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

The Waymo World Model

waymo.com

Post reply on HN
Print view View original

601–610 of 699 posts

Re: The Waymo World Model

#601

Post by kube-system »

scoofy wrote: post #511
raincole wrote: post #399

Earlier quoted context omitted.

Roads (cars) need well behave people too. The only way cars filter some of the out is by the price.

The vast majority of the anti-social behavior on public transit not relevant in automobiles because (1) you can't turnstile jump the gas tank, (2) an automobile is effectively very expensive set of headphones, and (3) you can inhale whatever you want in your vehicle and your neighbor doesn't have to breath it. Automobiles are a wildly inefficient and expensive form of transportation in urban areas. At the same time,…

I think they have a point. But the anti-social behaviors in a car on the road are mostly a different set of anti social behaviors than you’d see on a bus or train. But they certainly exist.

Re: The Waymo World Model

#602

Post by kube-system »

generalenvelope wrote: post #486
xnx wrote: post #428

Earlier quoted context omitted.

No, but roads are paid for by road users (i.e. everyone).

AFAICT, the majority (60%) of funding for roads doesn't come from direct user charges... Roads are subsidized, free parking (and generally a lot of paid parking) is subsidized, and the sprawl encouraged by car dependence combined with the resulting infrastructure costs has and will continue to bankrupt cities. I don't think we should "just only have trains", but the current US transit landscape is absurdly stupid and…

Yeah I think the single biggest red flag that the US absolutely could support more public transit is the fact that many cities successfully had more public transit in the past.

Re: The Waymo World Model

#603

Post by kube-system »

jrm4 wrote: post #330
iknowstuff wrote: post #187

Earlier quoted context omitted.

Filipino driver is false. Filipino guidance person is true.

The difference being?

They’re like a back-seat driver instead of a driver. They can say “take that turn”, or “go over there”, but they can’t operate the controls.

Re: The Waymo World Model

#604

Post by ericzundel »

mattlondon wrote: post #89

Suddenly all this focus on world models by Deep mind starts to make sense. I've never really thought of Waymo as a robot in the same way as e.g. a Boston Dynamics humanoid, but of course it is a robot of sorts. Google/Alphabet are so vertically integrated for AI when you think about it. Compare what they're doing - their own power generation , their own silicon, their own data centers, search Gmail YouTube Gemini wor…

I just listened to a fantastic multi-hour Acquired (https://www.acquired.fm/) podcast episode on Google and AI that talks about the history of Google and AI and all the ways they have been using it since 2012. It's really fascinating. You can forgive them for not focusing on Reader or any of their other properties when you realize they were pulling in hundreds of billions of dollars of value by making big bets in AI and incorporating it into their core business.

Re: The Waymo World Model

#605

Post by kube-system »

smotched wrote: post #465
goatlover wrote: post #180

Earlier quoted context omitted.

Walking, bikes and scooters.

again, this is not europe. we don't ride bikes, and we certainly don't walk.

Yeah, that’s the root of a lot of problems in the US.

But pedestrian infrastructure is a very simple problem to solve, even in the US. Just look at how the market responds to public transit projects in the US —- developers trip over themselves to build projects in response to the induced demand.

Likewise they also responded to the reduced demand as a result of ripping out public transit infrastructure in the 20th century. Which is why doughnut-shaped cities are common in the US.

Re: The Waymo World Model

#607

Post by quanto »

smallmancontrov wrote: post #361
magicalist wrote: post #298

Earlier quoted context omitted.

> but monocular depth estimation was spectacularly good by 2021 It's still rather weak and true monocular depth estimation really wasn't spectacularly anything in 2021. It's fundamentally ill posed and any priors you use to get around that will come to bite you in the long tail of things some driver will encounter on the road. The way it got good is by using camera overlap in space and over time while in motion to fi…

It was spectacularly good before 2021, 2021 is just when I noticed that it had become spectacularly good. 7.5 billion miles later, this appears to have been the correct call.

What are the techniques (and the papers thereof) that you consider to be spectacularly good before 2021 for depth estimation, monocular or not?

I do some tangent work from this field for applications in robotics, and I would consider (metric) depth estimation (and 3D reconstruction) starting to be solved only by 2025 thanks to a few select labs.

Car vision has some domain specificity (high similarity images from adjacent timestamps, relatively simpler priors, etc) that helps, indeed.

Re: The Waymo World Model

#608

Post by kube-system »

spaceywilly wrote: post #204
jrm4 wrote: post #163

1. Still hard not to think that this is a huge waste of time as opposed to something that's a little more like a public transport train-ish thing, i.e. integrate with established infrastructure. 2. No seriously, is the filipino driver thing confirmed? It really feels like they're trying to bury that.

My view on Waymo and autonomous taxis in general is they will eventually make public transit obsolete. Once there is a robotaxi available to pick up and drop off every passenger directly from a to b, the whole system could be made to be super efficient. It will take time to get there though. But eventually I think we will get there. Human drivers will be banned, the roads will be exclusively used by autonomous vehicl…

Only in lower density areas.

In high density regions, vehicles on surface roads can’t meet the passenger demand required. Even if you banned human drivers, the other human users introduce too much variability and delay (passengers loading and unloading, errant objects, cyclists and pedestrians, etc). Roll a dumpster in the street, and have a couple of jaywalkers, and the entire system crawls to a stop.

Controlled access is required to get even medium-high throughput. But these systems already exist, they are called personal rapid transit systems.

Re: The Waymo World Model

#609

Post by felixg3 »

rstuart4133 wrote: post #580
sdf2erf wrote: post #513

Earlier quoted context omitted.

Yeah people seem to be pretty poor at judging the impact of 'key' people. E.g. Steve Jobs was absolutely fundamental to the turn around of Apple. Will Brin have this level of incremental impact on the Goog/Alphabet of today? Nah.

The difference is: Apple had one "key person", Jobs, and yes the products he drove made the company successful. Now Jobs has gone I haven't seen anything new. But if you look at Google, there isn't one key product. There are a whole pile of products that are best in class. Search (cringe, I know it's popular here to say Google search sucks and perhaps it does, but what search engine is far better?), YouTube, Maps, An…

Docs was just an acquisition of Writely, an early „Web 2.0“ document editor service, so „first done by google“ is a bit imprecise

Re: The Waymo World Model

#610

Post by ragazzina »

nunez wrote: post #565
doctoboggan wrote: post #326

Earlier quoted context omitted.

> they (1) don't actually charge enough maintain the variable cost of operations Why do you expect them to make money? Roads don't make money and no one thinks to complain about that. One of the purposes of government is to make investment in things that have more nebulous returns. Moving more people to public transit makes better cities, healthier and happier citizens, stronger communities, and lets us save money on…

They do through taxes or tolls!

"The U.S. generates approximately $17.4 billion in annual toll revenue".

"The total annual cost for road maintenance in the U.S. is in the hundreds of billions of dollars, with estimates showing over $200 billion spent yearly".

Post reply on HN