Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Video of Tesla FSD almost hitting pedestrian receives DMCA takedown

twitter.com

Post reply on HN
Print view View original

181–190 of 455 posts

Re: Video of Tesla FSD almost hitting pedestrian receives DMCA takedown

#181

Post by rtkwe »

ChicagoBoy11 wrote: post #142
ChrisKnott wrote: post #63

Maximise the video and watch the left hand HUD pane from 0:10 to 0:11. The dotted black line coming from the front of the car (which I am assuming is the intended route) quickly snaps from straight ahead, to a hair pin right, to a normal right turn. Ignoring the fact that the right turn happened to be into a pedestrian crossing with people on it - what was the car even trying to do? The sat-nav shows it should have j…

I've made this argument here a few times and am always shot down, but I think its important to highlight that the airline industry has an extremely robust history of automation and HCI in critical transportation scenarios and it seems to me that all the lessons that we have learned have been chucked out the window with self-driving cars. Being able to effectively reason about what the automation is doing is such an i…

Cars are vastly more complex to do navigation for than planes too so we need to be even more careful when making auto autos. Plane autopilots are basically dealing with just the physical mechanics of flying the plane which while complex are quite predictable and modellable. All of the obstacle avoidance and collision avoidance takes place outside of autopilots through ATC and the routes are known and for most purposes completely devoid of any obstacles.

Cars have a vastly harder job because they're navigating through an environment that is orders of magnitude more complex because there are other moving objects to deal with.

Re: Video of Tesla FSD almost hitting pedestrian receives DMCA takedown

#182

Post by mcjshciejebcu »

partido3619463 wrote: post #23

Is the car turning right (after a no right turn sign) while it was supposed to be going straight according to nav?

The no right turn sign appears to be for the other side of the street, since at the intersection itself, there's a one way sign indicating right turns are possible, and no do not enter signs.

Re: Video of Tesla FSD almost hitting pedestrian receives DMCA takedown

#183

Post by cogman10 »

aeternum wrote: post #161
cogman10 wrote: post #49

Earlier quoted context omitted.

I agree, but this is probably the worst behavior I've seen of the FSD software. It abruptly tried to do a right turn on a no-right intersection with no warning (map said it was supposed to go straight, it looked like it was going to do that right up to the last second). Putting aside the "almost hitting a pedestrian", this is really dangerous behavior for an autonomous vehicle.

It's not like the car is going rogue and just randomly making a right turn. It's trying to find the right side of the road in a rare intersection. A monorail in the middle of a city street is quite rare so this is an understandable failure-mode.

Look at the screen. It is going rogue, the line on the screen shows where the car is supposed to go, it abruptly decided it was going to take a right turn.

Re: Video of Tesla FSD almost hitting pedestrian receives DMCA takedown

#184

Post by aaroninsf »

oefrha wrote: post #91
ChrisKnott wrote: post #63

Maximise the video and watch the left hand HUD pane from 0:10 to 0:11. The dotted black line coming from the front of the car (which I am assuming is the intended route) quickly snaps from straight ahead, to a hair pin right, to a normal right turn. Ignoring the fact that the right turn happened to be into a pedestrian crossing with people on it - what was the car even trying to do? The sat-nav shows it should have j…

From the admittedly not much footage of Tesla FSD (1-2 hours total maybe) I’ve watched, it seems to be roughly on par with a student driver who occasionally panics for no apparent reason.

...and it is obvious that it will actually ever get more than incrementally technically better, absent AGI.

The problem is too hard for existing tools. Good job on the 80% case; let's look for problems for which the 80% case is good enough and back away from unsupportable claims about "just a little more time" bringing FSD in environments defined by anomaly and noise, in which the cost of error is measured in human life and property damage.

Re: Video of Tesla FSD almost hitting pedestrian receives DMCA takedown

#185

Post by AlotOfReading »

silisili wrote: post #169
darkmarmot wrote: post #154

Earlier quoted context omitted.

I recently avoided a startup prospect because they were looking to build a car OS that wasn't hard real-time. The very idea that they're trying to develop such things that might intermittently pause to do some garbage collection is freaking terrifying.

To play devil's advocate...and because I'm just not that educated in the space, is this really a huge deal? If we're talking couple ms at a time delays, isn't that still vastly superior to what a human could achieve?

If you can set a guaranteed maximum on the delays (regardless of what those limits are), you're hard real-time by definition. The horror is that they weren't building a system that could support those guarantees.

Re: Video of Tesla FSD almost hitting pedestrian receives DMCA takedown

#186

Post by toxik »

rtkwe wrote: post #181
ChicagoBoy11 wrote: post #142

Earlier quoted context omitted.

I've made this argument here a few times and am always shot down, but I think its important to highlight that the airline industry has an extremely robust history of automation and HCI in critical transportation scenarios and it seems to me that all the lessons that we have learned have been chucked out the window with self-driving cars. Being able to effectively reason about what the automation is doing is such an i…

Cars are vastly more complex to do navigation for than planes too so we need to be even more careful when making auto autos. Plane autopilots are basically dealing with just the physical mechanics of flying the plane which while complex are quite predictable and modellable. All of the obstacle avoidance and collision avoidance takes place outside of autopilots through ATC and the routes are known and for most purpose…

Interesting point of view: autonomous cars as a form of contact-rich manipulation

Re: Video of Tesla FSD almost hitting pedestrian receives DMCA takedown

#187

Post by yawaworht1978 »

oefrha wrote: post #91
ChrisKnott wrote: post #63

Maximise the video and watch the left hand HUD pane from 0:10 to 0:11. The dotted black line coming from the front of the car (which I am assuming is the intended route) quickly snaps from straight ahead, to a hair pin right, to a normal right turn. Ignoring the fact that the right turn happened to be into a pedestrian crossing with people on it - what was the car even trying to do? The sat-nav shows it should have j…

From the admittedly not much footage of Tesla FSD (1-2 hours total maybe) I’ve watched, it seems to be roughly on par with a student driver who occasionally panics for no apparent reason.

The difference is the student driver will learn within a few more dozen hours and be fit for the road, Tesla no silver lining on the horizon.

Re: Video of Tesla FSD almost hitting pedestrian receives DMCA takedown

#188

Post by toxik »

spywaregorilla wrote: post #168
darkmarmot wrote: post #154

Earlier quoted context omitted.

I recently avoided a startup prospect because they were looking to build a car OS that wasn't hard real-time. The very idea that they're trying to develop such things that might intermittently pause to do some garbage collection is freaking terrifying.

That doesn't seem especially bad. The car could, for instance, predict whether or not it was safe to do garbage collection. Humans do the same when they decide to look away while driving.

Heck, some humans even do literal garbage collection while driving!

Re: Video of Tesla FSD almost hitting pedestrian receives DMCA takedown

#189

Post by LewisVerstappen »

Someone1234 wrote: post #105
LewisVerstappen wrote: post #13

Earlier quoted context omitted.

Edit: I was being dumb and am wrong. This is YouTube's internal system for copyrights not DCMA. Apologies. Old comment below... You can read up on how to submit DCMA takedowns for YouTube here -> https://support.google.com/youtube/answer/2807622?hl=en The original uploader of the video submitted the DCMA takedown request.

Your YouTube support link isn't about the DMCA, and in fact is an attempt at trying to get people to use their system instead of the DMCA. YouTube's internal copyright takedown system is just that: Internal. DMCA is a legal avenue that you can use against YouTube and their users, but it wouldn't be via their internal copyright take down system. It is in YouTube's best interests for you NOT to use the DMCA as there ar…

My mistake, apologies.

Edited the comment to note my error.

Re: Video of Tesla FSD almost hitting pedestrian receives DMCA takedown

#190

Post by oefrha »

Draiken wrote: post #163
oefrha wrote: post #148

Earlier quoted context omitted.

Drunk drivers on the road are… “fine”? Not sure where you live.

Of course it's not fine in that sense. What I mean is that you don't see a headline on news outlets or twitter hashtags trending for every drunk driver fatality or crash that happens. Which for me tells that collectively, we are fine with it. We accept it as ordinary, as crazy as it may be.

A DUI, in California for instance, means you’re suspended for months (years if you’re a repeat offender). Since it’s basically the same “driver” driving all FSD Teslas, are you arguing that they should be suspended under the same rules for drunken behavior? If so, they will basically be out of commission indefinitely, and we won’t see headlines anymore.
Post reply on HN