How Waymo outlasted the competition and made robo-taxis a real business • Hacker News Board

Re: How Waymo outlasted the competition and made robo-taxis a real business

#311

Post by 1024core » Thu, May 30, 2024, 5:11 PM UTC

leesec wrote: post #266

zellyn wrote: post #107

This seems silly. It’s been obvious even to casual observers like myself for years that Waymo/Google was one of the only groups taking the problem seriously and trying to actually solve it, as opposed to pretending you could add self-driving with just cameras in an over-the-air update (Tesla), or trying to move fast and break things (Uber), or pretending you could gradually improve lane-keeping all the way into auton…

Lol Tesla has made significant progress and doesn't show much sign of slowing down. There's no reason to think there approach can't work at this point. People go weeks without intervention.

You mean, like this? https://www.nbcnews.com/video/video-shows-moment-tesla-nearl...

Re: How Waymo outlasted the competition and made robo-taxis a real business

#312

Post by codexb » Thu, May 30, 2024, 5:12 PM UTC

bigfudge wrote: post #90

codexb wrote: post #55

Earlier quoted context omitted.

Maybe if you're under 25 and have always lived in a dense city this seems like a valid take. Taxis aren't new, they have always existed. Just because they're driven by computers now isn't going to magically change all the reasons that people didn't use them before (hint: it wasn't because they were driven by humans). No one with kids wants to ride in taxis with kids all the time. Ditto for anyone with hobbies that re…

I think you’re wrong about most of the scenarios on your list. And once the market is mature, I can imagine it would be great to be picked up in a minivan after a days cycling somewhere new and not on a loop route. Americans have become emotionally attached to cars because of what they enable them to do. That might take a while to die. But in Europe cars are more of a pita to own and run because we have less space. I…

Yeah, Americans just have more space, and America is just far larger, and Americans often do relatively long road trips to places where other modes of transportation are not possible or prohibitively expensive. I don't think that is ever going to die, nor should it.

Re: How Waymo outlasted the competition and made robo-taxis a real business

#313

Post by jefftk » Thu, May 30, 2024, 5:14 PM UTC

jvanderbot wrote: post #274

shkkmo wrote: post #260

Earlier quoted context omitted.

That 'level 3' is still basically lane keeping and auto cruise control, the driver still has to be ready to immediately takeover, if you don't the car will stop in it's current lane with it's blinkers on. This is about the peak of what you can get with automated lane keeping and braking. I don't see any route from this point to anything like level 4.

> level 3 is still basically ... well yeah, that is the definition of level 3. That's not going to change. They are limited by: > Our technology relies on a digital high-definition map that provides a 3D image of the road and the surroundings with information on road geometry, route characteristics, traffic signs and special traffic events IMHO Tesla's "F--- it all just use NN" approach does get around the pre-genera…

> it is not much more than Level 3.5 at the moment

It's not even level 3, and couldn't be certified as such. It's not reliable enough for the person in the driver's seat to focus their full attention elsewhere.

>> level 3 is still basically lane keeping and auto cruise control

> well yeah, that is the definition of level 3

No, it's the definition of level 2: https://www.sae.org/blog/sae-j3016-update ("example features: lane centering and adaptive cruise control at the same time")

Re: How Waymo outlasted the competition and made robo-taxis a real business

#314

Post by denimnerd42 » Thu, May 30, 2024, 5:23 PM UTC

zellyn wrote: post #107

This seems silly. It’s been obvious even to casual observers like myself for years that Waymo/Google was one of the only groups taking the problem seriously and trying to actually solve it, as opposed to pretending you could add self-driving with just cameras in an over-the-air update (Tesla), or trying to move fast and break things (Uber), or pretending you could gradually improve lane-keeping all the way into auton…

I've put tens of thousands of miles on a comma.ai. it's just hands free lane keep assist. it solves my hand/shoulder fatigue issues over long drives. it's not autonomous driving and doesn't pretend to be.

if you want to drive across the ultra straight highway flyover states it's game changing. if you don't do that, it's not that useful.

Re: How Waymo outlasted the competition and made robo-taxis a real business

#315

Post by m348e912 » Thu, May 30, 2024, 5:24 PM UTC

zellyn wrote: post #107

This seems silly. It’s been obvious even to casual observers like myself for years that Waymo/Google was one of the only groups taking the problem seriously and trying to actually solve it, as opposed to pretending you could add self-driving with just cameras in an over-the-air update (Tesla), or trying to move fast and break things (Uber), or pretending you could gradually improve lane-keeping all the way into auton…

>pretending you could add self-driving with just cameras in an over-the-air update (Tesla)

I have watched enough recent Tesla self-driving ride along videos on YouTube to suspect you might be mistaken on this point. Tesla intends to launch a cybertaxi fleet and their software looks like it will be good enough to get them there without lidar or additional sensors.

Re: How Waymo outlasted the competition and made robo-taxis a real business

#316

Post by grecy » Thu, May 30, 2024, 5:29 PM UTC

tialaramex wrote: post #237

flutas wrote: post #225

Earlier quoted context omitted.

> Most importantly: at no point does someone remotely "drive" the vehicle. They can direct it to say "hey make a u-turn and go to this new point", but they aren't remotely driving. This doesn't line up with other statements made by Waymo though. That blog post as an example: > The Waymo Driver does not rely solely on the inputs it receives from the fleet response agent and it is in control of the vehicle at all times…

Judging from the red light incident, the Waymo Driver does not consider passing a red light to be a Never event, in the same way that say, hitting a pedestrian would be a Never event. So it's OK with being advised by a human that it needn't obey the red light whereas it wouldn't be OK with being told to just drive through cyclists. That makes a kind of sense, a human shouldn't need to run red lights but they do it mo…

I've done it to get out the way of an emergency vehicle coming up behind me with full lights and sirens. It was kind of fun.

Re: How Waymo outlasted the competition and made robo-taxis a real business

#317

Post by jvanderbot » Thu, May 30, 2024, 5:29 PM UTC

jefftk wrote: post #313

jvanderbot wrote: post #274

Earlier quoted context omitted.

> level 3 is still basically ... well yeah, that is the definition of level 3. That's not going to change. They are limited by: > Our technology relies on a digital high-definition map that provides a 3D image of the road and the surroundings with information on road geometry, route characteristics, traffic signs and special traffic events IMHO Tesla's "F--- it all just use NN" approach does get around the pre-genera…

> it is not much more than Level 3.5 at the moment It's not even level 3 , and couldn't be certified as such. It's not reliable enough for the person in the driver's seat to focus their full attention elsewhere. >> level 3 is still basically lane keeping and auto cruise control > well yeah, that is the definition of level 3 No, it's the definition of level 2: https://www.sae.org/blog/sae-j3016-update ("example featur…

I mean, that's very official looking. And the differentiating criteria for level 3 is "You must take over when asked" and everything 2 or below is "You must brake, steer, or accelerate as needed to ensure safety".

Am I missing something? Lane keeping, cruise control and offset keeping is level 3. That's what this feature offers according to a few posts up.

It makes no difference to the conversation. I'll stop poking the bear here.

Re: How Waymo outlasted the competition and made robo-taxis a real business

#318

Post by maxdo » Thu, May 30, 2024, 5:30 PM UTC

marcusverus wrote: post #232

a_c_s wrote: post #218

Earlier quoted context omitted.

Tesla is still years behind Waymo: "FSD 12.3 seems superior to Waymo’s technology circa 2018, it’s not as good as Waymo’s technology at the end of 2020" https://arstechnica.com/cars/2024/05/on-self-driving-waymo-i...

The author's opinion is based on one intervention from one trip: > "The version of FSD I tried in March [of 2024] was clearly not ready for driverless operation. For example, I had to intervene to prevent the Model X from running over a plastic lane divider, a mistake Waymo would not have made in 2020. So while FSD 12.3 seems superior to Waymo’s technology circa 2018, it’s not as good as Waymo’s technology at the end…

I'm using FSD every day in NYC. It is one of the hardest environments in the world.

99% of interventions I had were from a driver's experience perspective, not the actual safety.

It's still far away from 99.999 that you would expect.

Re: How Waymo outlasted the competition and made robo-taxis a real business

#319

Post by E39M5S62 » Thu, May 30, 2024, 5:31 PM UTC

m348e912 wrote: post #315

zellyn wrote: post #107

This seems silly. It’s been obvious even to casual observers like myself for years that Waymo/Google was one of the only groups taking the problem seriously and trying to actually solve it, as opposed to pretending you could add self-driving with just cameras in an over-the-air update (Tesla), or trying to move fast and break things (Uber), or pretending you could gradually improve lane-keeping all the way into auton…

>pretending you could add self-driving with just cameras in an over-the-air update (Tesla) I have watched enough recent Tesla self-driving ride along videos on YouTube to suspect you might be mistaken on this point. Tesla intends to launch a cybertaxi fleet and their software looks like it will be good enough to get them there without lidar or additional sensors.

Tesla 'intends' to do a lot of things, but rarely seems to be able to actually DO them.

Re: How Waymo outlasted the competition and made robo-taxis a real business

#320

Post by maxdo » Thu, May 30, 2024, 5:34 PM UTC

swsieber wrote: post #235

marcusverus wrote: post #232

Earlier quoted context omitted.

The author's opinion is based on one intervention from one trip: > "The version of FSD I tried in March [of 2024] was clearly not ready for driverless operation. For example, I had to intervene to prevent the Model X from running over a plastic lane divider, a mistake Waymo would not have made in 2020. So while FSD 12.3 seems superior to Waymo’s technology circa 2018, it’s not as good as Waymo’s technology at the end…

While true, if you go to page 1 of the article you find this: > During a 45-minute test drive in a Tesla Model X, I had to intervene twice to correct mistakes by the FSD software. In contrast, I rode in driverless Waymo vehicles for more than two hours and didn’t notice a single mistake. That seems pretty significant.

While Waymo is only trying to enable itself on 1-2 particular highways in western America, Tesla's FSD can work hours with no interventions on the highways, do exits, and automate pretty much the entire trip on a highway in any place in the US, Canada, and China.

Again, it's just different approaches to solve the problem.