Lidar vs. Tesla: the race for fully self driving cars

How ”self–driving” do you want your self-driving car to be?

Hey guys i have a prjoect where i have to come come up with a way to stop damages due to close reflective objects cuasing the incoming pulse to damage the system. Tbh i didn't even know this stuff existed till a few days ago, im in second year of electronics..any suggestions??

LiDAR schmidar…. The car could literally be fully aware of every atom within 100 miles. The real problem is real-time adaptive reasoning. Human soft gray matter fuckn rules in that department.

when you talk about how many people hurt using lidar while providing the miles, you should as well compare it to tesla while providing the miles, to make them on a comparable scale

i dont understand whats wrong on "laser is the sause"

Self driving cars would be a God send to those who do not drive.

now they renoved USS

Lidar doesn't even work in heavy rain. So all companies that trust on lidar must have a 100 % working redundant camera system if they want their cars to drive autonomous in all weather conditions. Why should anyone develop two separate systems if only one of them is capable of mastering all situations? For me Lidar is only a historical intermediate step, due to the lack of skill in processing 2d camera data to 3d data. Humans only have a visual sense as well. And humans never make accidents because we lack a lidar sense. We make accidents because we overestimate ourself (driving-skills, alcohol, drugs etc.) or we get distracted. Both will not happen to computers. Since FSD Beta 11.4 it's not about what sensors anymore, but about how much data the AI ​​has to be fed to drive better and safer than human.

Arguing one tech over the other is responsible. It likely to be mix of the two.
Also, there is a thing called "solid state lidar", much cheaper.

3D Lidar = capture depth info
2D Cameras = interpretations i.e. require AI guessing

Lidar, radar, and cameras. All are needed to have safe fsd, it wont be cheap though

With the release of Tesla's v14 neural net suite that learns from driving footage without the need to code in maps and specific instructions, Tesla is now arguably closest to a computer driving like a human does, but without the human error that causes most accidents. Lidar seems overkill when we are literally a living example of how driving is accomplished with just images and neural networks.

Wow I stopped watching after I realized how biased this was
Try taking a waymo car and a Tesla to a place neither has ever driven on before
Get back to me with the results
We already lnow

I believe in lidar

So, no consensus what tech is best for FSD, still we expecting LVL 5 anytime soon

Absolutely disagree with this analysis. Pure rubbish. Tesla is building one of the most powerful computers on the planet to power FSD so you'll have the fusion of data from millions of cars being combined with known map data. Tesla will not need to create the huge point maps to know where things are located and what they are. It will do that with a fraction of the data. The idea that you need a certain type of light to see something (in this case LASER light) is silliness.

😍

Does LiDAR outperform camera data in adverse conditions? That would be the #1 question to me. I thought that it did, but I read otherwise.

It's ironic that Google was and still likely is the leader in image recognition and yet still saw the need for sensor redundancy to reach necessary confidence levels for safe driverless operation. With Tesla FSD, we still see lots of issues with the perception. We often see it initially misplace objects in the world or identify objects which aren't there. If you watch FSD videos closely, you'll often see phantom road cones appear, suggesting Tesla is setting its confidence thresholds low in order to not miss things, but at the expense of occasionally seeing things that don't exist. You can also see it get fooled by reflections, sometimes showing cars driving inside buildings that have reflective windows.

Either you don't really understand Tesla's FSD or youre being economical with the truth. Ive also noticed your other video on why DJI is not innovative. Your takes are mostly midwit or biased understanding

Self driving cars will not be the cure for climate change.
We need to get away from car culture and eliminate private car ownership.
Micro-mobility and public transportation are what we need.
Not gimmicks to make car makers rich.