Waymo will beat Tesla FSD because of LIDAR

[EvilNuff]

More people need to wake up and realize that vision only level 5 automation is...not...possible.

 

[BornToFly]

I truly feel Tesla will also implement some form of Lidar in combo with vision in their fully autonomous vehicles.. Vision will not work in all conditions ie rainy/snowy conditions.

My understanding is that Lidar doesn't work in heavy rainy/snowy conditions.

 

[jerhenderson]

Same thought for me initially, and now it’s in four cities and growing

4 cities. Lol. At this rate it'll be everywhere in 10 000 years.

 

[TwilightHan]

Bring back Adobe Flash!! It still is better than all of today’s technology!

 

[Curt]

Waymo cleverly overcame this limitation by transforming the LIDAR 3D point map into a more manageable format. I have not had the time to read all the research, but Waymo solved the LIDAR point map problem, where a mess of 3D dots inhibited using machine learning fully

What does this mean? Does it mean that Waymo is ready to drive anywhere and not just in pre-HD-mapped geofenced areas? When will this happen?

Your attachment states:

We have made extraordinarily exciting progress in series autonomy [Waymo’s method], but until we are able to deploy safe systems in all conditions, we will not be able to have series autonomy on public roads.

What is holding them back from deploying safe systems in all conditions? Is Waymo now able to deploy in all conditions because they have “solved the LIDAR point map problem”? If not, then when?

From page 4 of your attachment:

For this reason, we have begun to explore an alternative way to autonomy, which we call parallel autonomy [Tesla’s method]. The idea behind parallel autonomy is that the human is in control, but there is also an autonomy system that is able to check the sensors of the car and is able to run in parallel with a human, kind of like a guardian angel, looking over the shoulders of the human.

If the parallel autonomy system notices, perhaps children running on a cross street that are outside of the field of view of the human, but the autonomy system can know about it because the autonomy system can network with sensors that are installed on that piece of the road, the autonomy system can correct the maneuvers of the human to ensure that driving is safe.this adds

….And this additional information allows the parallel autonomy system to know much richer information about the state of the road than the human can get with the naked eye, and for this reason, can truly act as a guardian angel and prevents accidents from happening.

…will compute small modifications to what the human wants, but modifications that are safe in the current context.

The above sounds like the “autonomy system” in the “parallel autonomy” [Tesla’s method] is already superior to the human driver when it comes to safety. Safety is the most important factor in autonomy and Robotaxis. This is why a very small percentage of the FSD disengagements are safety related. Most are related to navigation or personal preference in speed, lane change, etc.

So, why isn’t it possible for the “autonomy system” in the “parallel autonomy” to eventually be better than the human in not only safety, but also in the way the human drives (such as for speed, lane changes, turning, comfort, etc.)? Once this happens, we don’t need the human driver. Why do you think this is going to take longer than Waymo becoming able to drive everywhere?

 

[jerhenderson]

I truly feel Tesla will also implement some form of Lidar in combo with vision in their fully autonomous vehicles.. Vision will not work in all conditions ie rainy/snowy conditions.

Then you haven't been following them at all. Tesla wants affordable cars by the millions in the road. That is not LIDAR. my eyes work in rain and snow - dunno about yours.

 

[jerhenderson]

Lol no. LIDAR only has a chance if it can be built into a car that sells for under 35k. A 100k+ car is not, cannot, will not be mass-adopted.

 

[mkstohler]

I own a Lucid GT that has Lidar. It is so much better.

 

[Amuma]

Then you haven't been following them at all. Tesla wants affordable cars by the millions in the road. That is not LIDAR. my eyes work in rain and snow - dunno about yours.

Most eyes follow the tire path of others when in extreme heavy rain and the lines are not visible. Intuition... Can't train that!

 

[jerhenderson]

I own a Lucid GT that has Lidar. It is so much better.

Lol. There's

Most eyes follow the tire path of others when in extreme heavy rain and the lines are not visible. Intuition... Can't train that!

That's very bold to think that it can't be trained. It's learning. A tire path is a guide. It'll learn. After all, you were trained.

 

[skinzy]

It's all about economics. Elon understands this. The high margin search guys don't.

 

[evnow]

I own a Lucid GT that has Lidar. It is so much better.

Wow - didn't know Lucid had door-to-door FSD !!!

 

[igs]

Tesla's Big Failure: No LIDAR

That is Tesla's big success.

Mobileye to shutter lidar development unit; will impact 100 jobs

https://www.reuters.com/technology/...lopment-unit-will-impact-100-jobs-2024-09-09/

Lidar is a fool's errand. It is doomed to fail.

 

[Speednet]

OP writes as if he has intimate knowledge of Tesla's reasoning, yet is actually ignorant of basic information already provided on the subject by Elon himself. Elon publicly stated that the main reason for eliminating LIDAR is that it creates problems when coupled with vision. When the two disagree about what they are seeing, which one do you trust? That is apparently a problem that has no solvable solution, other than eliminating LIDAR.

The other point is that the vision cameras have much better vision for the car than what you see when looking at the screen. When a camera's picture is shown on the screen, it has already gone through a great deal of computer processing to eliminate much of what the camera sees and then make the colors balanced to what we expect to see. But to the car, it sees all the photons captured by the cameras, and it can basically see in the dark and to a much better extent than what can be seen on the screen.

So the OP is basically just adding FUD here. I think I'll go with what the Tesla engineers say. After all, they're the world's best.

 

[JGTESLA]

Doesn’t have to be an either/or. Different missions call for different equipment. No need to be tribal about this. Root for success of all of these companies unless you view it as a zero sum game which it isn’t.