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

NTSB: Autopilot steered Tesla car toward traffic barrier before deadly crash

arstechnica.com

Post reply on HN
Print view View original

381–390 of 546 posts

Re: NTSB: Autopilot steered Tesla car toward traffic barrier before deadly crash

#381

Post by morogop »

annerajb wrote: post #368
lscotte wrote: post #300

Earlier quoted context omitted.

Wow, Tesla doesn't have auto emergency braking? Even my Kia has that - adaptive cruise for following cars, auto emergency braking for stationary objects (and when the car in front of you suddenly slows down). Yeah, I'll keep my Kia...

It does but it cannot detect stopped object which apparently is a standard limitation. Besides aeb is made to reduce crash speed the car will still crash.

that's not a standard limitation. Both my wife and my auto brake systems will start squealing if driven too close to stationary obstacles.

Re: NTSB: Autopilot steered Tesla car toward traffic barrier before deadly crash

#382

Post by jchb »

dcposch wrote: post #369

Tesla Autopilot makes it to HN pretty much every week now, almost never in a good way. Every time, we have a big discussion about autopilot safety, AI ethics, etc. What about lack of focus ? Tesla has already reinvented the car in a big way--all-electric, long range, fast charge, with a huge network of "superchargers". It's taken EV from a niche environmentalist pursuit to something widely seen as the future of autom…

The interior design of the Model 3 is very simple - there are few physical controls - with the assumption that the car usually does not need to be driven by a human. As Elon presented it: https://youtu.be/GZm8ckvsu9I?t=2m2s. Pure speculation: perhaps the simplified interior is necessary to bring the costs down for mass-production, and here is where the "synergy" with the autopilot comes in.

Re: NTSB: Autopilot steered Tesla car toward traffic barrier before deadly crash

#383

Post by unclebucknasty »

Animats wrote: post #42

NTSB: • At 8 seconds prior to the crash, the Tesla was following a lead vehicle and was traveling about 65 mph. • At 7 seconds prior to the crash, the Tesla began a left steering movement while following a lead vehicle. • At 4 seconds prior to the crash, the Tesla was no longer following a lead vehicle. • At 3 seconds prior to the crash and up to the time of impact with the crash attenuator, the Tesla’s speed increas…

>it doesn't detect stationary obstacles

Wait, how can that be? I mean clearly it didn't detect the barrier in this case, but that wasn't by design was it?

Re: NTSB: Autopilot steered Tesla car toward traffic barrier before deadly crash

#384

Post by CamelCaseName »

megablast wrote: post #328
buvanshak wrote: post #303

Earlier quoted context omitted.

If a company is this blatantly evil while still in a growing phase, I can only imagine what they would do once they are a established major player...

It is a car company. Their products directly kill over a million people every year. The injure 10x as many. Their pollution causes a similar number of deaths. They are responsible for so many horrible side effects, including dangerous city and suburbs to people taking up more and more space. You think this one crash makes them evil?

Yes, cars kill, injure, and create disease, but they also connect people across the world, to relatives, to work, to buy and deliver goods and services.

Without cars, our level of productivity would be a fraction of what it is today as employment is confined to a tiny geography. Many more people would die from fires, disease, and crime as emergency services arrive on horse drawn carriage. Most people would never venture out of their hometowns.

Car companies, for all their faults, for all their fraud and corruption, create products that immeasurably benefit us every day. Before we call them evil, we must look at the impact they have on each of us. That impact is decidedly positive, as evidenced by the widespread ownership of cars.

Re: NTSB: Autopilot steered Tesla car toward traffic barrier before deadly crash

#386

Post by wooter »

amelius wrote: post #278
stickfigure wrote: post #270

Earlier quoted context omitted.

This is a popular idea: Just put someone in charge! It ignores the incentives for those gatekeepers, who are now part of the system. In practice I don't think you're going to get better updates, you're going to get "almost no updates". See also: The FDA and drug approvals.

So you want to do away with the FDA? Put BigPharma in charge and let them regulate themselves? That sounds a lot less appealing to me.

fdareview.org - the fda kills more people in late/non approvals than it saves through denials. this is why compassionate use has been on the rise

Re: NTSB: Autopilot steered Tesla car toward traffic barrier before deadly crash

#387

Post by berti »

uncoder0 wrote: post #312
Fricken wrote: post #308

Earlier quoted context omitted.

Were you using the Velodyne 64s? Cruise, who uses the 32 laser velodynes avoids highway/freeway speeds because their lidar doesn't have the range to reliably detect obstacles at that distance.

SICK LMS 2xx. Weakest link was the java microcontrollers we had to use because we were majority funded by SUN. My favorite part was the old elevator relays we found in a junkyard and used for a bunch of the control system. You could hear the car 'thinking' and know what it was about to do.

I'm involved in a project using the LMS5xx.. but on a PLC, so I envy your Java microcontroller! Have you seen SICK's new MRS 6000? Range of 200 m, and 15 degrees vertical (15 degrees)! Pricing is similar to LMS5xx.

Re: NTSB: Autopilot steered Tesla car toward traffic barrier before deadly crash

#388

Post by acct1771 »

Alupis wrote: post #188
thatswrong0 wrote: post #135

Earlier quoted context omitted.

Is there an equivalent safety standard for ICE vehicles? I don't think a gas task would do particularly well in the exact same circumstance either

ICE vehicles don't typically spontaneously combust after a crash...

No, just during, when you're unconscious, and not safe in your new car miles away.

Re: NTSB: Autopilot steered Tesla car toward traffic barrier before deadly crash

#389

Post by carlmr »

mark-r wrote: post #354
ploxiln wrote: post #218

Earlier quoted context omitted.

All cars from all manufacturers are running 10s or 100s of times more code than they did 10 or 20 years ago. https://skeptics.stackexchange.com/questions/39559/does-the-... This really affects the nature of the situation. 20 years ago, cars contained microcontrollers with a tiny bit of code which was thoroughly reviewed and tested by skilled professionals. Today, all cars run so much code, even outside of the enterta…

AI takes it to a whole new level. Neural networks are all black box, they can't be reviewed. You feed in your training data, you test it against your test data, and just have faith that it will respond appropriately to a pattern that's slightly different than anything it's seen before. Sometimes the results are surprising.

That's my biggest problem with AI and neural networks. You can't really measure progress here. If you wanted the same safety standards as for every other automotive software you'd have to test drive for hundreds of thousands of kilometres after every change of parameters, because there's no way to know what has changed about the AI's behavior except for testing it thoroughly.

Compare this to classic engineering where you know the changes you've made, so you can rerun your unit tests, rerun your integration tests, check your change in the vehicle and be reasonably sure that what you changed is actually what you wanted.

The other approach to autonomous driving is to slowly and progressively engineer more and more autonomous systems where you can be reasonably sure to not have regressions. Or at least to contain your neural networks to very very specific tasks (object recognition, which they're good at), where you can always add more to your test data to be reasonably sure you don't have a regression.

I don't think we'll see too many cars being controlled by neural networks entirely, unless there's some huge advancement here. Most of the reason we see more neural networks now is that our computing power has reached the ability to train sufficiently complex NNs for useful tasks. Not because the math behind it advanced that much since the 60s.

Re: NTSB: Autopilot steered Tesla car toward traffic barrier before deadly crash

#390

Post by mortehu »

salawat wrote: post #358
Pfhreak wrote: post #299

Earlier quoted context omitted.

This seems testable. IANAAE (I Am Not An Automotive Engineer), but why can't you run both the new and old code side by side and if the actions they take are materially different investigate further? Like, if in one case the new code would want you to move left, and the old code goes straight, one of those behaviors is probably wrong. If the driver corrects, then the new code is probably correct, but if the driver doe…

It has already been touched on by another commenter, but testability of Machine Learned systems outside of a training dataset is pretty much a crapshoot. An ML solution stops "learning" after training and only reacts. To illustrate the difference, have you driven on roads under construction lately? As humans, when you've driven the same road hundreds of times, you start to do the same thing as a machine learned imple…

I think the point is to run the two models on the same data, either simultaneously in everyone's cars, or using recorded sensor data from the past (maybe in the car while parked after a drive for privacy reasons). Initially, only the old version gets to take any action in the real world. Any difference in lane choice would then have to be justified before making the new version "live".

You can do this sort of stuff when replacing a web service too, by the way. For example running two versions of Django and checking if the new version produces any difference for a week before making it the version the client actually sees.

Post reply on HN