News for hackers. Stuff that matters.
Re:Tesla FSD Timeline by eschneider on Wednesday December 13, 2023 @07:07AM (#38626173)
> To me, it indicates that they haven't solved even the easiest part: there is something in a static setting, don't crash into it, stop.

That turns out to be a harder problem than most people think, and it gets in the way of the 'driving' part. "Are we looking at some big, blank object or are we looking at the sky? It's probably the sky, so we'll just drop it from the model." Which is how Teslas drive into big trucks. :/

Re:Tesla FSD Timeline by mnau on Wednesday December 13, 2023 @07:11AM (#38626218)
Even if visuals failed, Tesla has a sonar, radar and Tesla is moving at snail pace.

Hell, my vacuum stops moving when it detects it crashed into something (likely torque required to move wheels is larger than expected).

Edit: at the end of the day, it doesn't matter why it happened. The result is a crash in a super simple environment and is (to me) quite indicative to the state of things. They are supposed to come up with solutions, not excuses (also, Elon hates lidar, but that is still on Tesla).

Re:Tesla FSD Timeline by Anarch157a on Wednesday December 13, 2023 @07:39AM (#38626485)
Tesla dropped radar, lidar and ultra-sound from their cars a while ago [0]. This was another childish decision by Musk, who personally overruled the engineers [1].

[0] https://www.tesla.com/support/transitioning-tesla-vision

[1] https://insideevs.com/news/658439/elon-musk-overruled-tesla-...

Re:Tesla FSD Timeline by yreg on Wednesday December 13, 2023 @08:00AM (#38626699)
Andrej Karpathy claims to stand by that decision: https://youtu.be/_W1JBAfV4Io?si=QUceD5ZG0j_hclHP&t=39
Re:Tesla FSD Timeline by tsimionescu on Wednesday December 13, 2023 @08:50AM (#38627303)
"Did you agree with your egomaniacal boss who thinks he is a brilliant engineer and programmer when he made one of the biggest blunders, or did you know better?"
Re:Tesla FSD Timeline by valval on Saturday December 16, 2023 @11:54AM (#38665682)
0 projection or prejudice being done here, you come across as perfectly rational.
Re:Tesla FSD Timeline by doublespanner on Wednesday December 13, 2023 @08:12AM (#38626818)
They are trialing a radar again in the S, but from their marketing it doesn't look like it's a clear benifit yet
Re:Tesla FSD Timeline by acdha on Wednesday December 13, 2023 @09:55AM (#38628226)
I would compare them to other companies: they’re not going to lightly outshow their own products since that both affects sales and increases the odds of a lawsuit on behalf of everyone who bought the older models under false advertising. It’s more likely to end badly in court if the lawyer can say everyone else in the industry got this right but their clients vehicles will never get the promised features because they lack the necessary hardware.
Re:Tesla FSD Timeline by malfist on Wednesday December 13, 2023 @08:00AM (#38626694)
Does Tesla still have sonar and radar? I thought everything but cameras were removed a few years ago
Re:Tesla FSD Timeline by me_me_me on Wednesday December 13, 2023 @09:38AM (#38627964)
> Hell, my vacuum stops moving when it detects it crashed into something (likely torque required to move wheels is larger than expected).

Ha ha, that's a good take. Maybe you could help musk and point him to that vacuum :D

On a serious note self driving sounds like a near impossible problem due to deadly corner cases that take intuition of a general purpose AI.

Driving in California is probably the easiest level of complexity. How do you drive in inner EU town and cities?

I will believe when I see it. Otherwise any claims of 'we almost have it working' are lies to me

Re:Tesla FSD Timeline by Zetobal on Wednesday December 13, 2023 @11:50AM (#38630072)
You say EU I say India.
Re:Tesla FSD Timeline by meindnoch on Wednesday December 13, 2023 @02:53PM (#38633300)
That's easy. Just drive slowly and keep intensely honking.
Re:Tesla FSD Timeline by Tempest1981 on Wednesday December 13, 2023 @11:47AM (#38630033)
> my vacuum stops moving when it detects it crashed into something

In the home, fewer objects are in motion near the vacuum. But maybe if you have a lot of cats...

Re:Tesla FSD Timeline by mrpopo on Wednesday December 13, 2023 @08:03AM (#38626724)
It's not a difficult problem as long as you have radar/lidar and not just computer vision as input.

I understand computer vision could be used as primary input, but IMO it should be mandatory to have some kind of proximity sensor as backup input.

Proximity sensor senses something, speed vector indicates collision in X seconds => stop

Re:Tesla FSD Timeline by mensetmanusman on Wednesday December 13, 2023 @08:11AM (#38626812)
It's not a difficult problem for humans with no lidar and 100W operating budget.
Re:Tesla FSD Timeline by suoduandao3 on Wednesday December 13, 2023 @08:22AM (#38626911)
Not a computer vision engineer here - do we just not know how the human brain recognizes objects or does it do so in a way that's hard to reproduce in silicon?
Re:Tesla FSD Timeline by tsimionescu on Wednesday December 13, 2023 @08:57AM (#38627401)
We don't know how it works, and the parts that we do know are very hard to implement.

In particular, our vision is very very tied to our model of the world, and is clearly an evolutionarily derived trait, not something we learn from scratch as children. We are basically born with a model that can augment the raw sensory input with basic physics (object permanence, but also we have an intuition for things like "heavy = large momentum even at slow speeds", and for "what goes up will come down", some basic optics of how objects cast shadows, and others). In addition, we learn to recognize objects and we know their actual sizes from past experience, so we typically estimate distance this way far better than relying on parallax. "Small image of car" is automatically "car far away", even if seen with one eye, because we know what size a car is.

In fact, much of our brilliant vision starts going awry immediately in an artifical setting with misleading sized objects.

Re:Tesla FSD Timeline by jampekka on Wednesday December 13, 2023 @11:39AM (#38629890)
We don't have much idea of what "our model of the world" is. Probably quite little of it is genetically encoded. E.g. object permanence has to be learned (takes around 7 months).

What you describe is largely the classical "cognitivist" model, which is more or less dead in the contemporary tought. We don't even have a very good account of depth estimation, apart from "bunch of things seem to affect it".

Re:Tesla FSD Timeline by tsimionescu on Wednesday December 13, 2023 @12:34PM (#38630885)
Object permanence is not "learned", it develops at around 7 months. Same as you don't "learn" to reach puberty, your body is pre-built to only start puberty at a certain age. Edit: I should note that object permanence in particular is a more contentious topic. Other parts of of our understanding of the world are more readily assigned to innate functions, though.

Note that many mammals have object permanence, and for some it develops right after birth. The fact that human development is so slow is the only reason some of these things look like actual learning. Another more clear example is our ability to walk/crawl - in humans it seems to be learned, but most other mammals are able to do it within minutes of being born, making it quite obvious it is in fact a genetically coded trait.

Re:Tesla FSD Timeline by jampekka on Wednesday December 13, 2023 @12:59PM (#38631370)
If the babies don't see objects, they don't "develop" object permanence. Yeah, here we can summon the "use it or use it" copeout, but then the nativist account becomes unfalsifiable.

Being able to crawl within minutes (and even somewhat run within hours as horses do) is mostly due to anatomy and "reflex pathways". E.g. a cat can walk without brains [1], as can famosly headless chicken.

Human babies too have these kinds of reflexes but they are "abandoned" well before the baby learns to walk.

[1] https://m.youtube.com/watch?v=wPiLLplofYw

Re:Tesla FSD Timeline by tsimionescu on Friday December 15, 2023 @02:03AM (#38651754)
While I agree it makes it very hard to test some of these hypotheses, "use it or lose it" is very clearly true of at least some bodily and cognitive capacities. So it's not unfair to posit it could apply to these as well.

If you think quadruped walking is only a bunch of reflexes and human walking isn't, that still doesn't completely negate my point. Primate infants also display significantly more agility than human babies right afer birth, and "learn" to walk significantly faster.

Here [0] is a study for example that finds that the age of walking is 94% predictable for any mammalian species that walks on the ground by a particular ratio between the mass of the infant brain and the adult brain (that is, an infant animal essentially learns to walk when its brain reaches a certain percentage of its final brain size).

Besides this type of animal comparison, another signal we can use to distinguish between built-in capacities and things we learn from experience is to see whether a capacity can be developed later in life. For example, if you lack visual stimuli in the early part of brain development, even if you get it later, you will never develop vision (we know this from studies on kittens...).

[0] https://www.pnas.org/doi/full/10.1073/pnas.0905777106

Re:Tesla FSD Timeline by jampekka on Wednesday December 13, 2023 @11:36AM (#38629831)
Cognitive scientist here: we have no idea how the brain works in general. In locomotive tasks like driving the brain probably does not even try to recognize objects most of the time.
Re:Tesla FSD Timeline by Qwertious on Wednesday December 13, 2023 @09:16AM (#38627655)
Okay how about we make cars that can fully self-drive, and then remove hardware crutches afterwards. Some blind people can ride a bike safely (with echolocation), but I'd strongly recommend you use eyes too if you have them.
Re:Tesla FSD Timeline by ndsipa_pomu on Wednesday December 13, 2023 @09:36AM (#38627922)
Our perception system does have the advantage of being aggressively trained for a significant number of years (hundreds of millions?)
Re:Tesla FSD Timeline by acdha on Wednesday December 13, 2023 @09:59AM (#38628302)
Humans have millions of years of evolution tuning our visual system and we still have tons of crashes due to poor performance during low light situations, high contrast, etc. Twilight is recognized as a time of increased accidents, we’ve had decades of mandating better types and positions of lights, roads are expensively designed with various paints and reflectors, etc.
Re:Tesla FSD Timeline by eschneider on Wednesday December 13, 2023 @11:05AM (#38629390)
It's still a hard problem as radar/lidar have similar object identification issues as cameras. (I've made production products with both lidar and cameras and the situations were both fail is non-zero).

The problems are both false-positive and false-negative and no matter what you do, you'll see some of both. (Yes, a problem people have, too.)

Oh, and don't forget cars are operating in an adversarial environment. Obstacles will appear w/out giving you time to stop.

Re:Tesla FSD Timeline by numpad0 on Wednesday December 13, 2023 @07:33AM (#38626437)
Problems involved being hard doesn't make it okay to willfully sell an unfinishable product.

I know for the fact that making a flying carpet is hard. Doesn't mean you should be greatful for life to be able to pay me $1M for a non-flying flying carpet that sets itself on fire.

Re:Tesla FSD Timeline by asylteltine on Wednesday December 13, 2023 @09:14AM (#38627637)
It’s actually not hard, like at all. Every other manufacturer solved it. The problem is that Elon dropped all sane forms of “vision” like lidar because he wants to squeeze out profits at the cost of consumer safety (not to mention Tesla kills motorcyclists hand over fist)

He’s hell bent on machine vision which can’t even identify a cyclist for fucks sake! And somehow this is legal to deploy on public roads!

Re:Tesla FSD Timeline by badpun on Wednesday December 13, 2023 @10:10AM (#38628467)
Are they just doing object detection, or are they also doing 3d scene reconstruction (visual SLAM)? My bet is on the latter, and the SLAM reconstruction should show them that there's something dangerously close to the car. Of course, vSLAM is notoriously finnicky in corner cases, lighting conditions etc., so it might have just not noticed the plane at all.