Hacker News Reader

Comment by dominotw | Hacker News Reader

i thought LIDAR has high cost barrier to be in consumer vehicles.

> i thought LIDAR has high cost barrier to be in consumer vehicles.

Ok, so you save a few bucks, kill a few people... then eventually come to the same conclusion every other Autonomous Driving company already has... you need LIDAR for this work reliably?

Or, you know, you get it working without LIDAR and make boatloads of money.

Humans don't rely on any sort of LIDAR to drive, I don't see how you could be so certain that computers need to.

>Humans don't rely on any sort of LIDAR to drive, I don't see how you could be so certain that computers need to.

1. using that logic we would still be trying to build airplanes with flapping wings like birds.

2. humans aren't that good of a drivers.

Humans are GREAT drivers compared to anything else out there. Especially self-driving cars.

Humans don't need LIDAR, but we rely on the massive amount of compute power available to us in our brains and a variety of other sensory inputs that go beyond simple vision. Of course, we're easily distracted, which is one reason why we aren't perfect drivers.

I really believe you can make a vision+radar only self driving car, but not without a lot of compute power. LIDAR just makes it easier. Will HW3 be enough? Probably for a lot of scenarios, but it's definitely not going to be level 4/5 anytime soon.

> I don't see how you could be so certain that computers need to

We're nowhere close to emulating what goes on in a human brain... neural networks are an absurdly simplified approximation of simple life-forms... it took the K supercomputer (having 705,024 cores and 1.4 Petabytes of RAM) 40 minutes to emulate 1 second of 1 percent of human brain activity.[1]

Since we cannot come close to sensory input processing a human can do... we need to augment our systems with better sensors. LIDAR is a better sensor, and can help "see" things that would otherwise go missed.

> you get it working without LIDAR and make boatloads of money

And why can't you make "boatloads of money" while using LIDAR? Killing people is bad for business... no?

Before you jump on it, no LIDAR is no silver bullet... but it's available technology that can help quite a bit. Why not use it? Unless you've overpromised what your price point will be for technology that is yet to exist?

[1] https://www.telegraph.co.uk/technology/10567942/Supercompute...

> "Before you jump on it, no LIDAR is no silver bullet... but it's available technology that can help quite a bit. Why not use it?"

Because Elon wanted to advertise his cars as having all the hardware necessary, because the automotive automation hype is very real. He wanted to sell luxury cars to tech enthused idealists, but he didn't want to cut down on his profit margins by actually delivering what he was selling.

The fact that he always admitted the software was lacking gave him plenty of cover. It allows his customers to continue to believe, even though their car can't actually drive itself. That's the beauty of selling hopes and dreams instead of anything concrete.

They are a bit expensive but prices have decreased rapidly over the last few years. You can get a good LIDAR for less than Tesla charges for their Autopilot. You can get consumer level ones that go out to 18 meters for around $100.

Please, show LIDAR that can create decent realtime 3D map of the environments for "around $100".

I don't know of any. But for some cases that Teslas seem to have trouble handling, like plowing into stopped white vehicles or concrete dividers[1], I think a 2D LIDAR like this one[2] would still be useful enough to have saved lives.

[1]: a la https://www.youtube.com/watch?v=6QCF8tVqM3I or https://www.youtube.com/watch?v=o02H2xGIecc

[2]: https://www.adafruit.com/product/4010

That's more or less why it's a pretty heated race to get a reliable solid state LIDAR. I think within a couple years we will have sub $2500 LIDAR units.

On top that, most LIDAR units I’ve seen have been quite bulky which would make designing a sexy looking vehicle around it near impossible. One of Tesla’s goals and main selling points is making “normal” looking cars instead of space bugs and in its present state, LIDAR integration would go against that.

Solid state LIDAR is a solution to that. Much cheaper too.

Putting form before function is almost never a good idea. If they actually got ugly Level 5 automation to work, it would sell. Period. And it would sell well enough to likely change public perception of what looks good and what looks ugly. Changes in technology causing changes in fashion is well documented.

There are many startups coming up with solidstate lidars that will be commercialized in the next two years. Teslas of today without lidars during that time will have big disadvantage compared to the competition. I am assuming Tesla will also release one with Lidar in 2020 though Elon Musk publicly say it is not needed. Like Steve Jobs he will change his statement when Tesla releases one with lidar.

It does, but the cost is coming down quickly as a result of innovation.

I wonder if solid state LiDAR would be cheaper?

Reply on news.ycombinator.com