General > General Technical Chat
TESLA FSD beta
<< < (3/3)
wraper:

--- Quote from: tom66 on November 10, 2020, 10:20:45 am ---Tesla are still using HD maps.  It needs to know lanes for turns, traffic signals etc.    The map is 'fitted' to the vision so the car can then read where cars are and what traffic signals are set to.

--- End quote ---
No it does not. There are no HD maps. Those are usual maps as in GPS navigator.
wraper:



--- Quote ---During the presentation, Karpathy shared a video of Tesla’s self-driving development software demonstration doing a turn and then Waymo’s self-driving prototype doing the same.

He highlighted how it looks exactly the same, but the decision making that is powering the maneuver is completely different:

Waymo and many others in the industry use high-definition maps. You have to first drive some car that pre-maps the environment, you have to have lidar with centimeter-level accuracy, and you are on rails. You know exactly how you are going to turn in an intersection, you know exactly which traffic lights are relevant to you, you where they are positioned and everything. We do not make these assumptions. For us, every single intersection we come up to, we see it for the first time. Everything has to be sold — just like what a human would do in the same situation.

Karpathy admits that this is a hard problem to solve.

However, the engineer explains that Tesla aims for a scalable self-driving system deployable in millions of cars on the road, and he argues that Tesla’s vision-based system is easier to scale:

Speaking of scalability, this is a much harder problem to solve, but when we do essentially solve this problem, there’s a possibility to beam this down to again millions of cars on the road. Whereas building out these lidar maps on the scale that we operate in with the sensing that it does require would be extremely expensive. And you can’t just build it, you have to maintain it and the change detection of this is extremely difficult.

The engineer described the map-based approach as a “non-scalable approach.”

He did say that Tesla also builds maps and use “all kinds of fusions between vision and the maps,” but their maps are not centimeter-level accurate and therefore, they can’t rely on them to navigate.

Tesla has to be able to handle any situation like it is seeing it for the first time.
--- End quote ---
tom66:
OK, I suppose it's a matter of terminology there, perhaps they aren't HD maps but there is vision fitting to maps at the very least.
I do believe Tesla will crack this but like all self-driving car projects it is the long tail of "what does it do in situation <X>?"
Waymo have been comparatively slow to develop the self-driving vehicles that can only navigate in Phoenix, AZ,  in mostly good weather.  (LIDAR doesn't handle heavy rain or snow well.)
wraper:

--- Quote from: tom66 on November 10, 2020, 11:13:26 pm ---OK, I suppose it's a matter of terminology there, perhaps they aren't HD maps but there is vision fitting to maps at the very least.

--- End quote ---
Maps are for navigation. But driving happens according to vision/radar (road, it's marking and and sign recognition).
wraper:
At 16:30 you can see how it drives around debris on the road. And at the other parts of the video you can see that sometimes it takes a wrong lane on intersections.

Navigation
Message Index
Previous page
There was an error while thanking
Thanking...

Go to full version
Powered by SMFPacks Advanced Attachments Uploader Mod