How the LIDAR tech GM just bought probably works • Hacker News Board

Re: How the LIDAR tech GM just bought probably works

#61

Post by rmonroe » Wed, Oct 25, 2017, 4:48 AM UTC

baybal2 wrote: post #47

dllu wrote: post #45

Earlier quoted context omitted.

I don't see how you can say millimetre wave radar "does the job many times better". State-of-the art 79 GHz automotive radar: 0.2 m range uncertainty, 5 degree azimuth angular uncertainty, dozens of points per second. Spinning lidar: Radar definitely has its uses as it can see through weather conditions and tell velocity, but lidar is the vastly superior sensor otherwise.

Looks surprisingly close to specs of a Panasonic made radar. That is far from what is currently considered advanced for mm-wave radar in 93-95ghz range - 0.5 degrees Google "GPU Acceleration of SAR/ISAR Imaging Algorithms" and see how much you can get with with regular high bandwidth 10ghz radar and computing power in tenths of gigaflops.

SAR generally relies on assumptions that your target is not changing. I question how well it would work in a complicated environment like a road scene. In my opinion, the single-shot nature of LIDAR is more robust. But its possible that SAR techniques have advanced since my work in it 3 years ago.

Re: How the LIDAR tech GM just bought probably works

#62

Post by perlpimp » Wed, Oct 25, 2017, 5:25 AM UTC

I see a number of beams going forward. I wonder what this tech can do however to avoid side collisions, number of my friends have been involved in those and those are particularly horrifying - perp running red light and ramming on the side. Schematically it can be an interesting problem to solve too.

Re: How the LIDAR tech GM just bought probably works

#63

Post by cryptonector » Wed, Oct 25, 2017, 5:41 AM UTC

taeric wrote: post #17

madengr wrote: post #3

I assume LIDAR is needed since the AI isn't advanced enough to do depth perception? If I can drive with two eye balls, then I'd think a circular camera array would be plenty. Maybe this is what Tesla plans on using (in combination with RADAR).

We don't want something that merely drives as well as a person. We want something that does better. To that end, if it is easier to build sensors that don't have to train so hard on just 2d images, why wouldn't we?

something that merely drives as well as a person

would be _awesome_ today, depending on which person we're comparing it to anyways... :)

And if in 15 years it could do much better, great.

Re: How the LIDAR tech GM just bought probably works

#64

Post by dlwdlw » Wed, Oct 25, 2017, 5:54 AM UTC

Animats wrote: post #9

Interesting. Frequency-modulated continuous-wave LIDAR is easy to do as a one-point device. Many such devices have been built. But they're usually short range, such as the discontinued Swiss Ranger, and don't reject ambient light as effectively as pulse systems. Being both eye-safe and sunlight-tolerant is hard. Eye-safe is easier if you can increase the diameter of the outgoing beam. Eye safety is measured based on…

I think more graceful failure modes would be better as well. One thing that AI systems don't seem to do a lot of nowadays is quantify their failure level. Voice assistants always reply with the same degree of sureness leading to some silly situations that wouldn't occur with a human. (Despite them having a confidence score)

It's not that better and better solutions are bad but there are probably a lot more gains in mitigating failure cases. I think our brains may even have dedicated systems for potential failure detection leading to timidness. Failure is currently mostly defined as lack of ability to get the right answer, it is negatively defined. I wonder is there's any merit in positively defining failure.

Another way to think of it is if timidness/shyness, typically "negative" traits (especially in American culture) are actually features rather than bugs.

Re: How the LIDAR tech GM just bought probably works

#65

Post by yogrish » Wed, Oct 25, 2017, 5:56 AM UTC

Animats wrote: post #9

Interesting. Frequency-modulated continuous-wave LIDAR is easy to do as a one-point device. Many such devices have been built. But they're usually short range, such as the discontinued Swiss Ranger, and don't reject ambient light as effectively as pulse systems. Being both eye-safe and sunlight-tolerant is hard. Eye-safe is easier if you can increase the diameter of the outgoing beam. Eye safety is measured based on…

COntinental Bought High flash 3D Lidar company. It seems promising to detect objects at 200mts and at very less cost compared to velodyne Lidars.

Re: How the LIDAR tech GM just bought probably works

#66

Post by burntrelish1273 » Wed, Oct 25, 2017, 6:17 AM UTC

How would this be better than / supplement 0 lux-capable machine vision? Rangefinding? Doppler shift relative velocity?

If the benefits aren't at least 3x better, it might not be marketable enough to justify the added complexities and costs.

Re: How the LIDAR tech GM just bought probably works

#67

Post by baybal2 » Wed, Oct 25, 2017, 9:33 AM UTC

deepnotderp wrote: post #48

baybal2 wrote: post #37

Earlier quoted context omitted.

Theoretical one is lower than that of lidar, but in practice a well made mm-wave radar, currently, has superior resolution to commercially available lidars

Can you point to any reasonably priced mm wave radar that has greater than lidar resolution? Genuine question.

I researched the topic further, I would say that commercial offerings for automotive use with 1Generally, to increase resolution you can do following - increase antenna size, increase number of antennas, increase amount of processing power thrown on it.

Right now, existing offerings can be improved in all 3 ways with ease.

Re: How the LIDAR tech GM just bought probably works

#68

Post by alex_duf » Wed, Oct 25, 2017, 10:03 AM UTC

Out of complete curiosity, and knowing nothing about these technologies:

How does these system avoid interference with other cars? Say if ten exact same car, with the exact same model of LIDAR are on the same street / crossing. Can I expect some noise being received by the sensor?

Re: How the LIDAR tech GM just bought probably works

#69

Post by valuearb » Wed, Oct 25, 2017, 1:37 PM UTC

melling wrote: post #7

madengr wrote: post #3

I assume LIDAR is needed since the AI isn't advanced enough to do depth perception? If I can drive with two eye balls, then I'd think a circular camera array would be plenty. Maybe this is what Tesla plans on using (in combination with RADAR).

Don't you always want a real world measurement of distance? Even if AI gets it (mostly) right, getting a second input that verifies your path is clear seems like a good idea.

not for 20% higher vehicle costs.

Re: How the LIDAR tech GM just bought probably works

#70

Post by qxamak » Wed, Oct 25, 2017, 3:44 PM UTC

alex_duf wrote: post #68

Out of complete curiosity, and knowing nothing about these technologies: How does these system avoid interference with other cars? Say if ten exact same car, with the exact same model of LIDAR are on the same street / crossing. Can I expect some noise being received by the sensor?

Yep. Every sensor will receive the output from the other emitters. This problem is actually pretty similar to the problem of sharing the wireless signal spectrum - how do all the cell phones in one area work at the same time? There's a few standard approaches to solving these problems:

- Frequency Division: each detector uses a different frequency/wavelength. This approach is very simple to implement, but the usable range of wavelengths for LIDAR is fairly narrow. So we'd run out of choices pretty quickly.

- Time Division: each detector is allocated a different operating time slot, so that only one is active at a time. For cell phones, this is relatively easy to implement because they all connect to a central system that can coordinate the timing. But for cars, this would be more difficult since there's no central system that links the detectors on different cars together (although they could still communicate with each other through other means).

- Code Division: each detector's output is pulsed in a unique pattern so that the reflected signals will return that same pattern, then the processor can reject any patterns that it didn't send out. This approach is much more complex, but doesn't suffer from many of the drawbacks of the other solutions.

Code division is by far the most widely used approach here, but frequency and time division also play a small role as well since different manufacturers/detectors use different wavelengths and not all detectors are being operated at exactly the same time (the time needed to send and receive a single signal is extremely short).