that seems very juicy?
edit: it seems people put a disclaimer on their ownership of tesla stock on hn about tesla threads. i dont own any.
It's cool that they can collect that data and no doubt will help refine the feature, but otherwise marketing speak. Says nothing about how accurate their algorithm is or how long it may take. There's nothing stopping them from rolling out an algo for anything and running it in "shadow mode".
If it is not turned on, they still send the inputs to autopilot, without controlling the car. I think they can also compare what the driver does against what the autopilot would have done.
They can also ask their "fleet" to match specific conditions, and collect data if they are met.
The autonomy day video showed some interesting images, for example "animals" the fleet had seen.
I think this is the video https://youtu.be/tbgtGQIygZQ
I'm just curious if it does make them way ahead, and if so how much more ahead? Is this driving a car vs horse wagon levels?
In truth there are only 3 self driving products that I know of available today. Tesla's Autopilot, GM's Supercruise (only on CT6), and commma.ai's openpilot.
Of those Autopilot is easily the best.
I never know why a source would matter in these cases as the writers of these sources usually have no idea and the answer isn't clear anyways. But if you want you can use me as a source because I'm an engineer who worked in automotive and has driven all 3 of aforementiond products. I also am not sure Waymo will ever release a feasible product other than their LIDAR.
Yup. Carmack illustrated this very well in his interviews when he would not talk about unreleased games vs. Doom/Quake/whatever. He always said: "It's really easy to be the best graphics engine when it isn't available to the public."
I suppose I used the wrong word. Any expert or well-informed opinion is what I was after.
They are also completely different approaches, i.e. Waymo using LIDAR and Tesla relying on cameras as the primary sensor.
But the major question is can LIDAR _ever_ be financially feasible, and if so can it become feasible faster than camera gets good enough at vision. Right now the sensors on the Waymo van probably cost more than the van itself.
That's either a very expensive purchase for the consumer or a very large amount of cap-ex Waymo would have to put up for a fleet of self-driving taxis.
And if it turns out cameras were the right choice, or visa versa, that means the opposite company would have spent a LOT of their R&D funding on the wrong tech, and would be way behind.
Even discounting aesthetics, Tesla couldn't have bolted it on to every car sold in the hope that it'll work in a few years time. They'd be bankrupt by now. They were forced to use cameras if they wanted any intermediate progress.
I get that there's a lot of misinformation about Tesla and you're trying to correct it. Even as a Tesla bear I acknowledge that.
But don't do it by creating further misinformation about competitors. You're just adding to the noise.
These are not levels where it makes sense to question if it will "ever" be financially viable. It's less than the premium people paid gladly for a Model S.
A true level 3 on consumer cars would sell like hotcakes.
Not only that, but by using cheap hardware that consumers can reasonably afford, they really only need to get to level 3 (eyes off so you can work/entertain but driver still in the seat) for it to be massively beneficial for everyone who commutes to work.
Waymo pretty much requires level 4 as it's too expensive to be sold as a consumer car and nobody will be in a taxi when it is driving between customers.
It's obviously got some benefits, and I think most people in ML would agree that real world data from the "average person" (as in "not a Dev or paid to do this") is worlds better than simulations.
Still, "ahead" and "behind" isn't really a thing before you reach the finish line here. Many think Tesla will never reach full self driving or won't reach it without additional sensors, others think it's possible but decades or more away, still others think it's right around the corner and can be done with what is on a Tesla right now.
Until someone reaches that finish line, we won't have anything to compare it to, so we don't have any idea how close or far anyone really is.
The last minute of video before each crash would probably be more useful. Training on dashcam data of people doing stupid stuff from Youtube might be useful. You don't need steering, braking, and accel data; you can run a 3D SLAM algorithm to extract the path and get that.
And even if they don't use the data to train, they can use it as an argument for how much better they are than humans. That's one hurdle that Waymo could have trouble with, whereas Tesla could point to tens of millions of miles where their sensors would have avoided crashes that humans failed to avoid.
edit: probably AWS [1]
[1] https://www.theinquirer.net/inquirer/news/3027077/hackers-hi...
Custom built clusters can be much cheaper than the cloud anyway.
For storage, they say they actually pull data on demand from the fleet. They have NNs that can detect similar-looking stuff to input samples, so if they want more videos of construction sites they just ask the fleet to send them more videos of construction sites. Actual storage of all video isn't required except for their test suites.
There are people much more informed than myself that believe Shadow Mode isn't real, and that Tesla is outright lying about its existence.
I don't know the extent of public statements about it, but comparing collected data like the stuff detailed there to driver behavior is certainly feasible and almost certainly being done. It's also likely true that the marketing department had their way with the announcement and made it sound more like an on-vehicle entity, but.. meh.
I just don't see how you got from that (again, really great) analysis to such an outraged conclusion.
> We'll start with the bitter truth. The "shadow driver that just sits there in the computer comparing notes and sending discrepancies and interesting events to Tesla" is a myth. I used to think people just misunderstood Elon, but now I believe Tesla lies about it on purpose
I really did not mean for my comment to be inflammatory (hence the disclaimer and including a source), but considering how quickly it was downvoted I guess people do not approve.
It is an obvious thing to do and the ‘shadowing’ aspect would not be particularly challenging tech, why the disbelief?
I consider it a very interesting thread where someone went looking for proof of shadow mode and couldn't find it. Maybe his conclusion is a little extreme, and I guess people thought I was trying to derail a Tesla thread with FUD when really I was trying to share an interesting piece and someone else's better-informed opinion (which is why I worded it the way I did). I sort of consider it similar to saying "expert A believes that..." but I guess I communicated that poorly.
For what it's worth, I'm glad people are actually looking at the source and critiquing it.
This seems to be assuming that it's something that exists entirely within the car, whereas the more sensible implementation is that the car uploads the sensor data and driver choices to a server in a datacenter somewhere and "shadow mode" happens there by running the autopilot code against the data.
That way you can continue to use the data even with newer or experimental versions of the autopilot code that didn't exist when some of the data was collected, compare different versions to see which ones do better and when, etc.
In casual talks with friends, this is something I've expected would be the competitive edge Tesla has over Waymo and the others; driving millions of "virtual miles" strikes me as far less useful than having a human baseline to compare to along with data capture from a fleet in all manner of real situations/locations.
In huge black font, then they just show the statistics of how often that happens.
It's an excellent way to prove (or disprove) the effectiveness of new safety-related features.
As for non-safety-related features, my 3-yr-old granddaughter calls my Model S the "fartmobile" because of a recent electronic whoopee-cushion easter egg.