401–410 of 550 posts
Earlier quoted context omitted.
My FOIA requests say no, but lots of blind spots. I'm not operating "at scale" due to the cost involved with non-electronic FOIA requests.
Thanks. I can imagine that police could mine this just like they're doing with Google geolocation data.
Man -- his engineers must cringe quite a bit when he talks about a future self-driving architecture built on DOJO with 'video-in, actuator controls out' ... just a tiny bit of speculation goes into saying something like that ... To my mind, it undermines the presentation quite a bit which otherwise appears to mainly argue that they will reach full self-driving by iterating on their neural network sensor perception mo…
Earlier quoted context omitted.
How so?
If Tesla succeeds at FSD - Tesla is competing against them with hardware that operates at (using the numbers from the presentation, if I recall them correctly) ~1/10th the price. They have contracts in place with the owners of cars they have sold preventing them from letting Uber and Lyft use the self driving capability to compete.
Earlier quoted context omitted.
> Humans have far higher resolution sensors This is really not true. The phone in your pocket is just plain better. More total pixels per unit area, much greater dynamic range, able to sample over time periods an order of magnitude faster. The reason your vision seems better is because your brain is amazingly good at synthesizing a picture of the world around you. But all that data (the sphere around you is something…
I agree that, ultimately, vision and some IMUs will be all that's needed for an as-perfect-as-possible self-driving cars. Your statement on phone cameras being better than the human eye isn't true today, though. The human eye has FAR better dynamic range than any camera built to date, at any price point. This matters a great deal on sunny, cloudless days in a city with tall buildings casting dark shadows, for example…
Not at all true. All you need to do is take your camera into a dark room for proof. It can take useful pictures in environments you can't see. And with some manual control and safety precautions (seriously, don't actually do this) you'll note you can shoot useful photos of things that are very near bright sources like the sun where your eyes would be completely useless (and irrevocably damaged, again do not try this).
What you're complaining about isn't dynamic range, it's exposure control. A human brain, again, makes much better decisions about what parts of the environment are "important" when setting the aperture (iris). So the stuff you want to see is visible, where the camera is mostly just going to guess that the center of the frame is what you want and will routinely leave stuff over or underexposed.
Your last paragraph has the correct analysis but the wrong conclusion. It's the vision processing that makes the difference. The optical systems of a semiconductor camera absolutely are better, so a control system based on optics can absolutely be better.
Compare the 2016 demo video.[2] That's a tougher route. That's the one where we now know it took a lot of tries to get a clean video.
Waymo and Cruise have put up videos of their cars in city traffic. They get criticized for things like getting stuck behind double-parked cars, and being a bit shy of parked cars that project into a traffic lane. But they get where they are going. Tesla is not showing anything near that level.
Supposedly the analysts at the meeting got to ride in a self-driving car. Anyone seen reports from them?
[1] https://www.youtube.com/watch?v=tlThdr3O5Qo [2] https://www.youtube.com/watch?v=eAal0juXXzU
Earlier quoted context omitted.
Note that currently Tesla’s “autopilot” doesn’t even beat Toyota’s and Subaru’s adaptive cruise control: https://www.caranddriver.com/features/a24511826/safety-featu... You can’t even mention Tesla in the same breath as Waymo.
That article is judging AEB which is a safety feature that comes free on Teslas and isn't a part of the Autopilot system. It would obviously instill more confidence if Teslas performed better, but this isn't a measure of the company's Autopilot or FSD capabilities since it is entirely possible that AEB is a completely independent system.
> But the system still wasn’t at feature parity with the first generation Autopilot, primarily because of the lack of Automatic Emergency Braking (AEB) feature. Electrek has now learned that the important feature is going to be released this week.
> As we reported during the release of the 8.1 update, AEB has been a high priority feature for Tesla, but due to the nature of the safety feature, the company needs to make sure to get the false positive rate as low as possible in order to implement it safely.
> Unlike with the first generation Autopilot, Tesla has to build the feature from the ground up using its own ‘Tesla Vision’ technology and the new sensor suite.
Earlier quoted context omitted.
> Humans have far higher resolution sensors This is really not true. The phone in your pocket is just plain better. More total pixels per unit area, much greater dynamic range, able to sample over time periods an order of magnitude faster. The reason your vision seems better is because your brain is amazingly good at synthesizing a picture of the world around you. But all that data (the sphere around you is something…
Take a photo with any camera at night and compare with what you're seeing with your eyeballs.
It's not even a secret. Light capture in a phototransistor[1] is a basically direct process without a whole lot of loss or wasted surface area. Those cone cells are living things and only have a little volume to dedicate to pigment chemistry.
[1] CCD's of course can do an order of magnitude better still, and those are easily cheap enough to put in a car.
Karpathy's presentation is really good. Watch it later if you get some time. The key points are - Telsa is using fleet for learning (Fleet learning). This has 3 components, a. Trigger infrasture that collects the kind of data telsa is looking for training. The rational here is we don't need massive amounts of same kind of data but needs right kind of data for training neural networks correctly. b. Data Engine which l…
>Karpathy's presentation is really good. Watch it later if you get some time. I would second this recommendation. He did a really good job not only explaining Tesla's approach, but also breaking down the concepts in an easy to understand way for laypeople. That is a rare skill to have especially among someone who is obviously so technically accomplished.
My guess is that Tesla will need another round of financing along the way and they have to make sure that the stock's price stays up. Musk is a great promoter but at some point he needs to come back to reality.
Here's the new self-driving demo video from today.[1] From Tesla's HQ in Palo Alto, out to I-280, down one exit, use interchange at Sand Hill to turn around, come back. No visible conflicting traffic on non-freeway streets. Compare the 2016 demo video.[2] That's a tougher route. That's the one where we now know it took a lot of tries to get a clean video. Waymo and Cruise have put up videos of their cars in city traf…
These guys also went on the ride-along: https://youtu.be/2BZHXh1nbWc?t=360