities would deploy the models across grids of neighborhood blocks to create “waves” of propagating green lights.
“Our AI recommendations work with existing infrastructure and traffic systems,” Maguire continued. “City engineers are able to monitor the impact and see results within weeks.” Maguire also noted that the Manchester test reportedly saw improvements to emission levels and air quality rise by as much as 18 percent. The company also touted the efficacy of its Maps routing in reducing emissions, with Maguire pointing out at it had "helped prevent more than 2.4 million metric tons of carbon emissions — the equivalent of taking about 500,000 fuel-based cars off the road for an entire year."
AI will probably very useful in optimizing traffic. Saving 2 minutes per person, multiplied by a million is 33,000 hours for a city of lost productivity.
With the number of badly timed traffic lights, I welcome this. DOT’s only want to expand their reach and add lights at every turn.
An excellent project for AI.
Or AI decides all those stop lights need to go green at the same time…ouch
It could be more effective if it had Cameras and could see the traffic volumes (and your license plates of course)
One of the more frequent term projects at my local university is an optimization study of traffic lights. Students collect and analyze data and propose optimizations to the local city council which refuses to act on the data due to opposition from businesses. These businesses do not want smooth and efficient traffic flow. They want to slow traffic down so they will get more customers.
This project highlights the fact that AI is nothing more than pattern matching.
My dad explained this to me in the 1950s during one of our family’s summer road trips.
Not to make your commute easier. Not to reduce frustration and road rage. Not to save you money. Not to reduce urban hydrocarbon pollution.
Nope. To save a billion tons of carbon. That's the ticket, baby. Nothing else matters.
Why do you think it doesn’t have cameras and license plate readers? Remember the at that time fiction TV show “Person of Interest” from a couple of years ago? If Hollywood writers can think of it I suspect Google engineers have thought of it too.
“It could be more effective if it had Cameras and could see the traffic volume”
With the ubiquity of cameras on traffic lights, I’d be very surprised if it DOES NOT have that data. Plus the data from the vehicle sensor coils embedded in the pavement at every intersection.
So I doubt any "data" Big Evil Google says.
All they have to do is get rid of the stupid medians everywhere and put back in the suicide lanes. I hate having to drive a block to do a U-turn and come back. Also hate paying for all that concrete work, and water for the plants and the maintenance cost which they never seem to do.
Not so much on freeways the 405 here in CA from 7:00am to 10:00 am and from 3:00pm to 7:00pm one can reach speeds up to 15 MPH.
Will never fly in the US. Eco nazis run the show and this contradicts their goal of making driving as painful as possible because everyone’s supposed to be on a bike or walking.
Ever since Hurricane Ian the lights have never been right, it's like the only smart guy in the room retired a decade ago in that department.
In this day and age they could cameras at stop lights and along with some programing to prevent lights from forcing people to sit idle at and intersection for no reason. They can’t even produce that.
Google’s AI will of course have access to facial recognition software and automotive registry information so that soon we’ll be just like China - they can track individuals throughout the day 24/7.
back in the sixties the highway department completed I35 in Oklahoma. Prior to this completion, there was a ~45 mile gap with a two lane highway spanning the gap. There were three/four small towns, pop. 3000 spaced along the gap. When the plans for the Interstate were published, the mayors of those small towns protested. No longer would the traffic be routed down the mainstreets of these small towns because the interstate went around the towns.
The mayors petitioned the state to stop the interstate at their city limits with the traffic continuing through town on the mainstreets and then pick up the interstate outside their towns. One of the mayors was quoted as saying they were sure the people on the interstate would miss the opportunity to see their towns.
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.