NTSB: Autopilot steered Tesla car toward traffic barrier before deadly crash • Hacker News Board

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

#161

Post by txcwpalpha » Thu, Jun 07, 2018, 6:24 PM UTC

slg wrote: post #158

txcwpalpha wrote: post #156

Earlier quoted context omitted.

> That update going out immediately OTA is going to save lives compared to if Tesla waited for the cars to be serviced like other manufacturers. I don't think you can legitimately argue against that fact. There is again no evidence to support this fact. There is evidence that Tesla's OTA software updates have introduced safety issues with Tesla cars. That's a fact. Better braking distance is of course a good thing bu…

I simply don't know what to say to you if you are going to legitimately argue that shaving 20 feet off of braking distance will not make a car any safer. EDIT: The comment I was replying to was heavily edited after I responded. It originally said something along the lines of improving braking distance is good but there is no evidence that it would improve safety.

And yet again, the same OTA update changed other parameters about the way the car drives that do make it less safe. I don't know why you're trying to ignore that fact. If I drastically improve the braking distance of a car, but in the same update I also make it so that the car crashes itself into a wall and kills you, is the car safer? Hint: no

As for your edit, you clearly misread the original comment, which is why I edited it for you. I said that there was no evidence that the OTA made the car safer. Please try to read with better comprehension instead of trying to misrepresent my comments.

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

#162

Post by jakelarkin » Thu, Jun 07, 2018, 6:24 PM UTC

cornholio wrote: post #103

jakelarkin wrote: post #14

self driving systems cant well reason about untrained scenarios or the intent of other humans on the road. I think the people have grossly underestimated how driving in an uncontrolled environment is really a general AI problem, which we're not even close to solving.

> driving in an uncontrolled environment is really a general AI problem Is it? Unless you are talking about NASCAR, an adversarial game where rational agents compete for road space, driving is essentially a physics problem: maintain a speed and direction that does not exceed the vehicle's ability to correct them so as to avoid any stationary or mobile obstacle. In this case, the vehicle was accelerated to a speed (72…

you can break it down to various expert-system subproblems

- perfect cv image classification (+ low visibility )

- anticipating behavior of bikers, children, elderly, animals, near roads

- responding to human non-verbal communication

- responding appropriately to never before seen obstacles/scenarios without being a nuisance on the road or endangering other drivers

- vehicle dynamics (+ in rain, ice, snow, emergency etc)

...

I would guess to do these tasks with accuracy similar to humans approaches a problem space that's as difficult as general AI

some of these seemingly require the machine to have theory-of-mind which is general AI

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

#163

Post by ummonk » Thu, Jun 07, 2018, 6:25 PM UTC

natch wrote: post #128

stefan_ wrote: post #100

Earlier quoted context omitted.

It's a hardware limitation. If you have a radar, the only way to get a signal out of it is to ignore all stationary stuff.

That would make sense if the radar is stationary. In this case, the radar system itself is moving... including moving relative to stationary objects. So I don't see how what you say makes sense. Not saying you are wrong. Just saying I don't follow your explanation.

Right. Besides, pulse doppler can detect stuff that is stationary relative to the radar anyway.

The real issue is false positives from things like soda cans on the road, signs next to the road, etc. Can't have the car randomly braking all the time for such false positives. As a result, they just filter out stationary (relative to the ground) objects, and focus on moving objects (which are assumed to be vehicles) together with lane markings. This is why that one Tesla ran right into a parked fire truck.

Interestingly, I've discovered one useful trick with my purely camera-based car (Subary equipped with Eyesight): if there is a stationary or almost stationary vehicle up ahead that it wasn't previously following, it won't detect it and will consider it a false positive (as it should, so it doesn't brake for things like adjacent parked cars), but if I tap the brake to disengage adaptive cruise control and then turn the adaptive cruise control back on, it will lock on to the stopped car up ahead.

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

#164

Post by unethical_ban » Thu, Jun 07, 2018, 6:33 PM UTC

aerovistae wrote: post #15

unethical_ban wrote: post #11

Earlier quoted context omitted.

Without commenting on the rest of the issues with Musk/Tesla, his tweet about a news verification agency was a joke. Verifiably. It was nicknamed Pravda, and a corporation related to his tweet was registered to Musk on Oct 17 2017, the anniversery of the October Revolution.

A joke? It's verifiable because he said he might name it Pravda, and the fact that he actually registered it is further evidence that it's a joke? I'm not saying he's really going to do it, but I question your certainty here with a total lack of actual evidence.

Verifiably is a strong word on this site. Fair enough. I'm still right though.

Options:

* In 2018, A foreign-born Capitalist billionaire with sometimes negative press coverage suggests creating a Ministry of Truth named after a Russian propaganda newspaper to call out journalists who make false claims in their reporting. He registers a corporation for that purpose on the 100th anniversery of a bloody revolution bringing about the Soviet Union.

* A man known for using puns and showmanship in their communications trolled a bunch of people who latch onto his every word, especially when they don't like the man.

And to ComradeTaco, this isn't the presidency, and he didn't spout hate speech. It was a joke.

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

#165

Post by btilly » Thu, Jun 07, 2018, 6:33 PM UTC

stefan_ wrote: post #100

nathas wrote: post #94

Earlier quoted context omitted.

I find it hard to think that a group of engineers didn't consider stationary objects when _designing_ an autopilot system. I would no longer consider it a flaw if it was considered.

It's a hardware limitation. If you have a radar, the only way to get a signal out of it is to ignore all stationary stuff.

Here is a more technical explanation of the limit.

You send a radar signal out, then it bounces off of stuff and comes back at a frequency that depends on your relative motion to the thing it is bouncing back from. Given all of the stationary stuff around, there is a tremendous amount of signal coming back from "stationary stuff all around us", so the very first processing step is to put a filter that causes any signal corresponding to "stationary" to cancel itself out.

This lets you focus on things that are moving relative to the world around them. But makes seeing things that are standing still very hard.

Many animal brains play a similar trick. With the result that a dog can see you wave your hand a half-mile off. But if the treat is lying on the ground 5 feet away, it might as well be invisible.

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

#166

Post by databus » Thu, Jun 07, 2018, 6:33 PM UTC

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…

The First Law of Autopilot should be: Don't run into shit. If this fails then it's not autopilot, it's "Autocrash".

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

#167

Post by WiseWeasel » Thu, Jun 07, 2018, 6:34 PM UTC

dogma1138 wrote: post #53

MBCook wrote: post #3

“[Driver’s] hands were not detected on the steering wheel for the final six seconds prior to the crash. Tesla has said that Huang received warnings to put his hands on the wheel, but according to the NTSB, these warnings came more than 15 minutes before the crash.” This kind of stuff is why I’ve lost all faith in Tesla’s public statements. What they said here was, for all intents and purposes, a flat out lie. Clearly…

It’s feature maybe? After all after insane and ludicrous mode kamikaze kinda fits. I don’t understand why people had faith in AP 2.0 in the first place, especially since Tesla boasted that it took them only 6 months to develop it. And unlike AP 1.0 the regulated ADAS features were not enabled (officially as in outside of AP mode) on it for the longest time some still aren’t.

Suicidal mode - we'll make it look like an accident.

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

#168

Post by slg » Thu, Jun 07, 2018, 6:35 PM UTC

txcwpalpha wrote: post #161

slg wrote: post #158

Earlier quoted context omitted.

I simply don't know what to say to you if you are going to legitimately argue that shaving 20 feet off of braking distance will not make a car any safer. EDIT: The comment I was replying to was heavily edited after I responded. It originally said something along the lines of improving braking distance is good but there is no evidence that it would improve safety.

And yet again, the same OTA update changed other parameters about the way the car drives that do make it less safe. I don't know why you're trying to ignore that fact. If I drastically improve the braking distance of a car, but in the same update I also make it so that the car crashes itself into a wall and kills you, is the car safer? Hint: no As for your edit, you clearly misread the original comment, which is why…

I never denied that. Your comment pointed out a problem with OTA updates and I agreed calling it "a clear flaw". I pointed out a benefit of OTA updates then asked an open ended question about how they should be handled. You responded be attacking the example I provided. I was looking to debate this serious issue, not getting into a pissing match about it.

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

#169

Post by btilly » Thu, Jun 07, 2018, 6:35 PM UTC

dingaling wrote: post #155

stefan_ wrote: post #100

Earlier quoted context omitted.

It's a hardware limitation. If you have a radar, the only way to get a signal out of it is to ignore all stationary stuff.

That is not accurate. In fact one of the key features of radar processing is to find objects in the clutter, usually by filtering on Doppler shifts. As far back as the 1970s helicopter-mounted radars like Saiga were able to detect power lines and vertical masts. That one could do so when moving up to 270 knots and weighed 53kg.

For radar detecting a power line against the sky is easy. Detecting a power line against a wall is not.

The same radar set that worked these wonders while flying would have been absolutely useless for a ground based vehicle.

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

#170

Post by ytpete » Thu, Jun 07, 2018, 6:36 PM UTC

ckastner wrote: post #82

d0lph wrote: post #65

Earlier quoted context omitted.

Or perhaps us fingers-in-ears Musk fans don't expect the AP to be perfect. Especially considering how new the fields are. Autopilot doesn't need to be perfect, just better than humans.

It must also never be worse than humans. In this case, it very clearly was.

Except a human driver had just recently crashed in the exact same spot - that's why the divider's crash bumper was damaged at the time of the Tesla accident.

I think there's no excuse for shipping an "autopilot" system that can't detect massive, stationary objects in broad daylight, but humans also do crash in those exact circumstances all the time.