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

U.S. opens probe into Tesla’s Autopilot over emergency vehicle crashes

reuters.com

Post reply on HN
Print view View original

491–500 of 507 posts

Re: U.S. opens probe into Tesla’s Autopilot over emergency vehicle crashes

#491

Post by harles »

diggernet wrote: post #490
harles wrote: post #442

Earlier quoted context omitted.

I’m not sure about newer models without radar, but the older ones explicitly discard stationary returns on their radar. As I understand it, without elevation data it can’t know if it’s a bridge you’ll pass under, a soda can in the road, or a stopped car - so just ignore it all. Of course the vision system is supposed to compensate for this, and it performs poorly on objects it doesn’t see often, like emergency vehicl…

why should it matter how often it sees something? Or even if it's something the car has never seen before? All it should care about is whether there is an obstacle, not what the obstacle is. Whether it's an emergency vehicle, a sofa, a boulder, a canoe, a table saw, or a dolphin, you don't want to hit it!

How often it’s seen in training data that is, which is pulled from data in the wild.

It’s simply not possible to do depth estimation like this without priors. That’s one of the serious limitations of such systems - you have to train on every class of object you don’t want to hit.

Re: U.S. opens probe into Tesla’s Autopilot over emergency vehicle crashes

#493

Post by geekraver »

It would be great if Tesla could actually get speed limit detection right for starters, and then slow down the car in time for a new reduced speed limit. Had my MY for just a few days and found that inability pretty annoying. It detected a 40mph road as 60, and a 60mph freeway (which is only ever 60mph) as 70. I’ve had 5 year old Garmin GPS units that do better than that offline. I mentioned this in a local owner group and a bunch others chimed in saying they see this too.

Re: U.S. opens probe into Tesla’s Autopilot over emergency vehicle crashes

#494

Post by tshaddox »

amanaplanacanal wrote: post #455
tshaddox wrote: post #450

Earlier quoted context omitted.

The point is that it makes driving on the highway easier, just like automatic transmissions, power steering, etc. I'm sure early critics of all of these technologies have said things like "but if the driver doesn't need to spend mental and physical energy to that this they will stop paying attention to the road and will be less safe."

You’re sure? Perhaps you could find where somebody actually said that.

I meant it sarcastically. Perhaps no one did say that at the time. My point was that it would obviously be ridiculous if they did.

Re: U.S. opens probe into Tesla’s Autopilot over emergency vehicle crashes

#495

Post by cameron_b »

quartesixte wrote: post #406
oaw-bct-ar-bamf wrote: post #389

Earlier quoted context omitted.

In my opinion the underlying assumption autopilots are built with are wrong. It is assumed that the road is free to drive on. Only when the vehicle computer detects a known object on the road that it knows should not be there it is applying brakes or trying to steer around. I would feel safer if the algorithm would assume the negative case as default and only give the „green light“ once it determined that the road is…

> It is assumed that the road is free to drive on. Trying to remember if the opposite of this is how human drivers are taught, or if this is implicit in how we move about the world. My initial gut reaction says yes and this is a great phrasing of something that was always bothering me about automated driving. Perhaps we should model our autopilots after horses: refusal to move against anything unfamiliar, and biased…

In my high school’s Drivers Ed class I distinctly remember the one-question pop quiz: “What is the most dangerous mile of road?”

The answer was “the mile in front of you”

Additionally there was some statistic about the frequency of accidents within a very short distance of the drivers residence, which seemed to underscore the importance of being aware of just how much your brain filters out the “familiar” in contrast to a newly stimulating environment.

Re: U.S. opens probe into Tesla’s Autopilot over emergency vehicle crashes

#496

Post by diggernet »

harles wrote: post #491
diggernet wrote: post #490

Earlier quoted context omitted.

why should it matter how often it sees something? Or even if it's something the car has never seen before? All it should care about is whether there is an obstacle, not what the obstacle is. Whether it's an emergency vehicle, a sofa, a boulder, a canoe, a table saw, or a dolphin, you don't want to hit it!

How often it’s seen in training data that is, which is pulled from data in the wild. It’s simply not possible to do depth estimation like this without priors. That’s one of the serious limitations of such systems - you have to train on every class of object you don’t want to hit.

Then they are doing it wrong. There are all manner of things that can end up in the road that have never been (and will never be) classified. If their system must classify a thing to not hit the thing, then they will kill people. It's gross negligence to work so hard to not, at the very minimum, install two cameras for stereo vision.

Re: U.S. opens probe into Tesla’s Autopilot over emergency vehicle crashes

#497

Post by 0x000000001 »

fxtentacle wrote: post #482
ajross wrote: post #395

Earlier quoted context omitted.

> The fact that they have given anyone an impression otherwise is problematic. Good grief. This meme will not die. The car literally tells you to keep your hands on the wheel every time you engage autopilot, yells at you if you don't, will lock you out of the system as punishment if you don't comply, and if you really seem disabled will bring the car to a stop and turn the hazards on. It simply will not operate witho…

Here's #1 out of your zero drivers ;) "Tesla driver slept as car was going over 80 mph on Autopilot, Wisconsin officials say"

And that driver was cheating the attention nags

Re: U.S. opens probe into Tesla’s Autopilot over emergency vehicle crashes

#498

Post by jiscariot »

cameron_b wrote: post #495
quartesixte wrote: post #406

Earlier quoted context omitted.

> It is assumed that the road is free to drive on. Trying to remember if the opposite of this is how human drivers are taught, or if this is implicit in how we move about the world. My initial gut reaction says yes and this is a great phrasing of something that was always bothering me about automated driving. Perhaps we should model our autopilots after horses: refusal to move against anything unfamiliar, and biased…

In my high school’s Drivers Ed class I distinctly remember the one-question pop quiz: “What is the most dangerous mile of road?” The answer was “the mile in front of you” Additionally there was some statistic about the frequency of accidents within a very short distance of the drivers residence, which seemed to underscore the importance of being aware of just how much your brain filters out the “familiar” in contrast…

I had always assumed the "close to home" numbers were just bad statistics, because I never saw them control for % of driving that was done "close to home".

If I google it, I get like three pages of law firms.

Re: U.S. opens probe into Tesla’s Autopilot over emergency vehicle crashes

#499

Post by barbazoo »

xsmasher wrote: post #360
barbazoo wrote: post #333

Earlier quoted context omitted.

I cannot open the study in the first link but the second on seems to actually refute the claim instead of supporting it. > There is a body of research on how driver behaviour might change in response to bicyclists’ appearance. In 2007, Walker published a study suggesting motorists drove closer on average when passing a bicyclist if the rider wore a helmet, potentially increasing the risk of a collision. Olivier and W…

Keep reading. > We then present a new analysis of the original dataset, measuring directly the extent to which drivers changed their behaviour in response to helmet wearing. This analysis confirms that drivers did, overall, get closer when the rider wore a helmet.

Yes, you're right. I should have read the whole thing.

Re: U.S. opens probe into Tesla’s Autopilot over emergency vehicle crashes

#500

Post by harles »

diggernet wrote: post #496
harles wrote: post #491

Earlier quoted context omitted.

How often it’s seen in training data that is, which is pulled from data in the wild. It’s simply not possible to do depth estimation like this without priors. That’s one of the serious limitations of such systems - you have to train on every class of object you don’t want to hit.

Then they are doing it wrong. There are all manner of things that can end up in the road that have never been (and will never be) classified. If their system must classify a thing to not hit the thing, then they will kill people. It's gross negligence to work so hard to not, at the very minimum, install two cameras for stereo vision.

100% agree. I think depth is critical and monocular estimation doesn’t cut it.
Post reply on HN