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

181–190 of 582 posts

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

#181

Post by klabb3 »

estearum wrote: post #159
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?"

I don't think that's the reasoning. The reasoning was simply that LIDAR was (and incorrectly predicted to always be) significantly more expensive than cameras, and hypothetically that should be fine because, well, humans drive with only two eyes. Musk miscalculated on 1) cost reduction in LIDAR and 2) how incredible the human brain is compared to computers. Having similar sensors certainly doesn't guarantee your acci…

> Musk miscalculated on 1) cost reduction in LIDAR and 2) how incredible the human brain is compared to computers.

And, less excusable, ignorant of how incredible human eyes are compared to small sensor cameras. In particular high DR in low light, with fast motion. Every photographer knows this.

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

#182

Post by heisenbit »

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…

The Swiss cheese model would like to disagree.

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

#183

Post by RobotToaster »

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…

> lidars don't work well in rain/snow/fog.

Neither do cameras, or eyeballs.

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

#184

Post by StopDisinfo910 »

Zanfa wrote: post #117
StopDisinfo910 wrote: post #83

Earlier quoted context omitted.

1% of Meta's global revenue is a tiny-tiny cost of doing business? At that point, I think I can stop even trying to argue here. It's a massive fine any way you put it. Especially when you consider the ceiling hasn't been reached and non compliance is more and more costly by design.

It's not even 1% of their annual revenue, let alone the entire multi year period they've been in breach before and since. It's nothing to them.

The interesting part is that it keeps going up. You seem to believe we have somehow reached a cap where Meta can just expense it as a cost of doing business. That's not how European law works. The fine maximum is far higher and repeated non compliance keeps making the fines higher and higher. It's a ladder not a sizing precedent.

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

#185

Post by heisenbit »

servo_sausage wrote: post #148
UltraSane wrote: post #74

Earlier quoted context omitted.

All of the actually WORKING self driving systems use LIDAR. This is not a coincidence.

I work with programs approaching L3+ from L2, with the requirement that the system works for 99% of roads (not tesla before people start fixating on that). We find that the cases where lidar really helps are in gathering training data, parking, and if focused enough some long distance precision. None of these have been instrumental in a final product; personally I suspect that many of the cars including lidar use it…

Accidents are not normal driving situations but edge cases.

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

#186

Post by zozbot234 »

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…

Why does this matter? You have to slow down in rain/snow/fog anyway, so only having cameras available doesn't hurt you all that much. But then in clear weather lidar can only help.

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

#187

Post by idiotsecant »

small_model wrote: post #172
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?"

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.

>A vehicle got stuck trying to figure out an obstacle so sensors with less information are better than sensors with more information.

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

#188

Post by RobotToaster »

small_model wrote: post #172
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?"

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.

That's an example of it failing safe. I'd rather it did that than drive me into a sinkhole because it thought it was a puddle.

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

#189

Post by tsimionescu »

mgoetzke wrote: post #180
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.

considering cameras can create reliable enough distance measurements AND also handle all the color reception needed for legally driving roads it was always a ridiculous idea by a certain set of people that lidar is necessary.

No, cameras cannot create reliable distance measurements in real-world conditions. Parallax is not a great way to measure distance for fast, unpredictably moving objects (such as cars on the road). And dirt or misalignment can significantly reduce accuracy compared to lab conditions.

Note that humans do not rely strictly on our eyes as cameras to measure distances. There is a huge amount of inference about the world based on our internal world models that goes into vision. For example, if you put is in a false-perspective or otherwise highly artifical environment, our visual acuity goes down significantly; conversely, people with a single eye (so no parallax-based measurement ability) still have quite decent depth perception compared to what you'd naively expect. Not to mention, our eyes are kept very clean, and maintain their alignment to a very high degree of precision.

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

#190

Post by cucumber3732842 »

rfv6723 wrote: post #152
cucumber3732842 wrote: post #146

Earlier quoted context omitted.

This is a reduction to absurdity. Those old societies you cite didn't actively surveil with the goal of micromanaging people's daily lives the way that modern ones do.

Rural surveillance was far more suffocating because every single action was subject to the community gaze. This is exactly why classic literature frames the journey to the city as a liberation from the crushing weight of the village eye. The idea of the peaceful countryside is a modern utopian fantasy that ignores how ancient clans dictated every aspect of life including marriage and death. Modern Homeowners Associat…

"It was always shit everywhere" is revisionist history born out of the fantasy of statists looking to justify the modern (administrative) enforcement state.

While the lack of anonymity in small towns certainly puts a damper on one's ability to deviate too far from social norms, the list of things and subject that could get you subjected to government violence without creating a victimized party was infinity shorter. Things that get state or state deputized enforcers on your case today were matters of "yeah that's distasteful, he'll have to settle that with god" or it would come back to bite you when something happened 150+yr ago because society did not have the surplus to justify paying nearly as manny people to go around looking for deviance that could be leveraged to extract money. These people had way more practical day to day freedom to run and better their lives than we do now, if constrained by the fact that they had substantially less wealth to leverage to that effect.

> Modern Homeowners Associations prove that localized oversight is often the most intrusive form of management

And they almost exclusively deal in things that historical societies didn't even bother to regulate.

You're beyond delusional if you think running afoul of HOA is worse than running afoul of the local, state or federal government. Yeah they can screech and send you scary letter with scary numbers but they don't get the buddy treatment from courts that "real" governments do (to the great injustice of their victims) and their procedural avenues for screwing their victims on multiple axis are way more limited.

Seriously, go get in a pissing match with a municipality over just where the line for "requires permit" is and get back to me. Unless you want to do something that is more than petty cosmetic stuff and unambiguously in violation of the rules a HOA is a paper tiger for the most part (not to say that they don't suck).

Post reply on HN