Live data from Hacker News

Sub-$200 Lidar could reshuffle auto sensor economics

spectrum.ieee.org

351–360 of 582 posts

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

#351
I never understood why Tesla HAD to get rid of the Lidars. Expensive today sure, but can you imagine all that training data they missed out on? Technology has a way of becoming cheaper and cheaper. It seemed short sighted, even if at a loss, again, the training data.

If the pros of having a camera are monumental, then couldn't the video and lidar be combined to be even greater?

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

#352
post #6

Oh hell yeah, we can finally stop the braindead attempts to make a safe self-driving car with just cameras.

Tesla actually re-introduced radar sensors in HW4. https://www.teslarati.com/tesla-hardware-4-hd-radar-first-lo... They might not use them for autopilot, but maybe for some emergency braking stuff, when everything else failed.

I wouldn't be surprised if this was a better solution. I think while radar might have a worse spatial resolution, it's depth perception, speed measurement capability, and general robustness to adverse weather might make it a better complementary sensor.

Lidar struggles with things like rain and snow way worse than cameras do.

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

#353
post #349
post #306

Earlier quoted context omitted.

I’m not disagreeing with what you’re saying, but does Alphabet actually intend Waymo to be a trillion dollar retail car business itself, selling cars to everyone? Or would they be happy to sell all those super cool things to OEMs? In a world where “everyone” can make a car affordable that can run Waymo’s software, they may be happy to license all that to “everyone” and simply collect fat royalty checks, à la Microsof…

In a saner world Teslas would be running Waymo's self-driving stack instead of the half-baked "might kill you at any time" not quite-FSD.

They are not the same. I don't think Tesla or its consumers are interested in geofenced self driving, they want to be able to use it on road trips and driving around suburbs.

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

#355
post #306
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…

I’m not disagreeing with what you’re saying, but does Alphabet actually intend Waymo to be a trillion dollar retail car business itself, selling cars to everyone? Or would they be happy to sell all those super cool things to OEMs? In a world where “everyone” can make a car affordable that can run Waymo’s software, they may be happy to license all that to “everyone” and simply collect fat royalty checks, à la Microsof…

Why sell cars to everyone?

People on here used to buy servers themselves (very few of us still do), most now rent via cloud.

Why should transportation be different?

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

#356

Earlier quoted context omitted.

I'd rather a Waymo be useless in the rain rather than a Tesla be actively dangerous and likely to kill me. Tesla ""autopilot"" fatalities: 65 Waymo fatalities: 0

> Waymo fatalities: 0 By some measures Waymo is actually at -1 fatalities. There has been one confirmed birth of a child in a Waymo. https://apnews.com/article/baby-born-waymo-san-francisco-6bd...

I think the car would have to be more actively involved in the process for that to count. :)

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

#357
post #349

Earlier quoted context omitted.

In a saner world Teslas would be running Waymo's self-driving stack instead of the half-baked "might kill you at any time" not quite-FSD.

They are not the same. I don't think Tesla or its consumers are interested in geofenced self driving, they want to be able to use it on road trips and driving around suburbs.

I think that was implied in my comment: that Tesla would use Waymo's stack for free navigation and self-driving, instead of not quite-FSD.

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

#358

I never understood why Tesla HAD to get rid of the Lidars. Expensive today sure, but can you imagine all that training data they missed out on? Technology has a way of becoming cheaper and cheaper. It seemed short sighted, even if at a loss, again, the training data. If the pros of having a camera are monumental, then couldn't the video and lidar be combined to be even greater?

Because Tesla Clown-in-Chief asked if humans could drive with just visual input, why can't a Tesla? C-in-C conveniently ignored that, to begin with, humans have binocular vision, and his cars had none. Also conveniently ignored were the facts that human eyes have immense dynamic range, are self-cleaning, and can move to track objects of interest. On top of this, humans also have hearing, which helps gauge danger. Many of these things could be filled in by Lidar but since C-in-C apparently had a revelation from heaven, possibly caused by drugs, lidar had to go.

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

#359
post #354

I still believe in Cameras. I have a comma.ai 3x and it works really well. Just get a thermal camera to deal with fog etc. Waymo has some of the same limitations with cameras that Comma and Tesla does.

There's no reason to believe in just cameras. Cameras are easily blinded by glare and have their efficacy drop dramatically when they get dirty. Having inexpensive lidar AND cameras is the best of both worlds. When it comes to safety and comfort, we shouldn't be trying to optimize for cost. If we figure out how to make cameras alone bulletproof in the future, great. But there's not where we're at today.

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

#360
post #354

I still believe in Cameras. I have a comma.ai 3x and it works really well. Just get a thermal camera to deal with fog etc. Waymo has some of the same limitations with cameras that Comma and Tesla does.

I think that supports most people’s viewpoint though. Visible light Cameras alone can ‘work’ but more sensors is of course better. You infrared example for instance.

The only reason not to have more sensors of different types is cost (equipment and processing costs). Those costs are coming down fast.

Post reply on HN