[fooker]

The hypothesis was that LIDAR was a crutch, humans manage with just vision.

Whether this is correct for delivering self driving cars, we will find out soon enough. Long term though, it definitely makes sense. We just don't know what the missing pieces of the puzzle are.

[seanhunter]

> humans manage with just vision

this is commonly repeated but very obviously untrue.

We don't only have vision. We have a general intelligence, coupled with vision. In the absence of AGI, the base assumption has to be the sensor apparatus needs to be significantly superior to humans for an FSD system to drive at a comparable level.

[vel0city]

Not to mention it is also untrue because we use senses other than just vision when we drive. We use our ears for acceleration information, sometimes hearing, and the feeling of the wheel when we drive.

[fooker]

We don't have anything close to LIDAR though

[seanhunter]

And a car doesn't have anything close to a human brain.

Humans process sensory data in a fundamentally different way to anything that's possible for a self-driving car. The idea that we should base the decision about the sensors on what humans have just fundamentally makes no sense.

Lidar substitutes hardware for something which humans find easy and CV systems find hard - creating a map of the environment. Humans do that by using a brain. CV systems based purely on video really struggle to do that in lots of edge cases. You can shortcut that in a car by using something like lidar.

[fooker]

You are right.

Would you agree then, that if the goal was to develop AGI, just relying on vision is a credible choice?

[seanhunter]

No. Why should the design parameters for AGI be limited by what a human can do? If the goal was AGI then I'd want all kinds of additional sensor input that humans don't have.

[fooker]

Once it's a solved problem, yes, it makes sense to think about design parameters.

When learning how to solve problems, that is not as helpful.

[Zenzero]

> humans manage with just vision.

But they don't. I can't see how anyone could look at modern driving and see an optimal state. Driving isn't being managed at all, it's killing droves of humans.

If we put the same restrictions on airplanes (flying by instrument is a crutch), everyone would rightfully find that ridiculous.

They appear to have bet on the wrong technology. The failure happened back in the design phase.

[fooker]

Aircrafts often don't have vision at all, in regular operation.

If a driver doesn't have vision, the right decision is to figure out how to safely stop.

[have_faith]

Human vision has a dynamic range of roughly ~21 stops, plus other differences, do we have any cameras that come close to the human eyes "specs"?

[fooker]

Yes.

https://www.cined.com/canon-claims-to-have-developed-a-senso...

[beaglesss]

The missing piece may be a different mode of transport like trains. Humans adapted from creatures that lived in trees over millions of years, a computer has nothing on that evolutionary process of the bad tree jumper getting eaten or breaking a leg and dying.

Spend a few million years programming a computer to swing through trees and they'll probably get something that can drive a car.

[fooker]

We have close to that much in training data in the form of cars driven by humans.

What we lack is (still) the fundamental algorithms to learn from video. Tokenization like LLMs or diffusion are starting to fall short of this goal.

[drcongo]

The missing piece is LIDAR.

[fooker]

Great, I hope I can someday be this confident about predicting the future!