[syntaxing]

Interesting because to me, LIDAR is an absolute necessity. Startups use cameras (+ radar) only because it's technically and financially "easier" than other technology. I don't know of any company with Level 3 and above self driving capabilities not using LIDAR (though I would love to be proved wrong because that would be awesome to see)

[ModernMech]

In the long run, binocular cameras should be enough. We are an existence proof of that. But that requires human-level cognition and inference, which is not something that's even on the horizon. Until then, LIDAR will be a key technology.

[xoa]

>In the long run, binocular cameras should be enough.

No they won't. They have all the issues that pure visible light sensors fundamentally have in Earth weather and lighting conditions. There hasn't been much choice for human drivers obviously (though in principle there we could have pushed for better HUD ages ago, and could still make use of AR), but with the switch to computers we can and should do better. It is foolish not to make use of better data input.

>We are an existence proof of that.

Proof of what? Millions of deaths and casualties every single year due to driving? We tolerate it because the benefits are even bigger, and there aren't any other options. It is literally worth mass suffering and death, not to mention economic expense, to gain arbitrary point-to-point mechanized transportation. But that acceptance is purely a relative matter because there is nothing better, as with medical technology standards can and will change once we can improve. There is no reason that self driving cars shouldn't generally be able to see animals (deer, moose etc) in a pitch black night in the fog for example and keep from running into them. Yeah that'd be impossible for us, but that's not a law of physics just a limitation of information input limited purely to the visual spectrum. Using humans as a standard is really foolish given how objectively terrible we are at this.

[ModernMech]

> Using humans as a standard is really foolish given how objectively terrible we are at this.

Yeah, it would be foolish to use my grandmother as a benchmark for driverless cars. Humanity would experience a net increase in safety if she were to take a driverless car to church.

But even the best driverless car today with all their LIDARs can't outperform my father, a 40 year veteran of UPS with literally millions of accident free miles under his belt in every driving condition imaginable - rain, sleet, snow, fog, bright sun. All with binocular cameras, and a finely tuned driving ethic. If I presented UPS with a fleet of similarly capable driverless trucks, I would be a billionaire, and the world would be net-safer.

[mrep]

US car fatalities are at 1.16 per 100 million miles in 2017 [0]. Anecdotal evidence for accidents based on multiple orders of magnitude less miles doesn't say much (fatalities was the first data i could find) [1].

[0]: https://en.wikipedia.org/wiki/Motor_vehicle_fatality_rate_in...

[1]: 20 mph average driving rate (guess on my part but they stop a lot) * 8 hours a day * 5 days week * 50 weeks a year * 40 years = 1.6 million miles

[ModernMech]

Anecdotal evidence shows that's it's possible. It shows under the right condition with the right controller, it's possible to go millions of miles without making a single mistake for a human with binocular camera sensors.

Over all human drivers we don't get that result, of course. But how many were following too closely? How many were distracted? How many were sleepy? How many were intoxicated? How many were going too fast? How many were old? How many have a slow reaction time? How many weren't wearing their glasses? All of the above factors have nothing to do with the sensory input to the controller, but are indictments of the individual controllers themselves.

Some human controllers are better than others. Some people hit parked cars. Some people go millions of miles without hitting anything. They both have binocular input sensors. If we equip a car with binocular cameras, that doesn't mean we will have the same result as humans in aggregate. Computers will never get drunk. Computers will never be distracted. In the limit, where we have the right cognition, I believe we won't need LIDAR to achieve better aggregate results than the ones you quoted. It would be as if everyone drove like my father, rather than grandmother.

What do you think the fatality rate over all of UPS, Fedex, and USPS are? Some quick Googling shows that UPS alone logs over 3 billion miles per year for their fleet, with only 25 deaths per year. That's 0.8 deaths per 100 million miles. So we can see with proper training, a human controller can be 100% more effective at preventing death than the general population. And the question still remains -- why were those deaths caused? Were they due to being limited to binocular cameras? Or were they something we could program away like being distracted or driving drunk? Or maybe some were unavoidable under any circumstance? I don't know, but it definitely shows me that this idea that humans are de facto terrible at driving and therefore binocular sensors are not enough for driverless cars (again in the long run) is questionable.

[bobsil1]

- Lidar and visible light both use EM radiation, just different wavelengths, coherence and active v. passive

- Passive sensors have huge range, power and deconfliction advantages

- The better system is passive sensors in superhuman wavelengths

- Even Levandowski's come around to Elon's POV on unnecessary lidar

[raisedbyninjas]

Even when cameras are "enough" LIDAR will still provide additional data not obtainable through cameras, allowing even safer driving. If humans had evolved biological LIDAR we would use it while driving.

[Klathmon]

I may be mis-remembering, but wasn't an argument from Tesla that LIDAR would actually be a disadvantage?

LIDAR has a lot more "false positives" if I remember correctly, and a lot of the work is going toward filtering LIDAR data and cleaning it up in cars that use it. I could see not wanting to spend the time and effort in trying to tame something like that when they have something working pretty well right now with different kinds of sensors.

[shaklee3]

I think at this stage, nobody is certain. But I tend to side with more information is better, and you filter what you don't need. Same reason sensor fusion algorithms use the gyroscope and accelerometer in concert to measure movement.

[sliken]

Dunno, seems like Lidar often results in seeing plastic bags or tumbleweeds as car killing objects.

[shaklee3]

Yes, but that's what I was getting at. You filter those out from the camera. The reverse is probably true as well, where you need depth since an image can't give you enough information.

[InitialLastName]

> In the long run, binocular cameras should be enough. We are an existence proof of that.

Americans kill 40,000 people a year driving with their insufficient binocular vision. It's obviously not enough.

[ModernMech]

Insufficient binocular vision isn't always the cause though. Not all human controllers are equally capable. There is a such thing as the best driver in the world and the worst driver in the world. For example, my father worked as a driver for UPS for 40 years. He drove literally millions of miles in every condition imaginable and never got into an accident. Not a single fender bender. My sister on the other hand has been driving for a decade and has been in dozens. They have the same sensory input but vastly different performance. I would definitely buy a driverless car that performs like my father. If I could build one like that, I would be a billionaire. Not so much with one that performs like my sister.

[erikpukinskis]

Human eyes take in data that's not available to a camera. Fo example we can detect a single photon. We can also change the lens shape of the eye. And the brain uses more than just eyes to drive. We use our ears for example, and our vestibular system. And there are even parts of our body at work that don't talk to the brain... Our brainstem certainly handles many aspects of driving without talking to the eyes. So I wouldn't say there's an existence proof there.

[albertgoeswoof]

Self driving cars need to be safer and faster than human driven cars, otherwise it will be cheaper to keep humans in the driving seat.

[mrep]

You are ignoring the cost of human labor which in the US is minimum $7.25 an hour which is why waymo is targeting taxis as they don't have to pay those human labor costs if they can get rid of the drivers.