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

191–200 of 582 posts

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

#191

Post by UltraSane »

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…

Waymo is the best current autonomous driving system and Waymo uses LIDAR. This is because LIDAR is an incredibly effective sensor for accurate range data. Vision and Radar range data is much less accurate and reliable.

Waymo used LIDAR in the realtime control loop. It combines LiDAR, camera, and radar data in real time to build a 3D representation of the environment, which is constantly updated.

I fundamentally don't trust any level 4 system that doesn't use LIDAR

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

#192

Post by idiotsecant »

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…

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.

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

#193

Post by throwa356262 »

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.

There are tons of evidence showing that cameras are alone are not safe enough and even Tesla has realized that removing lidar to save cost was a mistake.

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

#194

Post by idiotsecant »

Someone wrote: post #167
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.

> Since lidar has distance information and cameras do not, it was always a ridiculous idea by a certain company to use cameras only Human eyes do not have distance information, either, but derive it well enough from spatial (by ‘comparing’ inputs from 2 eyes) or temporal parallax (by ‘comparing’ inputs from one eye at different points in time) to drive cars. One can also argue that detecting absolute distance isn’t n…

Let me know when you have a camera package with human eye equivalency.

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

#195

Post by tsimionescu »

Someone wrote: post #167
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.

> Since lidar has distance information and cameras do not, it was always a ridiculous idea by a certain company to use cameras only Human eyes do not have distance information, either, but derive it well enough from spatial (by ‘comparing’ inputs from 2 eyes) or temporal parallax (by ‘comparing’ inputs from one eye at different points in time) to drive cars. One can also argue that detecting absolute distance isn’t n…

Human/animal vision uses way more than parallax to judge distances and bearings - it uses a world model that evolved over millions of years to model the environment. That's why we can get excellent 3D images from a 2D screen, and also why our depth perception can be easily tricked with objects of unexpected size. Put a human or animal in an abstract environment with no shadows and no familiar objects, and you'll see that depth perception based solely on parallax is actually very bad.

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

#196

Post by Rohansi »

cheema33 wrote: post #103
small_model wrote: post #27

Earlier quoted context omitted.

Why wouldn't you trust a Telsa, millions of people let there Tesla drive them all over USA (not geofences like Waymo) without touching the wheel from parking spot to parking spot everyday. Have you tried it?

> Why wouldn't you trust a Telsa, millions of people let there Tesla drive them all over USA (not geofences like Waymo) I own a Tesla and paid about $10K for the full self driving capability a few years ago. Yeah, I would not trust a Tesla to drive me from airport to my house. There is a reason Tesla is still stuck at level 2 autonomy certification and not 3, 4 or 5.

I would agree for most Teslas on the road. However, the very latest (HW4) cars are significantly better at FSD where I would nearly trust it now. Most of those older (pre-2023?) cars will not have their hardware upgraded so they'll still have FSD that drives like an idiot!

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

#197

Post by throwa356262 »

zelphirkalt wrote: post #178
wasmainiac wrote: post #139

Earlier quoted context omitted.

Just say Tesla, why censor yourself.

I have a suspicion here on HN. When criticizing big tech, especially Google and FB, at a certain time of the day a specific cohort comes online and downvotes. Suspiciously, that is a time when one could conclude, that now people in the US start working or come online. Either fanboys, employees or an organized group of users trying to silence big tech criticism. I have no proof of course and it might be coincidence, o…

I have seen this happening multiple times, some to fairly reasonable comments with a just tiny negative tone.

There is also flagging abuse which effectively kills the comment /post.

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

#198

Post by tsimionescu »

rfv6723 wrote: post #142
donkey_brains wrote: post #135

Earlier quoted context omitted.

Mass surveillance is a relatively recent development. Dense urban civilizations are not. And yet their denizens have not historically devolved into a “nasty, brutish, and short” existence. In fact, cities have been centers of culture and learning throughout history. How does this square with your theory?

The 19th century was the true cradle of mass surveillance. Civil registration, property tracking, and institutionalized police forces provided the systemic oversight required to manage dense urban life. These administrative tools served as the analogue version of digital monitoring to ensure every citizen remained known and categorized. Cities thrived as centers of culture only because these new forms of visibility p…

And what about all of the previous ~40-50 centuries where cities were centers of learning and art and not Hobbesian hell holes? Ur is slightly older than the 19th century, I believe.

And note that there is evidence for cities of tens of thousands of inhabitants from 3000 BCE, while Rome reached 1 000 000 residents by 1CE. Again, without becoming some Hobbesian nightmare.

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

#199

Post by macintux »

expedition32 wrote: post #171
donkey_brains wrote: post #135

Earlier quoted context omitted.

Mass surveillance is a relatively recent development. Dense urban civilizations are not. And yet their denizens have not historically devolved into a “nasty, brutish, and short” existence. In fact, cities have been centers of culture and learning throughout history. How does this square with your theory?

In my country it wasn't until the late 19th century that someone had the balls to stop going to church on Sunday. It was a huge scandal at the time but it all worked out in the end. Humans have always done mass surveillance on eachother. You don't need technology for that.

At no point in time before this era was it possible for a random bureaucrat to have a reasonably comprehensive list of everyone in a country who attended church yesterday.

Scale matters.

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

#200

Post by small_model »

RobotToaster wrote: post #188
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.

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.

Ok so Waymo is useless in the rain then, kind of limiting. But at least that 0.000000000001% times it actually is a sinkhole you won't damage the bumper.
Post reply on HN