Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Waymo pauses Atlanta service as its robotaxis keep driving into floods

techcrunch.com

Post reply on HN
Print view View original

291–300 of 498 posts

Re: Waymo pauses Atlanta service as its robotaxis keep driving into floods

#291

Post by KennyBlanken »

sarchertech wrote: post #280
dhbradshaw wrote: post #123

To me this doesn't seem like a disaster but just the kind of thing that happens as you role out a service and expose it to new challenges. Presumably they haven't had the chance to do a lot of flood training but now they have that chance. The huge advantage they have over people in general is that ideally if they figure this out then it will stay figured out. Then they can slowly role out and watch for the next hitch…

> The huge advantage they have over people in general is that ideally if they figure this out then it will stay figured out. Then they can slowly role out and watch for the next hitches from new situations. This is also a huge disadvantage because any flaws in the software that don’t show up in a slow rollout will be present in every single car. It’s a contrived example, but say a new billboard campaign rolls out tha…

Waymo has had a ton of problems like their fleets getting stuck circling a particular block or neighborhood. That's been a thing for years. There was a story about it happening in a new city, just a week or two ago.

Even fairly far into their roll-out they clearly didn't do any simulations of the vehicle getting pulled over or interacting with police, and that sort of thing continued to be a problem for a while. I remember footage of a Waymo just driving off after being 'pulled over.'

These self-driving companies need to be held to the same legal standards as any other driver. Right now it's the wild west and people have literally been killed because the only people writing the regulations are their lobbyists.

Re: Waymo pauses Atlanta service as its robotaxis keep driving into floods

#292

Post by sarchertech »

kibwen wrote: post #198
srdjanr wrote: post #196

Earlier quoted context omitted.

I wouldn't call floods "very common"

Any given person might only experience a single flooded roadway or two in their lifetime. But that doesn't mean that there aren't tens of thousands of people exposed to flooded roadways every year. Something can be individually uncommon and yet frequent in absolute terms.

If you live in a city like Atlanta that gets significantly more rainfall that Seattle but concentrated into fewer rainy days, you’ll see flooded roadways multiple times per year.

Re: Waymo pauses Atlanta service as its robotaxis keep driving into floods

#293

Post by sarchertech »

Fernicia wrote: post #223
JamesSwift wrote: post #214

Earlier quoted context omitted.

Well its not that simple. In the same way that throwing an LLM into a process will always have a risk of blowing up spectacularly. In this case it failed open. It didnt recognize that it was in an edge case (which itself is an edge case). So what are you proposing to be the solution to that? If the car itself does not recognize that its in an abnormal situation that needs intervention then how do you intervene?

His point is that humans are prone to the same error. The flooded engine damage doesn't come from humans recognising the danger of a flooded road and choosing not to attempt it.

No one cares about flooded engines that Google has to pay for. They care about a taxi that might kill them.

You have to compare this to the number of taxi and Uber drivers who will drive into moving water with passengers on board while a passenger is telling them to stop.

Re: Waymo pauses Atlanta service as its robotaxis keep driving into floods

#294

Post by jimbo808 »

dhbradshaw wrote: post #123

To me this doesn't seem like a disaster but just the kind of thing that happens as you role out a service and expose it to new challenges. Presumably they haven't had the chance to do a lot of flood training but now they have that chance. The huge advantage they have over people in general is that ideally if they figure this out then it will stay figured out. Then they can slowly role out and watch for the next hitch…

The huge disadvantage they have over people is that their cars cost $250k, require a workforce of people to retrieve and repair them, maintain them, clean them, monitor them, etc. They are more expensive to operate than a normal car with a human driver, so far. The break-even point requires a lot of problems to be solved, and even then, the upside is not looking to be astronomical in the best case.

Re: Waymo pauses Atlanta service as its robotaxis keep driving into floods

#295

Post by bluGill »

sarchertech wrote: post #290
bluGill wrote: post #229

Earlier quoted context omitted.

They are still not very common. They happen more than other weather, but that still isn't common.

That depends on you definition of “flood”. But here we’re just talking about dangerously flooded roadways, and in many parts of the US those happen multiple times per year. Definitely common enough that you can’t just shut down your fleet anytime there is a danger of it happening.

My experience with them is they only last a short time, and there is almost always an alternate route so you are not shutting anything down, just slowing things down a little.

Re: Waymo pauses Atlanta service as its robotaxis keep driving into floods

#296

Post by riknos314 »

krackers wrote: post #153
grumbel wrote: post #151

Earlier quoted context omitted.

I am a little worried that this is still a problem after 20 years. Don't they have simulators to test every weird and unexpected road condition offline? And flooded roads aren't exactly an unusual event to begin with.

They can simulate "driving out of a raging fire" but not a flooded street? This seems like an admission that the fancy "world model simulation" doesn't actually mean much https://waymo.com/blog/2026/02/the-waymo-world-model-a-new-f...

No simulation is perfect, so ideally you have a feedback look constantly looking at new real-world data as it comes in and finding where the simulation has errors, and updating the simulation to improve the correlation between the simulation and the real world over time.

My guess is they did have flooded street sims but the correlation was much lower than expected, or the details of the situation being simulated (lighting, building locations, how dirty the water is, ...) were sufficiently different from the situation that was encountered that the sim based training didn't generalize to the new context.

Re: Waymo pauses Atlanta service as its robotaxis keep driving into floods

#297

Post by roxolotl »

kibwen wrote: post #198
srdjanr wrote: post #196

Earlier quoted context omitted.

I wouldn't call floods "very common"

Any given person might only experience a single flooded roadway or two in their lifetime. But that doesn't mean that there aren't tens of thousands of people exposed to flooded roadways every year. Something can be individually uncommon and yet frequent in absolute terms.

It’s funny as someone from the North East who’s always lived around rivers I assumed uncommon means once or twice a year. Not disagreeing they are uncommon, nor suggesting driverless cars are never going to happen. Just marveling at how different two individuals understanding can be of the same word.

Re: Waymo pauses Atlanta service as its robotaxis keep driving into floods

#298

Post by chippiewill »

jfim wrote: post #245
ryukoposting wrote: post #232

Earlier quoted context omitted.

SV is the most cloistered place I've ever seen. I'm comfortable assuming that nobody in any position of power at Waymo ever thought to themselves "gee maybe the weather is different in this new city we're deploying to, perhaps we should test that"

There's a long tail of unpredictable events in the AV industry that you end up seeing, especially since the cars in aggregate end up driving more than one could over a lifetime. At a previous employer, we've seen anything from cars getting mooned, a SUV slowly driving past the AV, the rear window roll down, and someone poke their head out and start throwing dollar bills at the AV, a convention of people dressed up in…

I used to work for an AV startup.

One of my favourite things to see were the random encounters that our data annotators would flag up.

Unusual agricultural vehicles, large to-scale images on the sides of vehicles, cars facing backwards being carried by a vehicle transporter.

It's a wildly long tail of things that automated vehicles need to handle.

Re: Waymo pauses Atlanta service as its robotaxis keep driving into floods

#300

Post by rawgabbit »

grumbel wrote: post #151
dhbradshaw wrote: post #123

To me this doesn't seem like a disaster but just the kind of thing that happens as you role out a service and expose it to new challenges. Presumably they haven't had the chance to do a lot of flood training but now they have that chance. The huge advantage they have over people in general is that ideally if they figure this out then it will stay figured out. Then they can slowly role out and watch for the next hitch…

I am a little worried that this is still a problem after 20 years. Don't they have simulators to test every weird and unexpected road condition offline? And flooded roads aren't exactly an unusual event to begin with.

Can Waymo cars even sense or detect flooded roadways? That is when it sees images of water covering the road, is it smart enough to know the car might get pushed into the raging waters?

This is one of the reasons why I switched to Apple Maps years ago. Google Maps kept giving directions to small backroads that I knew were prone to flooding. I noticed it when Google announced they were changing the algorithm to save people gas or something.

Post reply on HN