Tesla deploys massive new Autopilot neural net in v9
electrek.co
electrek.co
Even if it's not reckless their competitors will offer low light and night time autonomous driving which will be a major advantage.
Conventional cameras alone are not trustworthy for self-driving, and this is part of the reason every respectable company venturing into self-driving is incorporation technologies like LIDAR.
I find it sketchy that Tesla markets "future full-self-driving" when they are unlikely to have the hardware to make that a safe experience.
Their ability to deliver is a function of the costs of their basic technology supplies (batteries for the Roadster were expensive, less so for the S, X, and energy storage, and now even less so for the 3). This is very similar to the cost decline curve of solar, wind, and storage in the utility energy space (project developers provide bids based on where prices will be in 3-5 years).
Tesla can do this because technology and batteries rapidly decreases in cost every year. Need new autopilot compute hardware? It should be cheaper by the time they need to perform the swap to realize the capability. Need LIDAR? They'll find a way to install it, and the costs should be fairly reasonable per vehicle instead of thousands, or tens of thousands, if they went all in when it was expensive.
This is not unlike a technology startup, where technical debt you're going to pay off in the future is an acceptable tradeoff, so you push off the decision and/or work until the last possible moment (but no further).
And relating it to technical debt makes no sense as you have to design with LIDAR in the beginning.
Everyone is partnering with someone or organising supply deals. And everyone other than Tesla uses LIDAR.
Also I never said these cars were being sold today.
Then you're moving the goal posts. Tesla is selling cars today to people that they are (EDIT) targeting support of full autonomy, or have their hardware swapped to do so. Everything else is an experiment in a lab or on a track.
Well, Tesla claims that. It's quite possible that neither will happen.
An incredibly dangerous one.
https://thehill.com/policy/transportation/automobiles/315133...
> Federal regulators "did not identify any defects" in Tesla's autopilot feature after a lengthy investigation of the technology, officials announced Thursday.
> A six-month investigation failed to uncover any flaws with the autopilot's emergency breaking technology and other advanced features linked to a deadly accident last year, according to a National Highway Traffic Safety Administration (NHTSA) report released Thursday.
> "NHTSA’s examination did not identify any defects in design or performance of the AEB or Autopilot systems of the subject vehicles nor any incidents in which the systems did not perform as designed," the NHTSA report said.
I think Tesla is bang on the money going only with cameras. They are already better than the human eye.
Because it compensated for poor sensor hardware with a processing unit and software that we have thus far been unable to even come close to replicating? Granted, solve that, and we’re just a few years away!
People seriously misjudge the limitations of these sensors, and this leads to accidents.
Better to use cameras, which have almost exactly the same issues humans have (e.g. bad vision in low light, limited view, "blind" angles near corners, bad optical performance near the edges, ...), which will lead to "understandable" mistakes.
Nobody will understand if a LIDAR misses a beam sticking out of a truck in front of you (which would be expected behavior: such a thing is essentially invisible to LIDAR) and impales the person sitting in the passenger seat on it.
Or the Tesla fuckup. Failing to see the difference between front and back wheels of a large truck and 2 cars. Then decapitating the driver by driving in between the 2 sets of wheels at high speed. That's a typical LIDAR issue.
Sooner or later LIDAR will decide that just driving off an abyss is the best solution to a simple traffic situation (because LIDARs see abysses everywhere, so they use algorithms that assume abysses don't exist).
I've seen LIDAR controlled robots drive into tables "decapitating" (sort-of) themselves, because it only saw the feet of the table, looking at the data, and coming to the conclusion ... yep ... it was a perfectly understandable mistake. That robot also threw itself off the stairs. Again ... tough to fault it for that, as it saw the stairs as pretty much the same thing as a stick lying on the floor. Afterwards looking at the data, that was a perfectly reasonable conclusion.
We lost the robot to the stairs. I was looking at it making that decision. Why ? You see it move, and you're automatically assuming "surely it's not going to go for the hole in the staircase". And then it decides on a solution. Boom. And yes, I pressed the emergency stop button. Doesn't help much if the robot is already falling.
Surely, he cries, the argument is to use both and simply apply use some kind of likelihoods/confiendence in the output to combine them?
Hint: it’s not due to the sensor package being used.
But it is. The package is pretty limited, and the firmware running it is full of hacks that compensate. Hiding the blind spot, saccade masking, not paying attention to stationary things...
This has consequences. It takes them forever to find anything, even if they can do it from great distances. They are blind for several seconds when they change position (such as when they just caught prey), or just generally at short range.
And you can try this with cats: this makes it very easy to sneak up on them. No peripheral vision, directional hearing ... if they're focused in front of them, you can almost just walk up to them from the back, they won't notice.
These things are tradeoffs. Humans are prey species, pack hunters. If a human is paying attention you can't really hope to sneak up on them. One human is easy to take down. But 10 humans will defend each other effectively.
I'm not accusing you of any of this, just pointing out that a seemingly innocuous, almost cliched term like "evolutionary ladder" can carry a lot of unwelcome baggage.
So can digital cameras.
> And of course SONAR exists in whales, dolphins etc which is a corollary.
The reason for (active) SONAR is the lack of ambient sound. An alternative for a car would be headlights. Or passive infrared cameras.
Tesla is cutting corners by eschewing a well-known technology that will increase the fidelity of their autonomous driving system. That is irresponsible.
Do. No. Harm. It isn't just for Doctors. You can't sit on the positivist side of the fence and say, "Bah, it'll never happen."
It always does. When the cost is lives, you don't mess around or skimp. Closer to Perfection over pretty good is 100% justifiable in safety critical applications. In many cases, critical systems are redundantly reinforced.
Look up risk compensation to understand why a half-baked solution is almost guaranteed to be worse. If you are still relying on the human to compensate for failures in a system in an environment where response time to live is measured in seconds, you might as well just have them being alert and engaged at all times with as few things to have to compensate for malfunctioning as possible.
Another somewhat tangential demonstration of this is observable in nuclear reactor design, and utilising delayed fission product neutrons to attain criticality. This slows down the timescale over which things can go horribly wrong to the scale of minutes instead of seconds that would make avoiding prompt criticality highly problematic.
https://teslamotorsclub.com/tmc/threads/neural-networks.1014...
>Inception V1 is a four year old architecture that Tesla is scaling to a degree that I imagine inceptions’s creators could not have expected. Indeed, I would guess that four years ago most people in the field would not have expected that scaling would work this well. Scaling computational power, training data, and industrial resources plays to Tesla’s strengths and involves less uncertainty than potentially more powerful but less mature techniques.
I find it very, very hard to believe that. I know ‘expressive power’ is a fairly vague concept, but if things scale that well, there must be papers out there that at least hint at such (IMHO) insane scaling laws.
I think it also must mean that it is fairly easy for those with huge budgets to build a system that’s way better, except for the fact that it is too slow or takes too much power (just as 3D graphics in movies show what will be on our desks/phones in a decade or two)
I’ve asked it before, but does anybody know of papers that describe an offline self-driving system that’s as good as perfect?
To me the statement doesn't seem that unreasonable
V is the set of nodes. Each node is a simple computation cell. E is the set of edges, Each edge has a weight. .... If the activation function is the sigmoid function and the weights are general, then the VC dimension is ... at most O(|E|^2.|V|^2) [apologies for the crappy formatting]
While Someone's quote from the article seems to be suggesting something exponential in the number of edges.
Given the huge range between that upper bound and the lower bound of Ω(|E|²), chances are that upper bound is far from tight (https://en.wikipedia.org/wiki/Upper_and_lower_bounds#Tight_b...).
Also, one line below the O(|E|².|V|²) you quoted:
”If the weights come from a finite family (e.g. the weights are real numbers that can be represented by at most 32 bits in a computer), then, for both activation functions, the VC dimension is at most O(|E|)”
Of course, they may use a different activation function, in which case that mathematical statement doesn’t apply, but I would think it’s more unlikely that applies than the claim made on the article we’re discussing.
For example, it would hugely surprise me if using an activation function that isn’t increasing or that has many large discontinuities behaves a lot better than the sigmoid surely used.
Likewise, I would be quite surprised if Tesla is really pushing state of the art for the size of their vision models with what they've deployed in cars. Researchers have built some pretty big models...
I found the article to be full of unbiased information and also more personal info in the "ELECTREK’S TAKE" section.
I get virtually nothing unless I get 20 of them - not sure of the current program but so far my life time total referrals is: 0. If you have questions and want to ask someone who has owned two different ones since 2012 ask me questions. If you want to buy a tesla, I have a referral link too, contact me via email on my account here, maybe hackernews wouldn't like me to just put it out here.
When someone makes a broad critical remark about an article, but provides no specifics, I tend to assume it is because they know the article was in fact accurate, but don't want to admit it.
Or do we have to talk only about what they want us to talk?
Any security patch will already come too late -- when it comes to cars, it must not have security problems to begin with.
The cybersecurity model just isn't safe for this. It's up to them to fix this, not me.
Look into the history of automotive safety to understand how ridiculous this sounds. Cars were total death traps for many, many decades.
No product is bulletproof from a security standpoint, and there's no way to make something bulletproof. What are you suggesting they do?
[0] https://www.blackhat.com/docs/us-17/thursday/us-17-Nie-Free-...
Is it really a choice that cannot be overridden by the update?
If X declares war on California, will California shutdown every Tesla in X?
Will I be allowed to export my Tesla in 15 years to whatever developing country I like?
Did you think before you typed because 2 of those questions have nothing to do with this.
Will other people's cars be taken over and kill me?
Will my car be taken over and be used to drive me to someone who will harm me?
These are life or death concerns and let's not act like they're not ignoring this.
There's concerns and then crazy questions and comments.
The question shouldn't be "has it happened." The question should be how realistic is the chance of this happening in the future?
#1 is easy: “pay us or we will accelerate your car in a random direction in 24h”. The first round will be scareware, the future may not be.
Can't happen in a tesla, “so even if somebody would gain access to the car, they cannot gain access to the powertrain or to the braking system.”
And how is this any different than we'll kill you in 24h if you dont pay?
Even shutting off the lights or disabling the wipers can create big problems.
Disabling wipers or turning off the lights will kill us now? Not forgetting this hasn't happened, hasn't been proved to be possible and is all a theory.
Theories are fine but acting as if tesla is activity ignoring this is funny.
Disabling wipers and all lights while driving at high speed with the wipers running full blast can be quickly fatal.
Sorry you are wrong.
If one system absolutely requires communication with the other to function, I would never call them isolated.
Security flaws will always exist but there are limits and just blatantly claiming we're all gonna die because tesla doesn't care about security is a joke.
What are they doing about it that's effective? They are ignoring this.