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

531–540 of 699 posts

Re: The Waymo World Model

#531

Post by sixo »

nelsondev wrote: post #526

Neat! What happens when the simulated data is hallucinated/incorrect? In the example videos, the Golden Gate bridge with snow shows the bridge as 1 road, with total of 3 lanes. But in reality, it’s a split highway with divider, so 2 sides both have 3 lanes, 6 total lanes. What happens when the car “learns” to drive on the simulated incorrect 3 lane example? For example will next time it goes on the real GG bridge hug…

Ideally it would learn a relationship between the sensor input and the correct actions, even if the sensor input is not realistic for the GG in reality.

Re: The Waymo World Model

#532

Post by sixo »

ex-aws-dude wrote: post #413
sixo wrote: post #409

Earlier quoted context omitted.

Well it certainly helps,doesn't it? This system is going to encounter more edge cases than a single human ever would. Hopefully the lessons from known unknowns generqlise to unknowns. And once they've been seen once they took can become part of the corpus.

Right but does this just rely on some human "brainstorming" a bunch of edge cases? It just strikes me as neverending edge case wack-a-mole A human doesn't need to see tons of examples of tornados and elephants to know to stop the car Doesn't that indicate some fundamental difference between the model and a human driver?

It might be "never-ending", but you're going to encounter edge cases in approximate proportion to the rate at which they actually occur. Anyway, the hope would be to learn behaviors which generalize, not to respond to each edge case ad-hoc; the edge cases provide out-of-sample tests of generalizability.

Re: The Waymo World Model

#533

Post by rswail »

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…

Maybe they were focusing on a real world use that basically requires AI, but not LLMs.

Tesla claimed that all their "real world" recording would give them a moat on FSD.

Waymo is showing that a) you need to be able to incorporate stuff that isn't "real" when training, and b) you get a lot more information from alternate sensors to visible spectrum only.

Re: The Waymo World Model

#534

Post by seanhunter »

permenant wrote: post #151
seanhunter wrote: post #40

Earlier quoted context omitted.

As a Londoner who used to have to ride up Abbey Road at least once per week there are people on that crossing pretty much all day every day reproducing that picture. So now Waymo are in Beta in London[1] they have only to drive up there and they'll get plenty of footage they could use for taht. [1] I've seen a couple of them but they're not available to hire yet and are still very rare.

Will Google finally fund Christopher Wren's post great fire "wide streets" rebuild of the City?

Yeah it’s interesting to imagine a London that had such a rebuild, like Napoleon’s rebuild of Paris. I personally love the weird narrow streets and little alleyways of the City, but that’s because when I’m there I’m pretty much exclusively on foot having taken the tube in.

Re: The Waymo World Model

#535

Post by rswail »

smallmancontrov wrote: post #228
ambicapter wrote: post #173

Earlier quoted context omitted.

So if they’re already “fusioning” all these things, why would LIDAR be any different?

Tesla went nothing-but-nets (making fusion easy) and Chinese LIDAR became cheap around 2023, but monocular depth estimation was spectacularly good by 2021. By the time unit cost and integration effort came down, LIDAR had very little to offer a vision stack that no longer struggled to perceive the 3D world around it. Also, integration effort went down but it never disappeared. Meanwhile, opportunity cost skyrocketed…

It doesn't solve the "Coyote paints tunnel on rock" problem though.

Re: The Waymo World Model

#536

Post by Arainach »

brokencode wrote: post #266
phkahler wrote: post #206

Earlier quoted context omitted.

Google has been doing more R&D and internal deployment of AI and less trying to sell it as a product. IMHO that difference in focus makes a huge difference. I used to think their early work on self-driving cars was primarily to support Street View in thier maps.

There was a point in time when basically every well known AI researcher worked at Google. They have been at the forefront of AI research and investing heavily for longer than anybody. It’s kind of crazy that they have been slow to create real products and competitive large scale models from their research. But they are in full gear now that there is real competition, and it’ll be cool to see what they release over th…

>It’s kind of crazy that they have been slow to create real products and competitive large scale models from their research.

Not really. If Google released all of this first instead of companies that have never made a profit and perhaps never will, the case law would simply be the copyright holders suing them for infringement and winning.

Re: The Waymo World Model

#537

Post by numpad0 »

schiffern wrote: post #362
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'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. So for the record, with this realization you're 3+ years behind Tesla. https://www.youtube.com/watch?v=ODSJsviD_SU&t=3594s

Practically ALL course introductory materials that regard robotics and AI that I've seen began with "you might imagine a talking bipedal humanoid when you hear the word `robot`, but perhaps the most commonplace robot that you have seen is a vending machine", with the illustration of a typical 80s-90s outdoor soda vendor with no apparent moving parts.

So "maybe cars are a bit of robots too" is more like 30-50 years behind the time.

Re: The Waymo World Model

#538

Post by rswail »

smeeth wrote: post #95
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 always understood this to be why Tesla started working on humanoid robots

The drop in demand for Tesla's clapped out model range would have meant embarrassing factory closures, so now they're being closed to start manufacturing a completely different product. Bait and switch for Tesla investors.

I wonder how long they'll be closed for "modifications" and whether the Optimus Prime robot factories will go into production before the "Trump Kennedy Center" is reopened after its "renovations".

Re: The Waymo World Model

#539

Post by rswail »

monocasa wrote: post #442
jasondigitized wrote: post #344

Earlier quoted context omitted.

I don't want a humanoid robot. I want a purpose built robot.

I mean, I would take a robot to handle all of my housework. Purpose built, that probably takes the form of a humanoid robot since all of tasks it needs to do were previously designed for humanoids.

Vacuuming and mopping are not inherently "designed" for humans.

Dusting with a single extensible and multiple degrees of freedom arm would be much more maneuverable than a human arm.

Loading and unloading washing machines or dryers or doign the same for dishes and cutlery in a dishwasher is not inherently designed for humans.

If anything, selling an integrated "housekeeping" system that fits into an existing laundry and combines features would be a much better approach.

Re: The Waymo World Model

#540

Post by rkomorn »

rswail wrote: post #535
smallmancontrov wrote: post #228

Earlier quoted context omitted.

Tesla went nothing-but-nets (making fusion easy) and Chinese LIDAR became cheap around 2023, but monocular depth estimation was spectacularly good by 2021. By the time unit cost and integration effort came down, LIDAR had very little to offer a vision stack that no longer struggled to perceive the 3D world around it. Also, integration effort went down but it never disappeared. Meanwhile, opportunity cost skyrocketed…

It doesn't solve the "Coyote paints tunnel on rock" problem though.

IIRC, that was only ever a problem for the coyote, though.

Source: not a computer vision engineer, but a childhood consumer of looney toons cartoons.

Post reply on HN