>During “treatment” days, the modified routing guided all trips that encountered the pre-selected congested segments toward alternative routes with similar travel times.
Why would they specifically need to route people away from congested segments? Presumably if a segment gets congested enough, it'd be considered slower and therefore won't get picked in the first place?
Traffic apps only know about congestion if someone running the app goes down the congested road. Because of this, I've always suspected that the apps, from time to time, will route someone down a route they haven't gathered data on in a while, just to collect the data, and even if the route is likely to be suboptimal.
One of the things this type of intervention doesn't take into account is that different roads are built with different levels of hardiness based on the amount of traffic they are expected to receive.
For instance, a few years ago, a segment of I-495 in Delaware needed to be unexpectedly shut down for emergency repairs. Drivers were rerouted. But because of the increase in traffic on the less-hardy detour route, that route needed repairs and repaving soon afterward, much more quickly than it would have ordinarily required.
So yes, drivers can be better dispersed to ease congestion, but we also need to consider the secondary effects to the roadways themselves.
Also, pedestrians and cyclists choose lesser traveled roads for safety. Granted you're talking huge roads but on a smaller scale, filling up neighborhood streets with commuter traffic is likely to provoke a backlash.
For over a decade, I imagined that if I ever landed a job at Google, this would be my most significant project. It made me chuckle a bit when I read the announcement, they finally built it! confirming that my thoughts weren’t entirely delusional XD
(I'm not saying I'm the first or only person to think of it, but I did patent it, as well as the extra claim of compensating those people sent on the slower route).
The way to maximise traffic congestion would be to remove trucks off the road during peak times, banning trucks from the fast lane at all times, making it the social norm to toot someone in the fast lane so they move over.
If we could copy the traffic laws of a country like Germany to the US, I think that would have the biggest + cheapest effect. I am OK with automated/elevated enforcement if it means stop & go traffic evaporates into free flowing conditions.
We should also take the idea from Finland where the traffic fines scale with each person's ability to pay. $100 for camping the passing lane or failing to maintain a reasonable following distance is not a big consequence for a lot of people. $100k covers the edges a lot better.
Just make sure not to fire half of your police forces. Finland has about 130 police officers per 100k people, America has 242 according to Wikipedia. Due to extreme lack of police resources, the enforcement of traffic laws is not good here. Mostly last century tech, like automatic traffic cameras in few fixed locations.
When Google Maps routes me using a smaller secondary road instead of the main road that I would otherwise have used , I've always wondered whether that significantly changes the amount of traffic that smaller road sees. It's funny to consider that arbitrary black-box changes to the routing algorithm can have a noticeable effect to people that live there.
> For this study, the Google Maps algorithm was modified to prefer alternative routes with similar travel times and segment types, effectively guiding trips away from the pre-selected congested segments
> Over a six month period, we adopted a city-wide switchback (also known as crossover) experimental design, alternating between this treatment and the control (unaltered) routing algorithm over consecutive days to appropriately measure the effect of this intervention
> Averaged across cities, we observe a median increase of around 2% in driving speeds on targeted segments, corresponding to a median decrease of 0.5% to 1.0% in fuel consumption rates
The cities were: Atlanta, Boston, Chicago, Los Angeles, Miami, New York, Philadelphia, Salt Lake City, San Francisco, Seattle.
Why cant we have smart stop lights. Nothing more annoying than sitting on a street with nobody coming and a red light for some arbitrary time period that's totally incorrect for the time period I'm currently in
Congestion can be solved by charging more for driving. Even a modest amount would start affecting how much people drive. The money could be used for better roads and improving other transit options that aren't so space-inefficient. That said, this would likely be unpopular to implement until the effects were visible. See congestion pricing in NYC as an example.
I think the bigger thing this making public transport a real alternative to driving - I most American metros using public transport isn’t faster, can be inconvenient (no parking, multiple transfers, etc), comfortable safe.
I guess I’m saying yes you can make driving less attractive, but I think the better answer is to make public transport more attractive.
Well, duh. Grid design that allows traffic to diffuse is a secret superpower of American cities. Along with stroads that seamlessly blend local and arterial traffic.
One of unforgivable mistakes of Project Zero Vision is sabotage of stroads. If forced more traffic onto local streets, resulting in MORE pedestrian deaths.
Happy that research time is being put towards this, however a fuel use decrease of ~0.75% is a bit underwhelming for this particular endeavor, even when consumer cars/vans are 10% of CO2 emissions.
The same things keeps happening every time I find myself stuck in traffic on the interstate. Out of nowhere, a popup appears in Google Maps: a faster route is available! 4 minutes faster! Unless either the passenger or the driver are fast enough to hit "No thanks", the change auto-applies, and Google now wants me to exit the interstate at the nearest exit and drive some random road I had no idea about, to rejoin the interstate a few miles ahead. Of course, a bunch of other vehicles in the same traffic jam got the same
notification, so that minor road now get a sizable fraction of the interstate traffic, all of which then struggles to merge back.
Seeing this again and again. We call it a "Google detour" in the family, and rarely agree to the change of the route.
If the original route was to continue on the current road, and the revised one is to come off, then you don't need to interact with the screen at all to reject it. Just continue driving, and the route will reset once you pass the exit.
It once made me exit the highway, using the nearly empty exit ramp, then do a U-turn on the surface street and get back using the lightly used entrance ramp. Wow, all that effort to move about 250m forward in traffic, saving me perhaps 30 seconds of time on my 3 hour drive. Very "over-optimized" software does bizarre stuff that no sane person would ever do.
Surely the top way to avoid traffic congestion would be communities where it's possible to live near where you work, shop, go out, etc. and not doing everything else exactly the same but taking a slightly different highway in your car
I've noticed that Google Maps has started sucking a lot lately, routing us onto routes that take 2-4 minutes longer when a faster route is clearly available or taking us on nonsensical detours, and I wonder if this experiment is a reason why.
There's a hidden cost to this, and that's trust in the mapping app. I've stopped using Google Navigation for routine trips where I know how to get to the destination. It used to be worth it for the traffic information, but now that there's a good chance that it'll take you on a slower route for reasons that may be beneficial to Google but detrimental to you, it's not worth it. My brother-in-law switched to Apple Maps for similar reasons: he's finding it simply gives better results nowadays.
Same. Though it's been happening for maybe a year? Or, at least since I learned where things actually are. I just can't trust the Google maps anymore! Many times I lost 10+ min because it took me through weird alley and then back to the main.
One way is to stop the war on cars. I see many cities basically making driving purposely bad. Super low speed limits, speed bumps, unnecessary bike lanes, poorly timed traffic lights, no right turn on red, etc. It’s all the typical pro bike anti car stuff but it hurts traffic. They never measure travel times in a transparent way as they make these destructive changes.
67 comments
[ 2.7 ms ] story [ 69.0 ms ] threadWhy would they specifically need to route people away from congested segments? Presumably if a segment gets congested enough, it'd be considered slower and therefore won't get picked in the first place?
For instance, a few years ago, a segment of I-495 in Delaware needed to be unexpectedly shut down for emergency repairs. Drivers were rerouted. But because of the increase in traffic on the less-hardy detour route, that route needed repairs and repaving soon afterward, much more quickly than it would have ordinarily required.
So yes, drivers can be better dispersed to ease congestion, but we also need to consider the secondary effects to the roadways themselves.
https://patents.google.com/patent/US20170184409A1
(I'm not saying I'm the first or only person to think of it, but I did patent it, as well as the extra claim of compensating those people sent on the slower route).
We should also take the idea from Finland where the traffic fines scale with each person's ability to pay. $100 for camping the passing lane or failing to maintain a reasonable following distance is not a big consequence for a lot of people. $100k covers the edges a lot better.
https://www.theguardian.com/world/2023/jun/06/finnish-busine...
> Over a six month period, we adopted a city-wide switchback (also known as crossover) experimental design, alternating between this treatment and the control (unaltered) routing algorithm over consecutive days to appropriately measure the effect of this intervention
> Averaged across cities, we observe a median increase of around 2% in driving speeds on targeted segments, corresponding to a median decrease of 0.5% to 1.0% in fuel consumption rates
The cities were: Atlanta, Boston, Chicago, Los Angeles, Miami, New York, Philadelphia, Salt Lake City, San Francisco, Seattle.
The data and code is also available (https://github.com/google-research/google-research/blob/mast...) from the paper (https://www.nature.com/articles/s44284-026-00443-x).
Kudos Google! Nice to see this kind of work. That said, let's just build more trains?
I guess I’m saying yes you can make driving less attractive, but I think the better answer is to make public transport more attractive.
Perhaps some sort of carpooling profile? That would be a dramatically bigger improvement than, say, routing users through residential neighborhoods.
One of unforgivable mistakes of Project Zero Vision is sabotage of stroads. If forced more traffic onto local streets, resulting in MORE pedestrian deaths.
Seeing this again and again. We call it a "Google detour" in the family, and rarely agree to the change of the route.
Reminder: you are not in traffic, you are traffic. :)
Until you support a feature that simple and obvious, I don't have a lot of interest in your input on this subject.
There's a hidden cost to this, and that's trust in the mapping app. I've stopped using Google Navigation for routine trips where I know how to get to the destination. It used to be worth it for the traffic information, but now that there's a good chance that it'll take you on a slower route for reasons that may be beneficial to Google but detrimental to you, it's not worth it. My brother-in-law switched to Apple Maps for similar reasons: he's finding it simply gives better results nowadays.