That's a tough problem - distinguishing wet pavement from deep water.
Humans make that mistake frequently.
Autonomous vehicles should probably be equipped with a water sensor. (We did that in our DARPA Grand Challenge vehicle back in 2005). Then they can enter water very cautiously and see if it's too deep. This may make them too cautious about shallow puddles on roads, though.
It’s a particularly hard problem in Texas. We get torrential rains and the landscape is relatively flat. Couple that with shallow soil over lots of limestone and it means flooding is really common. We also have roads that have a “low water crossing,” where a road crosses a creekbed that is normally dry but which will flood. There are often water depth signs there (basically a vertical ruler with feet marks so you can see where the water is up to). We lose people to this scenario (driving into flood waters) every year. It’s particularly problematic when it’s dark and you miss a warning sign. Before you know it, you’re in deep water and the flow can sweep the whole car downstream until it gets pinned against a tree, possibly with water forcing its way into the car.
I've seen several places in England (and at least one in the western United States) where they have fords.
For those not familiar, water runs over the road full-time, and people are expected to just drive through it like it's no big deal. Except for right after a storm, when it is a big deal. It's essentially the intersection of a road and a stream where a bridge should be, but nobody ever built one.
If they've mapped the surface of the water relative to themselves... couldn't they slowly wade in and just calculate the depth based on that 3d model without extra sensors.
Assumes there's no abrupt cliff to fall off... but short of the ability to make a 3d map underwater that seems inevitable.
This is also why they recommend not to use polarized while cycling, it can obscure slicks or water in certain sections. I still use mine but I know it's not as ideal as photo chromatic lenses.
Any human can't necessarily tell the difference between an inch of water, which is perfectly safe to drive on (if slow enough that you don't hydroplane), and a flooded street. They can tell the difference between an inch of water and wet pavement, though.
You underestimate how frequently details like this change in the real world and how difficult it is to reliably integrate them into the mapping models with very low error rates.
Aggregating this data in something close to real-time, verifying and corroborating that the change to the road model is real and correct, and then pushing those model updates to every vehicle that may need it almost immediately is not really a solved problem.
Such detailed database of fine grained road geometry gets stale very quickly, due to road maintenance and road construction. In US highway lanes are shifted sideways frequently.
So the first waymo to get to this less used road to john’s will not have the data rather than every waymo that travels down a new highway, that then becomes a problem if it rains.
One car with an issue of first coincides with rain on a less used road?
Waymo does have a database of every today they drive, but for this they don't need one.
If the car comes to a road covered with water, and that road is in the database, and the water level appears low compared to the historical level of the road in the DB, then the car could cross. if the road is not in the DB, then a different decision might be made.
This is similar to humans: you might make different decisions depending on whether you know the road well or not.
Isn’t that the Waymo data model, though? They extensively pre-drive every new market, building dense volumetric maps of the entire service area before they begin service, so they essentially do have that database of every road (that they drive on).
Granted, I am not sure exactly how Waymo operates, but I thought that the extensive testing was mostly for legal reasons+just handling edge cases.
I am saying this, because I noticed that they typically start with a low-tier restrictive permit to operate (with a rather small number of cars in the fleet). Then they run it for a year or two, iron out edge cases particular to a given city (e.g., climate particularities, crazy spaghetti junctions in ATL, etc.), and log a lot of data. Then they take that data, go to the city/state, say "we have all this data that demonstrates we were very above the board while running the test pilot program, we are safe, and now we want to expand out of a very limited test pilot program."
And then it either goes well (Bay Area, LA, etc.) or goes off the rails for other reasons (often failing earlier for entirely unexpected reasons, like the pushback against it from taxi driver unions in NYC).
My point being, I could be entirely wrong, but I don't think that they literally map every single inch of the road before being allowed to operate. I just don't see it as being possible in any large populated city, given how often things change there. Just in 3 years living at one apartment in Seattle, I had a road directly adjacent to me changed from 2-way to 1-way, and then had 3-4 lanes that were basically highway entrances/exits (a block away from me) created and the whole area being rerouted entirely.
Tesla is less "HD", they have standard maps like we all think of, and a lane level "see-ahead" system where they basically just grab a satellite image tile, and align it with what the car sees for "FSD".
They actually do significant mapping. Where it operates currently it is not unusual to see this. It will be a waymo with a human driver operating someplace not currently in the waymo zone and clearly not en route to any maintenance facility either. Stuff like windy canyon roads with no thru access anywhere that are currently gated away, you might see a waymo with a human today.
Waymo is not the only company making lidar maps right now either. I've seen UPS deliver trucks with retrofitted lidar scanners on the roof now. I've even seen this on a police car already, looked like a black rooftop industrial ventilator on a 2ft mast installed directly on the crown victoria roof.
It doesn't take much of a rainstorm to see localized flooding. Some debris over the storm drain is enough to flood a street. Hard to anticipate that happening.
They have been known to make that mistake. To use the word "frequently" demonstrates a misunderstanding between number of incidents and total miles driven. It also ignores that humans often drink and most of these types of accidents happen after 2am and most often in the state of Florida.
> equipped with a water sensor
Car washes will be fun.
> DARPA Grand Challenge
The problems the grand challenge ignores are more important than the ones it solved.
By a water sensor do you mean a sensor to detect the water level relative to the chassis? It seems like a very inexpensive downward-facing ultrasound sensor could work.
Is ultrasound less expensive than a moisture sensor?
The problem with both is they effectively require the vehicle to be in the water already. They need something that can tell depth before the vehicle has to slow down.
I've never made that mistake; I'm not aware of anyone I know doing it. I very rarely see it myself, except on news footage. Of course it happens some time somewhere but that says nothing about frequency.
> That's a tough problem
Not really. Don't drive where you don't know it's safe. Definitely don't drive into moving water - puddles only, and only if not too deep: I can usually figure it out based on the rest of the road - unless it's a sinkhole, the geometry is somewhat consistent - and especially by looking at objects in the water such as other cars driving through it. Sorry your friend isn't competent to figure it out.
People here are always quick to defend the autonomous cars, like a close friend. How often will we fall in love with a technology or company? It always distorts the truth.
It’s definitely a thing humans do a lot in certain places. Perhaps where you live, it isn’t as much of an issue, so naturally you and nobody you know has encountered it.
Article's current (possibly original), less ambiguous title: "Waymo recalls 3,800 robotaxis after glitch allowed some vehicles to ‘drive into standing water’"
IOW 3,800 Waymo vehicles aren't currently sat spinning their wheels in water.
It's an interesting case of whether it's possible to infer the condition of wading and avoid having to install a sensor specific to a one in a million trips circumstance.
The inference would come from standing water slowing down the vehicle and likely require steering correction, in combination with some machine vision for identifying standing water.
Then there's the advantage of being Google and having hundreds of thousands of people in the same area using Google maps and navigation. Accelerometers in phones can detect crashes pretty reliably. There's a good chance they can reliably detect deceleration from standing water and report the location of the hazard.
How about a Mastodon, Lamb of God take with Floods of Triton:
Heap data upon this modern age
All human drivers now phased away
A lidar's glow, the soft wheel's echo
Autonomous force of code remains
We are last of the before rides
Now hear the robot cars rise
Hum into eternity
Remember this, all roadways lead to the fleet
Kind of unrelated. That issue was due to a misguided effort to be cautious by having vehicles requesting human-review when they didn't really need it. Waymo fixed the issue by allowing the vehicles to operate in their normal, independent, mode.
part of the problem is that SFs traffic lights just turn off in a power outage, rather than flashing red battery power as I have seen in many other jurisdictions
Not necessarily. Depending on angle and water depth, multi-return LIDAR can give you returns from both water surface and the road surface beneath, in the same way multi-return LIDAR can produce returns from vegetation and the ground beneath.
This is one of the reasons why I'm suspicious of camera-only systems, here in Finland. Half the year there's a lot of snow and ice around. Which I imagine means most of the view is "white" and "shiny". Coupled with the dark winters it's gotta be a nightmare to deal with.
Could you use a different spectrum of EM radiation to detect water? There are parts of the microwave band that attenuate the signal by absorption and I wonder if you could use that. The only clue a human driver has in that situation is in the visible spectrum. The lines of the road disappear from view, which can be challenging to see at night.
They are rolling these out in New Orleans soon. Standing water is everywhere, and sometimes you have big hidden potholes. You just need to know the roads. Should be fun.
"Recall" is a technical term meaning: "public dangerous defect notice".
A "recall" is stating that the defective version of the product in the field must be "removed/recalled" and replaced/updated with a non-defective version at the manufacturer's expense. It just so happens that the removal and replacement of defective software from the field can occur remotely.
The important part is that the manufacturer delivered a defective product that risks your safety, that fixing that safety defect is the responsibility of the manufacturer, and the system is unsafe until that occurs.
They suspended service areas they deem high risk until the software update can be applied. So while, yes, it's just a software update, it's a recall in the sense that they've temporarily pulled all the cars off the road in certain areas
Yes, this is a common terminology issue. "Recall" is legally defined in terms of the kind of problems that require one, not the solution to those problems, because the relevant regulations were written when there was no way to fix consumer products other than physically delivering them to the manufacturer or an authorized repair person.
Maybe you drive into flood waters, but I don't. That's not a difficult skill to pull off.
We're still in the early days of self driving cars, and as much simulation and miles as they have, they're still constantly getting exposed to real world conditions that are new to them. The world is dynamic, so this will always remain true.
It remains to be seen where we'll converge on capability, incident rate, and acceptance.
Maybe you don't drive into flood waters, but your Uber driver might, and that's what Waymo is trying to replace, not your personal driving.
In that context I think comparing it to the average human driver makes a lot of sense, because even if you personally are an even better driver, or even if human drivers are better at some specific things, we have more than enough data to show that Waymo reduces accident rates overall in their current rollout.
The world is dynamic, so sure, it will always be true in some technical sense. But I am confident that eventually we’ll have trained them on enough scenarios that novelty will have a smaller and smaller effect on their ability to safely navigate through the world.
Since recall on cars no longer means doing anything to the car's physical location I think the regulator NHSTA should update this term
It just creates alarmist headlines for what's really an over the air update, although "recall" is still currently a regulatory accurate term in the vehicle space
Cars, especially EVs, have many similarities to being phones. Imagine if a routine software update from Apple was called a "recall", that functionally describes what's happening here
NHTSA should at least distinguish between "omg we have to get these cars off the road and bring them to the shop immediately!" versus "over the air software update"
Exactly what I was thinking, the CNBC article feels very clickbity because they don't say that in the opening lead that it's just a software update. They make it sound like they need to be taken back to some factory somewhere and get their systems updated. Which is not true because they just get a software update.
We really need a better term for when an urgent software update for a vehicle is issued. The extreme majority of the population completely misunderstands it when a "recall" is done when it's actually just an OTA software update.
I really want car companies to just automate publishing “recalls” for every commit pushed to any car ever. Flood this broken term and force a distinction between “the airbags will literally explode and destroy your face” and “the radio volume is too quiet sometimes”
A "recall" is a specific regulated action. It is announced as a recall because that is what is legally required according to the NHTSA. There is no wiggle room here.
Yes, we need to change the rules to create a distinction. The meaning of “recall” in common understanding vs. industry has diverged, and it’s almost certainly causing car manufacturers to do suboptimal things to avoid having “recall” tied to their name in the press.
There is no issue in understanding unless you are talking about only reading the headline that a media outlet decides to use. How about we all just use our brains and understand that things can be fixed in different ways, but it is important that they get fixed.
Suboptimal behavior from companies is what leads to recalls. I cant even understand an example of what you are talking about there. And now you want to carry water for the industry by creating some diluted term. Does the car have a safety issue that is should not? Then its a recall. The manufacture can now decide how to resolve it. Sometimes that can be done via an OTA update.
I think its is in the interest of consumers to know ALL the ways these corps are putting your life at risk through their engineering efforts or lack there of. If your car manufacture is doing weekly OTA bug fixes on the vehicle that you drive you kids in everyday, you (the apparent beta tester) should sure as well know. Then you can make an informed decision.
That you need world models to sensibly deploy "thinking" machines in the real world. Else they do stupid shit like drive straight into water. You can bruteforce some semblance of thinking by training on literally all knowledge that can be digitized but even that is proving to not be quite enough.
Just this morning I was almost killed twice on my bike ride to work by two separate drivers, one of whom looked to be 80 and could barely see over the dashboard, and one who was on their phone. I didn’t even bother trying to remember the plate numbers, knowing that the odds of any kind of consequences are absolute zero.
No, we can’t go back to driving our own vehicles. Waymo everywhere and human driving outlawed, ASAP.
Agree. Multiple people I know have bought Teslas because they don’t trust themselves or their spouses to drive safely, and want them to use FSD. There should be incentives to get people onto self driving.
"Failure to follow all warnings and instructions can result in property damage, serious injury or death."
"Driver intervention may be required in certain situations, such as on narrow roads with oncoming cars, in construction zones, or while going through complex intersections."
"Always remember that Full Self-Driving (Supervised) (also known as Autosteer on City Streets) does not make Model S autonomous and requires a fully attentive driver who is ready to take immediate action at all times."
Different states have different rules about what sort of things insurers are allowed to charge different rates for. In the states that allow it, Tesla does offer insurance discounts for FSD usage.[1] Lemonade also offers discounts for FSD usage.[2]
I've seen several places in England (and at least one in the western United States) where they have fords.
For those not familiar, water runs over the road full-time, and people are expected to just drive through it like it's no big deal. Except for right after a storm, when it is a big deal. It's essentially the intersection of a road and a stream where a bridge should be, but nobody ever built one.
Assumes there's no abrupt cliff to fall off... but short of the ability to make a 3d map underwater that seems inevitable.
And that is the difference. In a Waymo you are a prisoner, in your own car you can turn around.
Aggregating this data in something close to real-time, verifying and corroborating that the change to the road model is real and correct, and then pushing those model updates to every vehicle that may need it almost immediately is not really a solved problem.
Apparently they were built in just a few months.
But yes, this wouldn't work for other self-driving systems that don't rely on HD maps.
One car with an issue of first coincides with rain on a less used road?
You think you know how deep it is under because you've taken that road many times before (or in your case you have historical laser measurement)
But you don't know:
- Maybe the road under fully collapsed
- Maybe the flow of water is extremely strong, so you need to accurately estimate that too.
If the car comes to a road covered with water, and that road is in the database, and the water level appears low compared to the historical level of the road in the DB, then the car could cross. if the road is not in the DB, then a different decision might be made.
This is similar to humans: you might make different decisions depending on whether you know the road well or not.
I am saying this, because I noticed that they typically start with a low-tier restrictive permit to operate (with a rather small number of cars in the fleet). Then they run it for a year or two, iron out edge cases particular to a given city (e.g., climate particularities, crazy spaghetti junctions in ATL, etc.), and log a lot of data. Then they take that data, go to the city/state, say "we have all this data that demonstrates we were very above the board while running the test pilot program, we are safe, and now we want to expand out of a very limited test pilot program."
And then it either goes well (Bay Area, LA, etc.) or goes off the rails for other reasons (often failing earlier for entirely unexpected reasons, like the pushback against it from taxi driver unions in NYC).
My point being, I could be entirely wrong, but I don't think that they literally map every single inch of the road before being allowed to operate. I just don't see it as being possible in any large populated city, given how often things change there. Just in 3 years living at one apartment in Seattle, I had a road directly adjacent to me changed from 2-way to 1-way, and then had 3-4 lanes that were basically highway entrances/exits (a block away from me) created and the whole area being rerouted entirely.
https://waymo.com/blog/2020/09/the-waymo-driver-handbook-map...
Tesla is less "HD", they have standard maps like we all think of, and a lane level "see-ahead" system where they basically just grab a satellite image tile, and align it with what the car sees for "FSD".
Waymo is not the only company making lidar maps right now either. I've seen UPS deliver trucks with retrofitted lidar scanners on the roof now. I've even seen this on a police car already, looked like a black rooftop industrial ventilator on a 2ft mast installed directly on the crown victoria roof.
They have been known to make that mistake. To use the word "frequently" demonstrates a misunderstanding between number of incidents and total miles driven. It also ignores that humans often drink and most of these types of accidents happen after 2am and most often in the state of Florida.
> equipped with a water sensor
Car washes will be fun.
> DARPA Grand Challenge
The problems the grand challenge ignores are more important than the ones it solved.
The problem with both is they effectively require the vehicle to be in the water already. They need something that can tell depth before the vehicle has to slow down.
I've never made that mistake; I'm not aware of anyone I know doing it. I very rarely see it myself, except on news footage. Of course it happens some time somewhere but that says nothing about frequency.
> That's a tough problem
Not really. Don't drive where you don't know it's safe. Definitely don't drive into moving water - puddles only, and only if not too deep: I can usually figure it out based on the rest of the road - unless it's a sinkhole, the geometry is somewhat consistent - and especially by looking at objects in the water such as other cars driving through it. Sorry your friend isn't competent to figure it out.
People here are always quick to defend the autonomous cars, like a close friend. How often will we fall in love with a technology or company? It always distorts the truth.
IOW 3,800 Waymo vehicles aren't currently sat spinning their wheels in water.
The inference would come from standing water slowing down the vehicle and likely require steering correction, in combination with some machine vision for identifying standing water.
Then there's the advantage of being Google and having hundreds of thousands of people in the same area using Google maps and navigation. Accelerometers in phones can detect crashes pretty reliably. There's a good chance they can reliably detect deceleration from standing water and report the location of the hazard.
“Wash away maaaaan, take him with the floooood”
https://abc7news.com/post/san-francisco-leaders-press-waymo-...
A "recall" is stating that the defective version of the product in the field must be "removed/recalled" and replaced/updated with a non-defective version at the manufacturer's expense. It just so happens that the removal and replacement of defective software from the field can occur remotely.
The important part is that the manufacturer delivered a defective product that risks your safety, that fixing that safety defect is the responsibility of the manufacturer, and the system is unsafe until that occurs.
Look, you can't make progress without getting your feet wet and then diving straight into the deep end.
We're still in the early days of self driving cars, and as much simulation and miles as they have, they're still constantly getting exposed to real world conditions that are new to them. The world is dynamic, so this will always remain true.
It remains to be seen where we'll converge on capability, incident rate, and acceptance.
In that context I think comparing it to the average human driver makes a lot of sense, because even if you personally are an even better driver, or even if human drivers are better at some specific things, we have more than enough data to show that Waymo reduces accident rates overall in their current rollout.
It just creates alarmist headlines for what's really an over the air update, although "recall" is still currently a regulatory accurate term in the vehicle space
Cars, especially EVs, have many similarities to being phones. Imagine if a routine software update from Apple was called a "recall", that functionally describes what's happening here
NHTSA should at least distinguish between "omg we have to get these cars off the road and bring them to the shop immediately!" versus "over the air software update"
We really need a better term for when an urgent software update for a vehicle is issued. The extreme majority of the population completely misunderstands it when a "recall" is done when it's actually just an OTA software update.
Suboptimal behavior from companies is what leads to recalls. I cant even understand an example of what you are talking about there. And now you want to carry water for the industry by creating some diluted term. Does the car have a safety issue that is should not? Then its a recall. The manufacture can now decide how to resolve it. Sometimes that can be done via an OTA update.
I think its is in the interest of consumers to know ALL the ways these corps are putting your life at risk through their engineering efforts or lack there of. If your car manufacture is doing weekly OTA bug fixes on the vehicle that you drive you kids in everyday, you (the apparent beta tester) should sure as well know. Then you can make an informed decision.
https://waymo.com/blog/2026/02/the-waymo-world-model-a-new-f...
Or did you mean strictly in operation?
https://youtu.be/DOW_kPzY_JY
He posts on an internet message board
"Failure to follow all warnings and instructions can result in property damage, serious injury or death."
"Driver intervention may be required in certain situations, such as on narrow roads with oncoming cars, in construction zones, or while going through complex intersections."
"Always remember that Full Self-Driving (Supervised) (also known as Autosteer on City Streets) does not make Model S autonomous and requires a fully attentive driver who is ready to take immediate action at all times."
1. https://www.tesla.com/support/insurance/fsd-discount
2. https://www.lemonade.com/fsd