Search results

Which makes my point. If you set your expectations on random stuff you see on YouTube (and Chris seems to be going down the "click bait" route more and more these days) then of course you are going to be disappointed. The point is the OP was implying that FSD beta should have been better than...

If by "available" you mean that the car can be added to the beta, then you are correct. If you mean that anyone with qualifying hardware/cars will get the beta, then no, you are not correct.

No, that's not the point. Your post was about disappointment at the beta not behaving the way you wanted/expected it to. But what was your expectation based on? Certainly not Elon's wildly optimistic posts; who pays attention to those apart from the SEC? And, as you note, not by reading the...

Again, this is meaningless. "number of sensors plus sensor performance"??? hmm sounds like "Mine goes to 11" to me. And no, I'm NOT defending Tesla, I'm merely noting that nothing useful or meaningful can be deduced from that chart.

hmmm .. so probably have no meaning whatsoever .. the x-asis could be cost, number of sensors .. who knows what? Is the y-axis based on NN, CPU or GPU performance, or some undefined blend of each?

What was the numerical basis for both axes of this graph?

How are you doing that?

Yeah it's always done that. Wait till you get into a tight spot and the car folds the wing mirrors so it can fit through the gap!

H He/she/it just walks out into the road .. cars stop in amazement .. Chuck turns left.

The version number. Also, you will see "FSD Beta" in the version information on the Software screen. And, of course, you will get the extra FSD Beta toggles and controls in the Autopilot screen.

Agreed, but none of the things he listed haven't been discussed here a lot before, so its a bit odd he was expecting something else. Perhaps watched too many Whole Mars Catalog drives on YouTube.

It used to be an email than an update, but I think now they just push the update.

So why did you get on the beta?

If something like a curb is obscured by objects (cars etc) then I'm not sure what any sensor is supposed to do ... they are all going to be blinded. At that point you are relying on the NN being able to extrapolate the curb from the bits it can see (which it can do) and/or handle the object...

Phantom braking.

I would be interested in your comments contrasting this position to the PB issues, since the two are closely related... As fro DARPA .. there is always this (to add a little humor to the debate)...

I'm sure lidar is very helpful to Waymo, and in fact I'm sure, right now, they can't do without it. As I noted elsewhere, Waymo started out long enough ago that a pure vision approach was never going to fly as the raw processing power way not then available at a viable price point. The result, I...

When you learn to ride a bike you start with training wheels to stop you falling over .. but later you need to discard them as they ultimately are a hinderance to riding. That's I think basically what he means.

I didn't say it wasn't helpful, I said deriving accurate object estimations purely from point clouds is very hard (JPDAF has all sorts issues with merging, and was developed with other applications in mind where merging wasn't considered a problem). With a camera, you can train an NN to notice...

Very expensive very high-resolution ones connected to boatloads of computing power.

How do you determine what constitutes an "object" from the cloud of points data ? How do you determine the continuity of that object across time (frame to frame)? How do you determine the world-space velocity of an object, once you have identified it? How do you handle object intersections? Or...

Again, you are making unproven claims. Sure, we need high reliability (which is different from precision btw) though I'm not sure your 99.99999% has any meaning. You keep saying, again and again, that lidar/radar can do xxx, but based on what? You CANNOT point to Waymo, because they use HD maps...

This is a massively different problem. In your example all the system is doing is computing the approach velocity, and yes you can get this (more or less) directly from various measurements (doppler shift or frame-by-frame distance deltas). But computing the lateral velocity of an object is a...

Read my other posts .. basically I think some people here are claiming lidar magically solves all sorts of problems, skipping over bits that re actually much harder to solve.

No, you can't. Or at least not directly. You CAN, with a LOT of NN smarts, deduce the outline of an "object", but that itself is a hard problem. Once you have done that you have a direct velocity measurement only along the axis from the object to the sensor. If you want "true" velocity (that is...

I'm confused by this .. what do you think the raw output of lidar looks like? Or radar? There seems to be an assumption here that these sensors somehow provide all the data the car needs to determine the existence of, and the motion of objects?

But this is my point ... everyone is treating lidar and radar as "magical solutions". Can't get accurate motion? Add lidar/radar! Can't estimate xxx? Add lidar/radar!! Tooth decay? Try Cream Toothpaste now with Lidar protection! Are you so sure that lidar/radar could indeed handle those issues...

So Waymo could turn off HD maps and geofencing and everything would work just fine?

No, I'm arguing that when people say "Tesla should have used xxx" such as radar/lidar, they have no factual basis for that argument. They MAY turn out to be correct, but since no-one has yet demonstrated if these augmentations really do help, its all speculation at this point. And too many posts...

Nope, wasn't assuming anything, I was merely pointing out that there was an unvoiced assumption that adding lidar/radar would yield a fast(er) track to some level or other of self-driving. If you want my opinion, it's that the Tesla and Waymo approaches will converge .. Tesla will improve...

Which was my point. We know cars CAN be driven well with vision-only, the only reason we have these extra sensors is because right now we can't figure it out (though Tesla are doing their best). Sure, having radar helps with fog, but that's a post-event rationalization, not the reason radar has...

The range math the car uses is conservative for obvious reasons .. better to arrive with a bit of extra charge than not to arrive at all! But once you get going the energy graph etc will try to be as accurate as it can (and its not bad, considering all the variables it has to account for). You...

I'm not sure I buy this argument. Humans basically use three senses when driving: sight (primary), inner-ear accelerometer (car movement) and touch (steering etc feedback). The car has vision and accelerometer, with possible radar and/or lidar. Your argument is we can't (yet) make car vision as...

You are assuming the OP has the Gen 3 wall connector...

Yeah I know .. unfortunately I'm away from my car so can't give you the exact buttons and didn't want to tell you the wrong thing, so this might be an exercise in learning the UI a bit (someone else can probably point you to the right icons .. Tesla changed them all recently and there was...

Certainly the 14/50 wall plug is NOT designed for frequent insertion/removal. I'm not sure about the Tesla adapter connection, but I suspect (guess?) that its designed for occasional changes rather than (say) daily ones. If you can afford it, I would invest in another complete mobile connector...

The newer cars like your come with a USB stick already installed to a connector in the glove compartment (the last I recall, mins is an older year and doesnt have this). And if you tap the apps button along the bottom of the screen you can bring up a menu of app icons, and choose the Dashcam...

-- You can't make AP turn left using turn signals since it cannot make autonomous turns at all, it can only basically follow the road. -- NoA will take off ramps, and negotiate freeway interchanges, but that means you need NoA enabled and need to have a route in the nav system so it knows which...

Again, I did nothing of the sort. I merely said that WE DONT KNOW since we have no real-world information on MobileEye yet outside of their claims.

So is any American muscle car .. and these are a a price point (barely) where a younger guy (the most dangerous driver demographic, statistically) can get one.

ok, a couple of things... First, yes FSDbeta should follow the nav route to the destination, and 90% of the time will follow it exactly. There are circumstances when the car will deviate however, since it may find a road is blocked or may not even exist (it wont blindly turn where there is no...

Why do you think AP will make turns based on turn signals?

I didnt dismiss MobileEye at all .. read the last sentence of my post.

No insult but i think you need to study the various AP systems more, as you seem confused about what you expect the car to do or not do with the various options turned on or off.

No i’m saying you are blaming FSD beta for nav system errors, which is as silly as blaming the human driver for following a bad nav system route. If you want to point out the nav system has chosen a bad route thats fine, but dont say its an FSDbeta bug .. its not

But these are issues with the Nav system (which would tell you the human driver, to follow the same route) and TACC/NoA (which handles freeway driving and on/off ramp decisions). Neither of which are anything to do with FSDbeta.

But again, you are comparing MobileEye claims against Tesla FSD observed driver experiences. I'm sorry, but I don' think that warrants your conclusion. I dont know if MobileEye is better or worse than FSD, and I don't think you do either, if you base it only on this information.

And what conclusion do you draw from these numbers? Answer: None at all, since the relative populations of cars with ADAS per maker and miles driver are not taken into account.

Hardly surprising .. FSD it all profit so Tesla will prioritize the higher-end builds, given the supply constraints everywhere atm

In an ideal system, acceleration makes no difference since the final kinetic energy of the moving vehicle is the same. However, real-world cars are not ideal, and there are energy losses in all parts of the system, including friction in the moving parts (axles, tires etc) and electrical losses...