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

Waymo One doubles service area in Phoenix, continues growing in SF

blog.waymo.com

Post reply on HN
Print view View original

371–380 of 520 posts

Re: Waymo One doubles service area in Phoenix, continues growing in SF

#371

Post by dilyevsky »

jeffbee wrote: post #48

The Waymo approach has proven itself. Targeted testing, running the driver in hard mode as much as possible, is better than the Tesla approach. Tesla’s plan was essentially “machine learning underpants gnomes”. Collect ten billion miles of data from guys driving down 280 -> ??? -> profit. Didn’t work and now Tesla is recognized as being dead last in the game, behind dozens of no-name Chinese players. Now what I wonde…

Tesla approach is to grief their customers into paying for feature they have no concrete plans to ever deliver on (in the absence of lidar/radar sensors it’s a crapshoot) -> profit. Worked pretty well

Re: Waymo One doubles service area in Phoenix, continues growing in SF

#372

Post by xnx »

toss1 wrote: post #95
agnosticmantis wrote: post #74

Really love what waymo have been achieving with a relatively small team, but more importantly, they’ve had their heads down working and solving hard problems instead of opting for attention-seeking behavior, making ridiculously pompous claims and false promises (e.g. delivering robotaxies that make you $30k/yr by next year!), getting into ideological (sensor) wars, etc. (How many people know the name of their CEO? An…

Yup, I very much liked the broader approach of solving the general problem, but this actually seems to be doing better. The general problem has insane amounts of edge cases, and is basically trying to do a pole-vault-height high jump; if you succeed, you own the world (or at least can automatically drive anywhere on it), but until then, you and your customers have lots of problems. Meanwhile, the approach of map-ever…

Interesting question. I'm guessing the information density of 100 miles of standard American interstate is less than that of 1 city block in Manhattan.

Re: Waymo One doubles service area in Phoenix, continues growing in SF

#373

Post by xnx »

ra7 wrote: post #362
gonehome wrote: post #348

Earlier quoted context omitted.

I think Tesla does use Lidar in training for what it's worth (at least I recall someone telling me this - I think it was a friend that worked there but not 100% sure I'm remembering correctly). It's possible the lidar approach only really works with up to date high resolution maps and without that you end up in a local max you can't really escape with that approach. That's been Tesla's argument up to this point anywa…

> It's possible the lidar approach only really works with up to date high resolution maps and without that you end up in a local max you can't really escape with that approach. Sorry, but you’re just repeating Elon Musk’s buzzwords like “local maximum”. It doesn’t make sense. There’s no such thing as “lidar approach”. All sensor inputs are fused (early/late fusion) and run through perception algorithms. Lidar is used…

I expect Tesla's rationalization will suddenly change when the cost for lidar units drops to hundreds of dollars. At that point, Waymo will have a huge head start.

Re: Waymo One doubles service area in Phoenix, continues growing in SF

#374

Post by xnx »

gonehome wrote: post #350
xnx wrote: post #347

Earlier quoted context omitted.

Example? There are plenty of examples where mistakes that Tesla's cameras make (being blinded by the sun, having trouble with emergency vehicles) are no problem for systems with more sensors.

This talk was worth watching (any Karpathy or Carmack talk is imo): https://www.youtube.com/watch?v=g6bOwQdCJrc Specifically this is the relevant part: https://youtu.be/g6bOwQdCJrc?t=1370 They removed radar because it was making things worse.

I interpreted that statement by Karpathy as an accidental admission of Tesla's own limitations and not of the approach itself. (Note: I'm upvoting all your comments because they're very reasonable and supported.)

Re: Waymo One doubles service area in Phoenix, continues growing in SF

#376

Post by ra7 »

xnx wrote: post #373
ra7 wrote: post #362

Earlier quoted context omitted.

> It's possible the lidar approach only really works with up to date high resolution maps and without that you end up in a local max you can't really escape with that approach. Sorry, but you’re just repeating Elon Musk’s buzzwords like “local maximum”. It doesn’t make sense. There’s no such thing as “lidar approach”. All sensor inputs are fused (early/late fusion) and run through perception algorithms. Lidar is used…

I expect Tesla's rationalization will suddenly change when the cost for lidar units drops to hundreds of dollars. At that point, Waymo will have a huge head start.

Lidar cost has already dropped a lot. Waymo’s lidar on their I-Pace is 90% cheaper than the previous gen. We’re also seeing car manufacturers (GM, Volvo/Polestar, Mercedes, Chinese OEMs) include inexpensive lidar units for driver assistance.

Tesla’s problem is that they’ve promised their existing cars on the road are capable of full self driving. They can’t add hardware to them, so they will maintain the “camera is sufficient” stance for a long time.

Re: Waymo One doubles service area in Phoenix, continues growing in SF

#377

Post by xnx »

fallingknife wrote: post #197
jeffbee wrote: post #48

The Waymo approach has proven itself. Targeted testing, running the driver in hard mode as much as possible, is better than the Tesla approach. Tesla’s plan was essentially “machine learning underpants gnomes”. Collect ten billion miles of data from guys driving down 280 -> ??? -> profit. Didn’t work and now Tesla is recognized as being dead last in the game, behind dozens of no-name Chinese players. Now what I wonde…

Last based on what metrics? I've never seen anything better than the Tesla FSD except for the LIDAR robo taxis, but they are solving a very different problem with different constraints. Most recent cost estimate I can find shows a cost per vehicle of $130-150K for Waymo vs the Tesla system that needs to go in a vehicle costing $40-50K which makes using a Waymo style sensor suite impossible. Would be interesting to se…

Sensors are following a really great learning curve, rapidly getting both more capable, more reliable, and cheaper. It's reasonable to expect they could be a few hundred dollars per unit soon.

Re: Waymo One doubles service area in Phoenix, continues growing in SF

#378

Post by ra7 »

gonehome wrote: post #349
xnx wrote: post #344

Earlier quoted context omitted.

Birds fly by eating bugs and flapping wings, but that doesn't mean we should build planes that way. Tesla is stubbornly handicapping itself by cheaping-out on sensors because they think they can hail-mary yolo themselves all the way full self driving.

The Tesla's do have more than two cameras despite us having only two eyes. I don't think that analogy totally holds. It's more that because roads (and road signs) are designed for human vision and human drivers in order to handle all cases you really need to solve vision and if you do that sufficiently then the other sensors are redundant anyway. High resolution mapping works for localized solutions, but not in the g…

High resolution maps are only one part of the equation. Everyone is working on a generic perception/prediction/planning stack that works everywhere. Only the map changes between different cities. This is how Waymo/Cruise have been able to deploy in different geographies.

Re: Waymo One doubles service area in Phoenix, continues growing in SF

#379

Post by xnx »

brewdad wrote: post #184
jeffbee wrote: post #136

Earlier quoted context omitted.

As I understand it a large component of the particulate emissions from cars is resuspended road dust, so it doesn't really matter than an EV or hybrid has little of its own brake dust. The brake dust is already on the ground.

But like CO2 emissions, the amount of brake dust available to be kicked up will decrease as more EVs take the road.

This isn't even accounting for the efficiencies of an autonomous vehicle decelerating less by better anticipating/timing stoplights. I see so many human drivers keep accelerating into a yellow/red light instead of easing off the pedal so they can resume accelerating by the time it turns green.

Re: Waymo One doubles service area in Phoenix, continues growing in SF

#380

Post by gamblor956 »

surfpel wrote: post #313
gamblor956 wrote: post #272

Earlier quoted context omitted.

Tesla's advanced-driving systems (AP and FSD) lead the world in terms of deaths. It's not even close: Tesla has more fatalities than every other advanced-driving system in the world, combined. Even massaging the data in the light most favorable for Tesla, a Tesla is still 3x more likely to be in an accident resulting in injuries than the next worst advanced-driving system, and is more than 50x more likely to be in an…

Do you have a source for these claims? > Toyota's or GM's advanced driving systems What advanced driving system? Do you mean lane assist with adaptive cruise control? That’s not even remotely comparable.

It doesn't matter what advanced driving systems you compare; Tesla is the world's worst in terms of accidents, injuries, and fatalities. For sources: NYT and WaPo both have a series of articles covering this; the NHTSA has released a report documenting over 100 Tesla advanced driving accidents.
Post reply on HN