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

Tesla Autopilot Almost Steers Model 3 into Oncoming Train

thedrive.com

Post reply on HN
Print view View original

221–230 of 328 posts

Re: Tesla Autopilot Almost Steers Model 3 into Oncoming Train

#221

Post by alephxyz »

AshamedCaptain wrote: post #48
MarkMarine wrote: post #14

Earlier quoted context omitted.

I can’t imagine there is a way to get a refund, but if I could I would. 10k on something they won’t even let me beta test because where I live triggers incorrect forward collision warnings too frequently for my driving to be considered good enough. I was skeptical but paid up front, and I’m pretty sure I got taken

> they won’t even let me beta test because where I live triggers incorrect forward collision warnings too frequently for my driving to be considered good enough WTF. And I guess they will still compare "Autopilot" accidents with your average driver's, when they are literally combing (supervisor) drivers for their skill?

Combing drivers for their skill and their driving routes for how easy it would be for FSD to drive through.

Re: Tesla Autopilot Almost Steers Model 3 into Oncoming Train

#222

Post by hatware »

deng wrote: post #80

Actually, that steering into the oncoming train is just one of several severe instances in that video: * Almost driving right into a barrier because road is closed: https://youtu.be/yxX4tDkSc_g?t=426 * Choosing the wrong lane and getting confused: https://youtu.be/yxX4tDkSc_g?t=666 * Trying to run a red light, right into traffic: https://youtu.be/yxX4tDkSc_g?t=732 * Stopping in the middle of an intersection without r…

The best part is people paid $12000 for the compute "hardware."

Re: Tesla Autopilot Almost Steers Model 3 into Oncoming Train

#223

Post by chrisseaton »

salawat wrote: post #217
chrisseaton wrote: post #71

Earlier quoted context omitted.

> There have to be at least dozens of documented cases of this being unsafe. The human in the loop seems to catch the mistake just fine? Doesn't seem to be even remotely close to an accident?

This totally worked for 737 MAX. This one doesn't even have a well defined algorithm so it's behavior can be predicted ahead of time.

> This totally worked for 737 MAX.

But this is how all aircraft autopilot systems work - they expect a pilot to be able to step in. The pilots don't leave the controls.

Re: Tesla Autopilot Almost Steers Model 3 into Oncoming Train

#224

Post by _ea1k »

rainsford wrote: post #70
pwpw wrote: post #39

Earlier quoted context omitted.

Because your brain is freed up from taking in all of the data points for constantly steering and speeding up and slowing down, it's incredibly less exhausting. Instead, you can focus on observing a lot more of the road and capturing things that you previously would have been unable to focus on. It's not often it deviates from expected behavior and catches you off guard with some radically unpredictable maneuver. When…

It could definitely be one of those experience it to understand it things, since I've never driven very far in a car with more advanced self-driving (trying it in a colleague's Tesla on a short drive to lunch is about the extent of my experience). I'm a private pilot though and what you're describing sounds a lot like the autopilots on small planes. It handles keeping course and altitude for you, so you can focus on…

Longer drives are where I have noticed it to be significantly less fatiguing. The hands free systems would be even better on some of those roads.

Re: Tesla Autopilot Almost Steers Model 3 into Oncoming Train

#225

Post by magwa101 »

deng wrote: post #80

Actually, that steering into the oncoming train is just one of several severe instances in that video: * Almost driving right into a barrier because road is closed: https://youtu.be/yxX4tDkSc_g?t=426 * Choosing the wrong lane and getting confused: https://youtu.be/yxX4tDkSc_g?t=666 * Trying to run a red light, right into traffic: https://youtu.be/yxX4tDkSc_g?t=732 * Stopping in the middle of an intersection without r…

No post body was provided.

Re: Tesla Autopilot Almost Steers Model 3 into Oncoming Train

#226

Post by chrisseaton »

justin66 wrote: post #210
chrisseaton wrote: post #71

Earlier quoted context omitted.

> There have to be at least dozens of documented cases of this being unsafe. The human in the loop seems to catch the mistake just fine? Doesn't seem to be even remotely close to an accident?

OP was referring to the safety of the feature, you're referring to the safety of the driver who was experimenting with it.

> you're referring to the safety of the driver who was experimenting with I

Isn't the safety of running the beta (the issue being discussed) a function of the safety of the driver?

Re: Tesla Autopilot Almost Steers Model 3 into Oncoming Train

#227

Post by shiftpgdn »

klyrs wrote: post #164
shiftpgdn wrote: post #68

Earlier quoted context omitted.

That’s a misleading headline. Tesla let go of their labeling team because they weren’t needed anymore.

Whenever somebody calls musk the smartest man in the world, they don't understand the connection between data labeling and Tesla's propensity to stop for nothing and crash into stopped emergency vehicles.

OpenPilot doesn’t have a data labeling team. I think you should do some more research before doing a drive by comment on something you know nothing about.

Re: Tesla Autopilot Almost Steers Model 3 into Oncoming Train

#228

Post by Someone »

hristov wrote: post #204
petilon wrote: post #77

Meanwhile Cruise just obtained permission to charge passengers for driverless rides in San Francisco [1]. Cruise has been cleared to charge for rides in vehicles that will have no other people in them besides the passengers. There will be no back-up human driver present to take control if something goes wrong. Why is Tesla so far behind? Tesla is generating these autopilot mishap news on such a regular basis that it…

Cruise and Waymo have lidar. Lidar can give you much more certainty about detecting objects and distances. Teslas only use cameras and have to do complex image analysis to detect objects. On the other hand lidar is more expensive. But it is getting cheaper and it does seem like it might be necessary for actual self driving.

Having LiDAR may make it easier to implement, but there are plenty of humans who can drive well without LiDAR, so having LiDAR isn’t necessary.

Re: Tesla Autopilot Almost Steers Model 3 into Oncoming Train

#229

Post by ncmncm »

pyinstallwoes wrote: post #192
ncmncm wrote: post #158

Earlier quoted context omitted.

And tagged all 200 as fired for bad performance. Just to avoid complying with labor law. Classy move, Tesla.

You know this for an absolute fact and swear to it on first hand knowledge?

Really?

Re: Tesla Autopilot Almost Steers Model 3 into Oncoming Train

#230

Post by BbzzbB »

moritonal wrote: post #177
ra7 wrote: post #106

Here is another idiot "testing" it out in front a school bus. The car wouldn't stop so he had to intervene: https://youtu.be/zQO6RJCUPEI?t=10 I'm continually surprised how it's still being allowed on public roads. Tesla claims it's not an autonomous system to regulators and refuses to provide any data, while marketing it as imminent Level 5 self driving. It seems like it will take someone to be seriously injured or d…

The rough part is how the guy's obviously making a decent amount of money with the YouTube series on Tesla. The more dramatic, the better, which is only going to further incentivise risking others.

220k lifetime views, mostly over the last 2-3 years, is not really a significant amount of money. His videos this week got 97, 699, 18 and 48 views.

He's probably trying, but I'm not sure he gets anything more than some beer money from this channel.

Post reply on HN