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

281–290 of 582 posts

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

#281

Post by Zigurd »

RockRobotRock wrote: post #276
Zigurd wrote: post #268

Before y'all say that now everyone will be able to get Waymo's sensor suite for hundreds of dollars instead of tens of thousands, that's the easy part. Waymo benefits from Google's unparalleled geospatial data. Waymo also has a support architecture that doesn't depend on real time remote operation, which can't be implemented reliably in almost all cases. You can't be following your supposedly unsupervised cars with a…

>Waymo benefits from Google's unparalleled geospatial data. That's true, and they have a huge headstart, but I wonder if all these cubesat companies can bring the price down on data enough that others will be able to compete.

Maybe. But Google has been there in a sensor laden car, overhead with an airplane, and buying all the access that is available in satellite imagery, and fusing that together in a continually updated model. Plus real time data from a billion maps and navigation users. I pity the fool going up against that.

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

#282

Post by pinko »

btreecat wrote: post #214
bilsbie wrote: post #211

Are we sure these things aren’t damaging our eyes? It’s lasers shooting all over the place right?

When designed, built, installed and calibrated correctly, the power and wavelengths used are not considered harmful to humans.

What are the chances some non-trivial proportion of the millions of cars on the road will not have their LIDAR designed, built, installed or calibrated correctly? I suspect this is going to be a recognized public health issue in a decade or two. (It will likely be an issue well before that, but unrecognized...)

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

#283

Post by foooorsyth »

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 wouldn’t take too much issue with the “cameras are enough” claim if cameras actually performed like eyes. Human eyes have high dynamic range and continuous autofocus performance that no camera can match. They also have lids with eyelashes that can dynamically block light and assist with aperture adjustment.

The appeal to human biology and argument against fusion between disparate sensors kinda falls flat when you’re building a world model by fusing feeds from cameras all around the car. Humans don’t have 8 eyes in a 360 array around their head. What they do have is two eyes (super cameras) on ~180 degree swiveling and ~180 degree tilting gimbal. With mics attached that help sense other vehicles via road noise. And equilibrioception, vibration detection, and more all in the same system, all fused. If someone were actually building this system to drive the car, the argument based on “how did you drive here today?” gets a lot stronger. One time I had some water blocking my ear and I drove myself to the hospital to get it fixed. That was a shockingly scary drive — your hearing is doing a lot of sensing while driving that you don’t value until it’s gone.

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

#284

Post by RockRobotRock »

Zigurd wrote: post #274
nlitened wrote: post #174

Earlier quoted context omitted.

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…

No, it isn't "smarter." Camera-only driving is the product of a stubborn dogmatic boss who can't admit a fundamental error. "Just make it work" is a terrible approach to engineering.

Can hatred of Musk not derail this entire thread please? I have a camera-only ADAS that I think works quite well, but having both would be better.

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

#285

Post by devilbunny »

veltas wrote: post #252
galangalalgol wrote: post #246

Earlier quoted context omitted.

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.

If you drive the road every day, you probably do. If you can see someone drive through it (perhaps someone who knows the area well and knows how deep it is based on puddle width), you definitely do.

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

#286

Post by Ajedi32 »

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...

The bitter lesson I think is a great way of explaining the logic behind Tesla's strategy. People aren't getting it.

Whether or not it'll actually work remains to be seen, but it's a perfectly reasonable strategy. One counterargument would be that the bitter lesson can be applied to LIDAR too; you don't have to use that data for feature engineering just because it seems well suited for it.

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

#287

Post by xpe »

Analemma_ wrote: post #254
bko wrote: post #244

Earlier quoted context omitted.

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.

Yes! The smart and nuanced panoply of replies to the GP are a wonderful counterbalance to people "just saying things that pop into their head" -- which is unfortunately how I view a lot of human speech nowadays :/

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

#288

Post by Zigurd »

RockRobotRock wrote: post #284
Zigurd wrote: post #274

Earlier quoted context omitted.

No, it isn't "smarter." Camera-only driving is the product of a stubborn dogmatic boss who can't admit a fundamental error. "Just make it work" is a terrible approach to engineering.

Can hatred of Musk not derail this entire thread please? I have a camera-only ADAS that I think works quite well, but having both would be better.

Shoe, meet foot.

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

#289

Post by kevlened »

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

Given that Musk has a history of driving lower costs, it's unlikely he overestimated the long-term cost floor. He just thought we were close to self-driving in 2014.

Another factor is Andrej Karpathy, who was the primary architect for the vision-only approach. Musk wanted fewer parts, and Karpathy believed he could deliver that. Karpathy is still an advocate of vision-only.

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

#290

Post by xpe »

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 sure what would be wrong with the vision system that lidar needs to fix.

This conversational disconnect is as old as the hills:

1. Person 1 asks "what's wrong" (if it ain't broke don't fix it)

2. Person 2 wants to make something better

My meta-goal here on HN (and many places where people converse) is for people to step back and recognize the conversational context and not fall into the predictable patterns that prevent us from making sense of the world as best as we can.

Post reply on HN