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

531–540 of 582 posts

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

#531

Post by AlotOfReading »

dzhiurgis wrote: post #487
willio58 wrote: post #336

Earlier quoted context omitted.

Based on that list it boils down to 2 things it seems: - cost (no longer a problem) - too much code needed and it bloats the data pipelines. Does anyone have any actual evidence of this being the case? Like yes, code would be needed, but why is that innately a bad thing? Bloated data pipelines feels like another hand-wave when I think if you do it right it’s fine. As proven by Waymo. Really curious if any Tesla engin…

If Waymo proven their model works, why the silly automaker is doing several orders of magnitude more autonomous miles?

They aren't. Tesla has logged some 800k total miles with their robotaxi vehicles, including miles with safety drivers. Waymo has logged 200M driverless miles. That's 0.4% of the mileage, with the most generous possible framing.

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

#532

Post by toss1 »

wombat-man wrote: post #497
toss1 wrote: post #384

Earlier quoted context omitted.

>>Why should transportation be different? Good question, and for many it will not be, and rentals are acceptable. But also for many, renting a car has a huge ICK factor. It is one thing while traveling to rent from an agency who has (purportedly) thoroughly cleaned and inspected the car before you get it. It would be quite another to rent cars like scooters, where the previous user likely smoked, left wrappers and fo…

I think it's more comparable to Uber or Lyft. Some passengers may actually prefer to not have a driver chatting with them.

Yup, for some types of rides it's definitely better, and the not having to chat up the driver is definitely an advantage.

To take off as a real replacement for ownership, self driving cars likely needs to meet at least these criteria: 1) overall cheaper vs ownership for average mileage/year, maybe 12kmiles/yr. 2) consistent delivery of car to rider in Seems the short rides

, if they are cheaper than ownership, .

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

#533

Post by servo_sausage »

UltraSane wrote: post #484
servo_sausage wrote: post #468

Earlier quoted context omitted.

Sort of; accidents are the absolute core of the product. They are rare, but they are the focus of the design. By edge cases I mean scenarios like the lights going out in an underground garage; low vision due to colourful smoke or dust, or things like optical illusions or occlusion that a human would just need to remember. Lidar can help, but not really enough to be worth it.

Lidar is by far the most accurate source of range data. You need to explain why Waymo and Zoox use lidar in direct contradiction to what you claim.

Urban operating domain combined with legacy approaches.

If I was designing a robotaxi 10 years ago I would use lidar, designing consumer vehicles for near future L3 it's no longer the best use of resources. I prefer more compute and cameras for the money.

Our current issues are now scene understanding and navigation; followed by parking. We get very little value from LIDAR in the driving cases, so much so that we don't even use it for active nav even on cars that have it. Only for training and parking.

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

#534

Post by Mawr »

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.

> 1) it's not cheap to produce lidars at a stable predictable quality in millions;

It wasn't cheap to produce accelerometers at a stable predictable quality in millions before smart phones either. Mass production shakes things up somewhat. See the headline for reference.

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

#535

Post by leptons »

moogly wrote: post #475
leptons wrote: post #419

Earlier quoted context omitted.

One camera can't really produce depth/distance information, but two cameras sure can. The eyes in your head don't capture distance information individually, but with two eyes you can infer distance.

You're forgetting the nervous system and the brain connected to those eyes (and vestibular system).

Why would you assume I "forgot" about any of that? It's implied. That's what "infer" means in that sentence. Of course it requires a brain and nervous system. Maybe you don't know what the word "infer" means?

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

#536

Post by Mawr »

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.

> I'm not an expert on ML vision, but I do have a Tesla

Well, you did get a chuckle out of me, so that's something!

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

#537

Post by gpm »

anthonypasq wrote: post #470
kube-system wrote: post #408

Earlier quoted context omitted.

And also, even with the suite of sensors that humans have, their vision perception is frequently inadequate and leads to crashes. If vision was good enough, "SMIDSY" wouldn't be such an infamous acronym in vehicle injury cases.

the issue is clearly attention not vision when it comes to humans. if we could actually process 100% of the visual information in our field of view, then accidents would probably go down a shit load.

Attention is perhaps the limiting factor, but being able to look in two directions at once would help, and would help greatly if we had more attention capacity. E.g. anytime you change lanes you have to alternate between looking behind, beside, and in front and that greatly reduces reaction time should something unexpected happen in the direction you aren't currently looking...

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

#538

Post by rustystump »

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.

There are more practical difficulties than just cost. If you have lidar it must be calibrated relative to all other sensors. Bumps in the road, weather, thermals, this all causes drift which is non trivial. Waymos are constantly brought in and recalibrated. The advantage of camera only is you have less moving parts which is not insignificant.

But cost isnt the issue as much.

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

#539

Post by moogly »

leptons wrote: post #535
moogly wrote: post #475

Earlier quoted context omitted.

You're forgetting the nervous system and the brain connected to those eyes (and vestibular system).

Why would you assume I "forgot" about any of that? It's implied. That's what "infer" means in that sentence. Of course it requires a brain and nervous system. Maybe you don't know what the word "infer" means?

That fake indignation doesn't change the fact that you equated two cameras with two eyes, and if we're going that hard on semantics, you used the word produce for the cameras.

> One camera can't really produce depth/distance information, but two cameras sure can.

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

#540

Post by throw10920 »

kube-system wrote: post #483
anthonypasq wrote: post #470

Earlier quoted context omitted.

the issue is clearly attention not vision when it comes to humans. if we could actually process 100% of the visual information in our field of view, then accidents would probably go down a shit load.

Humans have both issues. There are many human failures which are distinctly a vision issue and not attention related, e.g. misestimation of depth/speed, obscured or obstructed vision, optical focus issues, insufficient contrast or exposure, etc.

> There are many human failures which are distinctly a vision issue and not attention related

Which are a tiny minority. The largest causes of crashes in the US are attention/cognition problems, not vision problems. Most traffic systems in western countries (probably in others, too, but I don't have personal experience), and in particular the US, are designed to limit visibility problems and do so very effectively.

Post reply on HN