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

Tesla Robotaxi

tesla.com

Post reply on HN
Print view View original

721–730 of 788 posts

Re: Tesla Robotaxi

#721

Post by fiddlerwoaroof »

matsemann wrote: post #145
cryptoegorophy wrote: post #45

Earlier quoted context omitted.

Exactly. I wish people actually used it instead of reading biased news about it. Driving is so much stress free with it now.

Saw a Tesla swerve into the bike lane yesterday while driver was on the phone. Driver probably felt safe and that everything was in order. The cyclists not so much. Point is it's a matter of perspective. How many around you have to accommodate?

Human drivers use the bike lane, shoulder or oncoming traffic lane to drive around cars turning left and to avoid hazards all the time. It’s not unsafe if you check to make sure no one is there and my Tesla detects people around me basically as well as a human can.

On the other hand, FSD won’t try to pass me on winding mountain roads with a double yellow line.

Re: Tesla Robotaxi

#722

Post by threeseed »

e_y_ wrote: post #680
threeseed wrote: post #455

Earlier quoted context omitted.

Humans continuously move their heads in three dimensions to infer depth. Cars can't do this. And not surprisingly the biggest problem with FSD is the accuracy of its bounding boxes.

Citation? Humans are not constantly moving their heads to the degree that chickens do, and I find it doubtful that the micro movements from our head (which our eyes have to adjust for with the vestibulo-ocular reflex so things aren't blurry, similar to image stabilization in cameras) are large enough to infer depth.

I never said people are moving their heads like chickens.

But we do move our heads around pretty frequently. Enough to build mental records of what the bounding boxes are going to be for a range of objects.

Re: Tesla Robotaxi

#723

Post by bgnn »

IshKebab wrote: post #663
jauntywundrkind wrote: post #496

Earlier quoted context omitted.

Intel's L515 lidar from 2020 was Good indoor range but not really useful outdoors at any range. Scaling to higher power is indeed a challenge, but that Intel delivered so so much in 2020 for such a small price is awesome, shows potential.

Damn that looks amazing! Such a shame they abandoned RealSense. Still, $300 is not $100 and presumably they were selling at big loss, otherwise they wouldn't have shuttered RealSense.

Apple has ToF lidar for face recognition for years now. It's a matter of spec.

Similar style single chip lidar for automotive is in engineering sampling phase now [1]. Price remains to be seen but anything sub 1k would be a no-brainer to add to a robo-taxi.

Oh, everyone in the industry thinks Tesla is .. how to put it nicely .. is irrelevant for the future because of their CEOs stance on sensors. Camera will never be enough.

https://scantinel.com/2023/07/03/scantinel-photonics-launche...

Re: Tesla Robotaxi

#724

Post by bgnn »

AlotOfReading wrote: post #590
acd10j wrote: post #467

Earlier quoted context omitted.

Ok, lets think of it other way, all things equal, if you are tasked with cutting costs of vehicle without cutting back things which makes your brand unique, and without reducing margin or running on loss how will you do it? You make vehicle simpler, with less expensive parts. That's how hardware design works. Cutting back on quality or software expense is not a option for Tesla as that will make Tesla equal to any ot…

Look upthread. I would reuse an existing vehicle platform because it's cheaper at any realistic volume.

yeah, share as much as possible. anything new comes with an extra cost which needs to justify itself woth returns.

Also using old and already amortized tech is another option. Dacia mastered this art in the recent past.

Re: Tesla Robotaxi

#725

Post by iwaztomack »

AlotOfReading wrote: post #198
iwaztomack wrote: post #197

Earlier quoted context omitted.

I thought they had remote drivers to take over when shit goes south?

No, remote operators are never in control of the vehicles. They give the computer hints about how to handle situations it's unable to resolve for itself, but the computer is ultimately still responsible for driving and maintaining the safety invariants. This is fundamentally different from FSD, where the human is always responsible for driving and maintaining the safety invariants.

"They give the computer hints about how to handle situations"

That's a cute euphemism for remote operators.

Re: Tesla Robotaxi

#726

Post by dzhiurgis »

modeless wrote: post #441
nikcub wrote: post #428

Earlier quoted context omitted.

This is why I want a pragmatic operational industry expert CEO[0] for Tesla, in the same way Shotwell is for SpaceX. Announce and do the far stuff, but at the same time ship the near things that people want. A pragmatic auto CEO would have had that $25k car moving already. A pragmatic industry CEO also wouldn't have such a large event without a call-to-action. If they had a "reserve now for Feb 2025 delivery" button…

I agree that Tesla's biggest mistake was doing Cybertruck before the $25k car. But if they solve autonomy and/or succeed with Optimus then everything else becomes irrelevant.

Biggest mistake was not releasing it soon enough. 2020 would’ve been perfect for it.

Cheap car for when interest rates hit would’ve been perfect too.

Re: Tesla Robotaxi

#727

Post by dzhiurgis »

nikcub wrote: post #507
modeless wrote: post #498

Earlier quoted context omitted.

Yeah Boston Dynamics is way better at locomotion, but their advantage in manipulation is smaller. You also won't see 50 at the same time like Optimus today. Tesla's advantage will be manufacturing. Optimus has improved quickly. Gen 3 should be better. They showed Gen 3 hands today that looked pretty good.

I don't think Tesla have an advantage in manufacturing. China today is what Japan was in the 70s and their processes are so fucking good. You can't win on manufacturing - this is, after all, a nation that is now building Volvo's better than the Swedes did. Tesla fell into the China partnership trap, where the gov subsidises you and you open a "partnership" there, meanwhile they take your IP and knowledge for the bene…

NZ has cheap BYDs, etc and Tesla still vastly outsells them.

Re: Tesla Robotaxi

#728

Post by bagels »

bufferoverflow wrote: post #261
bagels wrote: post #177

Earlier quoted context omitted.

No, he said it would fly, he really did. Edit: https://x.com/elonmusk/status/1005577738332172289 SpaceX option package for new Tesla Roadster will include ~10 small rocket thrusters arranged seamlessly around car. These rocket engines dramatically improve acceleration, top speed, braking & cornering. Maybe they will even allow a Tesla to fly … "Not saying the next gen Roadster special upgrade package will definitely…

He didn't say "it would fly". He said, from your own link, "Maybe they will even allow a Tesla to fly …".

I didn't make it up. In the above quotes he definitely implied it would be capable of flying, and more recently, stated it outright.

The car doesn't exist in the first place, doesn't exist with thrusters, and doesn't exist with thrusters that make it capable of flying, and so I think it's a little early to call victory on flying Tesla roadsters.

Discussing the thrusters in 2018: "Using the config you describe, plus an electric pump to replenish air in COPV, when car power draw drops below max pack power output, makes sense. But we are going to go a lot further."

And more recently, it was very explicit: https://x.com/elonmusk/status/1801980372823187707 "The new Tesla Roadster can fly"

Re: Tesla Robotaxi

#729

Post by coolspot »

porbelm wrote: post #479
hiddencost wrote: post #394

Earlier quoted context omitted.

Waymo is doing 100k paid trips a week in 4 cities.

They also use remote drivers though.

Not in the way you’re implying. Once in a blue moon, when car is stuck on a tricky parking lot, a customer service agent can give hints to the car on how to get out.

Re: Tesla Robotaxi

#730

Post by e_y_ »

threeseed wrote: post #722
e_y_ wrote: post #680

Earlier quoted context omitted.

Citation? Humans are not constantly moving their heads to the degree that chickens do, and I find it doubtful that the micro movements from our head (which our eyes have to adjust for with the vestibulo-ocular reflex so things aren't blurry, similar to image stabilization in cameras) are large enough to infer depth.

I never said people are moving their heads like chickens. But we do move our heads around pretty frequently. Enough to build mental records of what the bounding boxes are going to be for a range of objects.

We're not doing that while driving, though.

If we're talking purely about going off memory, there's no reason why machines couldn't build up a similar catalog (which could be used by every self driving AI once learned). And human ability to judge distances varies significantly between drivers.

Post reply on HN