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

251–260 of 582 posts

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

#251

Post by afavour »

nlitened wrote: post #230
idiotsecant wrote: post #192

Earlier quoted context omitted.

This is silly. Cameras are cheap. Have both. Sensors that sense differently in different conditions is not an exotic new problem. The kalman filter has existed for about a billion years and machine learning filters do an even better job.

Cameras are cheap, but, as I understand: 1) it's not cheap to produce lidars at a stable predictable quality in millions; 2) car driving training data sets for lidars are much scarcer (and will always be much scarcer due to cameras' higher prevalence) and at a much lower quality; 3) combined camera+lidar data sets are even scarcer.

Doesn’t that make it a sensible long term play to equip your car with $200 LIDAR and start gathering that data as a competitive advantage?

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

#252

Post by veltas »

galangalalgol wrote: post #246
veltas wrote: post #202

Earlier quoted context omitted.

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?

The amount of water will depend on the rain, so we don't know how shallow it is even with prior knowledge.

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

#253

Post by jeltz »

bko wrote: post #248
galangalalgol wrote: post #143

Earlier quoted context omitted.

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

Which means the mistakes vision-based models for today are unique to them.

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

#254

Post by Analemma_ »

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...

This knee-jerk reply is old and tired, and the counterarguments are well-trod at this point. Even if cameras-only can build a car that’s as good as humans, why should we settle for “as good as“ humans, who cause 40,000 fatalities a year in the US? If we can do better than humans with more advanced sensors, we are practically morally obligated to do that.

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

#255

Post by jeltz »

cobbzilla wrote: post #239
venusenvy47 wrote: post #222

Earlier quoted context omitted.

And also ignorant about how those two eyes have binocular vision, adjustable positions, and can look in multiple mirrors for full spatial awareness.

There are good arguments but this isn’t one. Many humans (like me!) drive fine without binocular vision. And the cars have many cameras all around, with wide angle lenses that are watching everything all the time, when a human can only focus in one direction at a time.

So your eye does not have an adjustable position and you cannot use mirrors?

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

#256

Post by elicash »

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...

Don't cars already use a ton of sensors that don't reproduce human senses and ways of doing things?

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

#257

Post by bob1029 »

plasticchris wrote: post #231
dsr_ wrote: post #221

Earlier quoted context omitted.

When it's not safe to drive, it's not safe to drive. I've been in zero-road-speed whiteout conditions several times. The only move to make is to the side of the road without getting stuck, and turning on your flashers. Low-light cameras would not have worked. Sonar would not have worked. Infrared would not have worked.

Radar might still have worked

https://en.wikipedia.org/wiki/L_band

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

#258

Post by theappsecguy »

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…

Do cameras work well in those conditions? Nope. Also cameras don't work well with certain answer of glare, so as a consumer I'd rather have something over-engineered for my safety to cover all edge cases...

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

#259

Post by jeltz »

afavour wrote: post #251
nlitened wrote: post #230

Earlier quoted context omitted.

Cameras are cheap, but, as I understand: 1) it's not cheap to produce lidars at a stable predictable quality in millions; 2) car driving training data sets for lidars are much scarcer (and will always be much scarcer due to cameras' higher prevalence) and at a much lower quality; 3) combined camera+lidar data sets are even scarcer.

Doesn’t that make it a sensible long term play to equip your car with $200 LIDAR and start gathering that data as a competitive advantage?

Yeah, this is all about Musk not wanting to admit he was wrong.

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

#260

Post by ubercore »

jeltz wrote: post #207
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.

Tesla does not handle rain well either. This is not a LIDAR problem, it is a problem with self driving cars in general.

My Tesla can't even tell if it should turn the wipers on consistently or correctly. Let alone drive in the rain.
Post reply on HN