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

401–410 of 498 posts

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

#401

Post by lnsru »

BurningFrog wrote: post #328
jimbo808 wrote: post #294

Earlier quoted context omitted.

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.

I think Google can handle paying for any number of $250k cars to get a good share of the future of transportation. I expect that in 10-20 years, all cars will be self driving.

This was thought decades ago too: https://en.wikipedia.org/wiki/Eureka_Prometheus_Project Compared to 1994 we have now endless computing power and yet no reliable self driving car is available on the market.

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

#402

Post by Ekaros »

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.

To me standing water sounds like obvious thing to include in testing. And maybe even design some reasonable technical solution like sensors near say wheels.

Areas with water should not be that uncommon that vehicles would never accidentally enter them. So seems like pools of say 10cm deep water should be included in testing.

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

#403

Post by rob74 »

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…

To me it looks like it's a problem with the "default attitude" (can't think of a better name) of the Waymo driving software. When a human sees that the road surface ahead is in some unknown condition (flooded, covered in lava, whatever) they usually default to caution - better stop and check first. While Waymo apparently defaults to blithely driving ahead, after all its maps tell it that there's a road ahead and it didn't detect any known obstacle, so what could possibly go wrong?

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

#404

Post by bitpush »

jurgemaister wrote: post #393
bitpush wrote: post #310

Earlier quoted context omitted.

Are you suggesting every DL holder knows all the driving conditions? Quick, what should one do when the car starts drifting in ice? How about aqua planing? If it is just taking a regular DL test, then waymo, Tesla and others would be driving all across the US by now. They already have a higher standard

> Are you suggesting every DL holder knows all the driving conditions? In my country at least: Yes. Hydroplaning and driving on ice is part of the compulsory training, including driving on simulated ice on a special course.

That's great. Would you your country's test covers 100% of the situations a driver might encounter?

Even without knowing the details, I can confidently tell you they don't.

Does it teach you how to recover the car when the tires blow out? How about it is raining? How to react when a car is coming straight at you in the wrong way? How about when a dog jumps out?

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

#405

Post by jimbo808 »

wasmitnetzen wrote: post #396
jimbo808 wrote: post #383

Earlier quoted context omitted.

I'm implying that drivers are more efficient at cleaning and maintaining, refueling, storing, repairing, and replacing their cars they own than the complex systems of personnel maintaining a much more expensive fleet of cars they don't own or give a shit about.

Are you also implying that people who maintain vehicles for a living do a worse job at it than the owners doing it themselves? I would say the opposite is true. Plenty of companies around the world have well-maintained fleets of vehicles. Trucking businesses, bus companies, train companies, even some taxi companies with salaried drivers, ...

No, I'm implying that people who maintain their own cars do it more efficiently. The simple stuff like cleaning has to be done by someone. It's not about doing a "worse job," it's about doing a more expensive job.

Waymo is replacing human drivers with a capital-intensive fleet business, a substantially more expensive vehicle, and still a large number of remote assistance staff, fleet operators, safety engineers, incident response, operations staff, etc.

But I'm not saying they can't beat a human driver, I'm just saying it hasn't been proven that they will. It may only be that the highest demand markets will provide a sufficient enough utilization to make it economically viable.

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

#406

Post by root-parent »

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…

[dead]

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

#407

Post by ViewTrick1002 »

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.

That is not a given when dealing with "machine learning".

They will need to have metrics for all these scenarious and ensure when they solve the 20th problem down the line this one does not regress, but instead it becomes more and more generalized.

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

#408

Post by mschuster91 »

ethbr1 wrote: post #238
namibj wrote: post #231

Earlier quoted context omitted.

Yeah you can start by not building _more_ in the flood plain. And if you do, then don't build architecture that is incapable of just accepting the temporarily higher ground water. We know how to basement just make the basement high enough to tower over the flood. Oh, no cheap ground-level storefront windows? Welp, guess those have to be elevated above sufficiently voluminous drainage channels (the former streets).

Or in Florida's case, mandate hurricane ties on timber homes so they can't lift off their slabs. One of the things that annoys me most about non-engineering mindsets is not looking at problems from a multivariate optimization perspective. There are problems, and then there are always more variables to be balanced to optimally solve them than people expect. The critical additional ones, more often than not: time and m…

> Or in Florida's case, mandate hurricane ties on timber homes so they can't lift off their slabs.

That doesn't mitigate much. The mass of a paper and matchsticks "house" just isn't enough to resist it getting torn apart - if not by the wind, then by debris.

The only kind of structure able to survive a dead-on hit is steel bar reinforced concrete or very, very solidly built brick-and-mortar. But that is expensive to build.

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

#409

Post by mschuster91 »

SR2Z wrote: post #388
QuercusMax wrote: post #192

Earlier quoted context omitted.

We had a story in the news this week about a Cybertruck driver who thought his Elonmobile was a boat because it has "wade mode" and deliberately drove into a lake! Humans are very stupid when it comes to driving through standing water!

To be fair if you take Elon Musk at his word the Cybertruck is supposed to have hermetically sealed powertrain components and be capable of exactly this.

The powertrain is one thing, the more critical issue is the car's structure, including the ventilation system, all sorts of gaps - and also, all hollow spaces, in which you need to balance weep holes (to prevent water condensation and subsequent rusting or weird issues regarding temperature changes) against the ability for external water to end up there at all.

Getting that right is a very expensive job and that's why you usually only see true (i.e. no visit to a shop needed afterwards) wade ability on large military vehicles and custom RV builds.

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

#410

Post by 21asdffdsa12 »

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 can already see the horrified passengers in a robo-taxi going full "military-survival" mode, driving at rally speed over fast flooding back-roads, evaluating moral dilemmas like ("If i stop and pick up one more, i become a lorry on a rail at the next flood intersection").

Surprisingly good at things that get you otherwise killed. Like - it auto-backs up once it detects ground rumbles of the ground moving during a mud avalanche.

Post reply on HN