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

Sub-$200 Lidar could reshuffle auto sensor economics

spectrum.ieee.org

Post reply on HN
Print view View original

241–250 of 582 posts

Re: Sub-$200 Lidar could reshuffle auto sensor economics

#241

Post by UltraSane »

small_model wrote: post #170
UltraSane wrote: post #127

Earlier quoted context omitted.

Your puddle example is utterly irrelevant. Tesla's are notorious for phantom breaking. Robotaxis are very much locked to tiny geofenced areas. Some even shaped like a penis because Musk is such a child. "people have driven coast to coast without a single intervention on FSD including parking spot to parking spot" I find this claim very dubious. Prove it. Teslas never drive empty for a very good reason.

Err they have lots of Model Ys in Austin as Robotaxis right now with no drivers. I guess this is also 'dubious'. Look it's clear you have a huge bias I would urge you to read up on https://grokipedia.com/page/List_of_fallacies otherwise your emotional responses will blind you to reality.

"hey have lots of Model Ys in Austin as Robotaxis right now with no drivers"

They do not. They have a very small number of them open to a select number of people, not the general public. And they are limited to even smaller areas. You need to understand that Musk is NOT an engineer, he is more of a con man desperate to inflate tesla stock price. If he says self driving cars don't need LIDAR then they must actually need it.

https://futurism.com/future-society/polymarket-fortune-betti...

Polymarket user David Bensoussan has made $36,000 by betting against Musk's wildly optimistic self driving predictions.

linking to grokipedia feels like intentional rage-baiting.

Re: Sub-$200 Lidar could reshuffle auto sensor economics

#243

Post by Rohansi »

cheema33 wrote: post #111
small_model wrote: post #56

Earlier quoted context omitted.

Waymos are still making lots of errors that a human wouldn't (Stopping in middle of a road due to a puddle was a recent one https://dmnews.co.uk/waymo-robotaxi-spotted-unable-to-cross-... ) 17 years after betting on LIDAR, I think Tesla is ahead now in most respects. It's could be wrong though we will probably know by the end of this year.

> I think Tesla is ahead now in most respects Do you actually own a Tesla? I do. With FSD. And let me assure you, you are very wrong.

How old? The 2023+ models with HW4 are pretty good at FSD. A 2021 model with HW3 was scary bad when I tried it about a year and a half ago.

Re: Sub-$200 Lidar could reshuffle auto sensor economics

#244

Post by bko »

zelphirkalt wrote: post #119

Since lidar has distance information and cameras do not, it was always a ridiculous idea by a certain company to use cameras only. Lidar using cars are going to replace at least the ones that don't make use of this obvious answer to obstacle detection challenges.

Why make things more complicated than they need to be? Humans don't have lidar and we are the only intelligence that can reliably drive. Lidar just seems like feature engineering, which has proven to be a dead end in most other AI applications (bitter lesson).

https://www.cs.utexas.edu/~eunsol/courses/data/bitter_lesson...

Re: Sub-$200 Lidar could reshuffle auto sensor economics

#245

Post by Yossarrian22 »

nlitened wrote: post #174
zelphirkalt wrote: post #119

Since lidar has distance information and cameras do not, it was always a ridiculous idea by a certain company to use cameras only. Lidar using cars are going to replace at least the ones that don't make use of this obvious answer to obstacle detection challenges.

As I understand, lidars don't work well in rain/snow/fog. So in the real world, where you have limited resources (research and production investment, people talent, AI training time and dataset breadth, power consumption) that you could redistribute between two systems (vision and lidar), but one of the systems would contradict the other in dangerous driving conditions — it's smarter to just max out vision and ignore…

When you have sensor ambiguity sounds like the perfect time to fail safely and slow to a halt unless the human takes over.

Re: Sub-$200 Lidar could reshuffle auto sensor economics

#246

Post by galangalalgol »

veltas wrote: post #202
small_model wrote: post #172

Earlier quoted context omitted.

Very recent issue with Waymo https://dmnews.co.uk/waymo-robotaxi-spotted-unable-to-cross-... . This is 17 years after they bet the farm on LIDAR, with no signs its ever going to be cost effective or that it's better than multiple cameras, with millisecond reaction 360 degrees, that never gets tired, drunk, distracted, and also has other cheaper sensors and NN trained on Billions or real world data.

Dude that's not a 'puddle' as the article claims, that's a body of water that it's not even visually obvious whether it's safe to drive through. Maybe I'm a bad driver but I'd hesitate to drive through that in a small car either.

I think the difference is the prior knwoldege a commuter has of that section of road. Does it always flood shallowly in heavy rain?

Re: Sub-$200 Lidar could reshuffle auto sensor economics

#247

Post by Phil_Latio »

radial_symmetry wrote: post #235
zelphirkalt wrote: post #119

Since lidar has distance information and cameras do not, it was always a ridiculous idea by a certain company to use cameras only. Lidar using cars are going to replace at least the ones that don't make use of this obvious answer to obstacle detection challenges.

I'm not an expert on ML vision, but I do have a Tesla and it seems to be able to tell how far away things are just fine. I'm not sure what would be wrong with the vision system that lidar needs to fix.

Yeah it's BS. Tesla uses lidar where it makes sense: They have a small lidar fleet to collect ground truth depth data for better vision estimation. This part is long solved.

Re: Sub-$200 Lidar could reshuffle auto sensor economics

#248

Post by bko »

galangalalgol wrote: post #143
zelphirkalt wrote: post #119

Since lidar has distance information and cameras do not, it was always a ridiculous idea by a certain company to use cameras only. Lidar using cars are going to replace at least the ones that don't make use of this obvious answer to obstacle detection challenges.

The reasoning is cynical but sound. If the system uses only the sensing modes people have, it will make the mistakes people do. If a jury thinks "well I could have done that either!" You win. It doesn't matter if your system has fewer accidents if some of the failure modes are different than human ones, because the jury will think "how could it not figure that out?"

Most accidents happen because people are human, aren't paying attention, are inebriated, not experienced enough drivers, or reckless.

It's not fair to say that vision based models will "make the same mistakes people do" as >99% of the mistakes people make are avoidable if these issues were addressed. And a computer can easily address all those issues

Re: Sub-$200 Lidar could reshuffle auto sensor economics

#249

Post by afavour »

bko wrote: post #244
zelphirkalt wrote: post #119

Since lidar has distance information and cameras do not, it was always a ridiculous idea by a certain company to use cameras only. Lidar using cars are going to replace at least the ones that don't make use of this obvious answer to obstacle detection challenges.

Why make things more complicated than they need to be? Humans don't have lidar and we are the only intelligence that can reliably drive. Lidar just seems like feature engineering, which has proven to be a dead end in most other AI applications (bitter lesson). https://www.cs.utexas.edu/~eunsol/courses/data/bitter_lesson...

Self driving cars are not equipped with human brains so this doesn’t really make sense.

“We should achieve self driving cars via replicating the human brain” strikes me as an incredibly inefficient and difficult way to solve the problem.

Re: Sub-$200 Lidar could reshuffle auto sensor economics

#250

Post by thunky »

bko wrote: post #244
zelphirkalt wrote: post #119

Since lidar has distance information and cameras do not, it was always a ridiculous idea by a certain company to use cameras only. Lidar using cars are going to replace at least the ones that don't make use of this obvious answer to obstacle detection challenges.

Why make things more complicated than they need to be? Humans don't have lidar and we are the only intelligence that can reliably drive. Lidar just seems like feature engineering, which has proven to be a dead end in most other AI applications (bitter lesson). https://www.cs.utexas.edu/~eunsol/courses/data/bitter_lesson...

> Why make things more complicated than they need to be? Humans don't have lidar and we are the only intelligence that can reliably drive.

Because we want self driving cars to be safer than human driven cars.

If humans had built in lidar we would use it when driving.

Post reply on HN