Waymo Is Using Its Self-Driving Taxis To Create Real-Time Weather Maps (engadget.com) 15
Waymo's latest car sensor arrays are "creating real-time weather maps to improve ride hailing services in Phoenix and San Francisco," reports Engadget. "The vehicles measure the raindrops on windows to detect the intensity of conditions like fog or rain." From the report: The technology gives Waymo a much finer-grained view of conditions than it gets from airport weather stations, radar and satellites. It can track the coastal fog as it rolls inland, or drizzle that radar would normally miss. While that's not as important in a dry locale like Phoenix, it can be vital in San Francisco and other cities where the weather can vary wildly between neighborhoods. There are a number of practical advantages to gathering this data, as you might guess. Waymo is using the info to improve its Driver AI's ability to handle rough weather, including more realistic simulations. The company also believes it can better understand the limits of its cars and set higher requirements for new self-driving systems. The tech also helps Waymo One better serve ride hailing passengers at a given time and place, and gives Waymo Via trucking customers more accurate delivery updates.
The current weather maps have their limitations. They may help in a warm city like San Francisco, where condensation and puddles are usually the greatest problems, but they won't be as useful for navigating snowy climates where merely seeing the lanes can be a challenge. There's also the question of whether or not it's ideal to have cars measure the very conditions that hamper their driving. This isn't necessarily the safest approach. Waymo describes the research in a blog post.
The current weather maps have their limitations. They may help in a warm city like San Francisco, where condensation and puddles are usually the greatest problems, but they won't be as useful for navigating snowy climates where merely seeing the lanes can be a challenge. There's also the question of whether or not it's ideal to have cars measure the very conditions that hamper their driving. This isn't necessarily the safest approach. Waymo describes the research in a blog post.
Great idea (Score:2)
The vehicles measure the raindrops on windows to d (Score:2, Funny)
So then what happens when a member of San Francisco's beloved homeless drug addict community pees on the windshield?
Re: (Score:2)
So then what happens when a member of San Francisco's beloved homeless drug addict community pees on the windshield?
You wake up from your faux news fever dream in a puddle.
Re: (Score:2)
One thing is for sure: There won't be any photographers there to take pictures. https://abc7news.com/san-franc... [abc7news.com]
Re: (Score:2)
they get hit by the car and then waymo buys them an home to keep the case out of court.
Why not? (Score:3)
Take this further too - map out obstructions, pot holes, large puddles, you name it. If a road is "slow going" because of the conditions, then it's good to know that before going there. Someone's got to go take a look to know that, so why not whomever happens to be driving that way?
As an example, our GPS took us a particular route around town. At one particular turn, my wife said "I heard there was a big pothole down here, tyres bursting etc", so was driving slowly as a precaution. At one point there was a large puddle covering most of the lane, so she slowed right down to go through it. The people behind probably just thought she was being overly cautious, but had our GPS been able to warn us about the pothole (or the puddle), then we'd have been able to go faster through the clear bits and slower during the dangerous bits.
I'm struggling to see the downside here - it seems like a far better use of their time than (for example) mapping out wifi SIDs.
Phoenix weather (Score:2)
Every car in Phoenix will just say it's 105 degrees and not raining, I can see how that will be very useful!
Better way: (Score:2)
The technology gives Waymo a much finer-grained view of conditions than it gets from airport weather stations, radar and satellites.
You could get a much more accurate view if you merely deployed (via drone) a bunch of tiny solar powered weather stations in a grid and had them broadcast information back every 10 minutes to a relay point grid with 20 mile spacing. The relay points would also be cheap because they wouldn't even need towers but they would need larger solar cells and battery. A system like this could cover all of California (not just where there are roads) for a few million dollars and run with minimal maintenance.
Re: (Score:3)
The technology gives Waymo a much finer-grained view of conditions than it gets from airport weather stations, radar and satellites.
You could get a much more accurate view if you merely deployed (via drone) a bunch of tiny solar powered weather stations in a grid and had them broadcast information back every 10 minutes to a relay point grid with 20 mile spacing. The relay points would also be cheap because they wouldn't even need towers but they would need larger solar cells and battery. A system like this could cover all of California (not just where there are roads) for a few million dollars and run with minimal maintenance.
There is already millions of weather stations deployed in homes and antenna sites https://aprs.fi/#!lat=40.8103&... [aprs.fi] Here's one near Harrisburg PA. They already communicate with NOAA.
How granular is the need? Because as you increase the granularity in WX monitoring, it eventually becomes pretty confusing. Just because there was a downpour 10 minutes ago, doesn't mean there is one now, and the reverse is also true. And given that this is a moving vehicle transmitting the weather, it will be kinda extr
Re: (Score:2)
How granular is the need?
I was hoping to get a level of data that could help weather prediction by reporting wind speeds.
There is already millions of weather stations deployed in homes and antenna sites https://aprs.fi/#!lat=40.8103& [aprs.fi]... [aprs.fi] Here's one near Harrisburg PA. They already communicate with NOAA.
That data is generally considered to be worthless because of it's dubious accuracy.
Re: (Score:2)
How granular is the need?
I was hoping to get a level of data that could help weather prediction by reporting wind speeds.
There is already millions of weather stations deployed in homes and antenna sites https://aprs.fi/#!lat=40.8103& [aprs.fi]... [aprs.fi] Here's one near Harrisburg PA. They already communicate with NOAA.
That data is generally considered to be worthless because of it's dubious accuracy.
Have you told NOAA that? And what is your expertise on how the WayMo data will be more useful than these https://www.weathershack.com/l... [weathershack.com]
I would like to know - if you have the cites, I'll give them to NOAA - I work with them fairly often, and it will be a big help to get them to abandon useless information - then they can settle on the accurate calibrated Waymo data.
Tunnels (Score:2)
The AI will now select tunnels as the best roads.
I suppose next week (Score:2)
we'll see a story about how this all pervasive surveillance violates the privacy of the weather.
What is this data really needed for? (Score:2)
When I need a ride I need a ride. As long as it isn't too extreme who cares what the weather is. You need to get there for that appointment, get to school, get to the store, make it to the airport on time or answer a booty call. Who cares if there is a little drizzle or fog?
What I suspect this is all about is that Waymo is dependent on LIDAR for its situational awareness and LIDAR efficacy deteriorates rapidly when there is more water in the air. So what they really want to know is when it is too dan
Reaching for Any Positive Effect (Score:2)