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

Why emergency braking systems sometimes hit parked cars and lane dividers

arstechnica.com

Post reply on HN
Print view View original

51–60 of 244 posts

Re: Why emergency braking systems sometimes hit parked cars and lane dividers

#51

Post by joe_the_user »

rayiner wrote: post #31

What this shows is that Tesla isn’t even on the path to self-driving technology. It sounds like “Autopilot” has no world model (or an extremely basic one)—it ignores stationary objects because it can’t tell whether it’s approaching something on the side of a road that curves away versus an obstacle in the lane. It can’t tell because it doesn’t know what the car is going to do and what the lane is going to do. That’s…

Do we know that "having a world model" is how self-driving cars ought to go?

It sounds like most self-driving systems have several systems that relate to each other (which each, at least implicitly, have a world model). It's hard to know if they should instead have a single world model that all information is extracted from or whether they should improve the integration of their existing systems. I am think you show humans tend to have several world-models at different levels of exactness when dealing with the world (which doesn't prove a car should have that - complete consistency seems to have advantages here - seems is the word).

Perhaps one could say - "despite various kind of progress, it's not obvious what direction to take for full self-driving cars".

Re: Why emergency braking systems sometimes hit parked cars and lane dividers

#52

Post by dchichkov »

rayiner wrote: post #31

What this shows is that Tesla isn’t even on the path to self-driving technology. It sounds like “Autopilot” has no world model (or an extremely basic one)—it ignores stationary objects because it can’t tell whether it’s approaching something on the side of a road that curves away versus an obstacle in the lane. It can’t tell because it doesn’t know what the car is going to do and what the lane is going to do. That’s…

It might be even worse than that. They likely think that they are on the path, because they are running a massive data-collection campaign on the sensor suite installed on the fleet. But the reality might be different. Running a data collection campaign is easy. Engineering products with machine learning is hard. Most of the teams don't even know what they need to know, to do it right. And so they engage into classical cargo cult of "carving wooden headphones". Regretfully, this is unlikely to change soon. It takes a decade to hone skills of building products with any technology. And the majority of people in the field are yet to join it.

Re: Why emergency braking systems sometimes hit parked cars and lane dividers

#53

Post by amelius »

Retric wrote: post #48
paulie_a wrote: post #32

Earlier quoted context omitted.

Let's be honest, actual mass deployed self driving tech is probably 20 years away at minimum. I personally might be able to enjoy it just before I retire.

I think these are already fairly close to human fatality rates. Tessa is well over 300,000 cars sold, if the average car has 10k miles that's 3 billion. Edit: actual number well over that https://electrek.co/2016/11/13/tesla-autopilot-billion-miles... Using US fatality rates you would expect ~34 deaths from that. https://en.m.wikipedia.org/wiki/Transportation_safety_in_the... Edit, my numbers where low. So, as far as…

That's a lot of guesswork. It is very difficult to believe that an automated system with such a limited concept of its surroundings is equal/superior to a human driver. Therefore, we need better evidence, and this means no pulling of numbers from thin air.

Re: Why emergency braking systems sometimes hit parked cars and lane dividers

#54

Post by DannyBee »

raverbashing wrote: post #11

I still don't get why do Autocrasher systems think it's better to ignore stationary objects even whey it's driving towards it at a high speed! Sure, slamming in the brakes is a bad idea. This doesn't mean the system can't start to slow down or change the direction of the car.

So, they don't slam on the breaks at highway speed but they do actually often do things not mentioned by the article.

The 2014 Audi I used to have would do different things depending on the calculation it made on how close you were to crashing:

1. Pre-tension the seat belts

2. Increase the braking power (IE needs lighter push)

3. Close the side windows and roof

4. Turn on hazard lights

5. Give you a slight jerk through braking to try to warn you. etc

The first one alone helps a lot. https://crashstats.nhtsa.dot.gov/Api/Public/ViewPublication/...

(13% fatality reduction)

Now, most cars will do this these days, and do it using the same sensors they need to trigger air bag deployment even without ACC.

I don't know of any study that tries to estimate the effects of doing it earlier like the Audi with ACC does (IE no study tries to evaluate whether the ones without ACC sensors have achieved the optimal amount of pre-tension in the time they have, which would make pre-tensioning them earlier like the ACC systems do pointless)

Re: Why emergency braking systems sometimes hit parked cars and lane dividers

#55

Post by Shivetya »

fhrow4484 wrote: post #4

This is a pretty good explanation of the shortcomings of today's assisted driving capabilities. The marketing towards 'self driving' or 'auto pilot' should really emphasize on these. My guess here is that the lane assist and adaptive cruise systems somehow thought the car it was following switched one lane to the right, and so the Tesla assumed it was on the most left lane, without any moving car in front (hence acce…

While the author implied that other system would act the same as Tesla they then go on to explain that most other systems are no where as integrated as the Tesla system implies that it is. In other words, Tesla cannot use the excuse that AEB is separate from cruise. They still have not taking down the picture on their Autopilot page which shows a driver with his hands in his lap [1].

So if current systems cannot or will not acknowledge objects not in motion even if they are in the path of travel why is the NTSB allowing them on the road? Why not force the issue and require it. It really seems that far too many bought into images of what marketers promised by interpreting them to be akin to what is seen in movies and TV shows (enhance!).

[1] https://www.tesla.com/autopilot

Re: Why emergency braking systems sometimes hit parked cars and lane dividers

#56

Post by Retric »

amelius wrote: post #53
Retric wrote: post #48

Earlier quoted context omitted.

I think these are already fairly close to human fatality rates. Tessa is well over 300,000 cars sold, if the average car has 10k miles that's 3 billion. Edit: actual number well over that https://electrek.co/2016/11/13/tesla-autopilot-billion-miles... Using US fatality rates you would expect ~34 deaths from that. https://en.m.wikipedia.org/wiki/Transportation_safety_in_the... Edit, my numbers where low. So, as far as…

That's a lot of guesswork. It is very difficult to believe that an automated system with such a limited concept of its surroundings is equal/superior to a human driver. Therefore, we need better evidence, and this means no pulling of numbers from thin air.

Insurance companies which have hard data will lower your rates if your car has autopilot. I am sure they base that on hard data I don't have.

If you have better data than I would love to see it. But, IMO using ballpark numbers is much better than simply having a bad feeling about something.

These cars are not going to fail the same way people do. Computers really fuck up in broad daylight, people get drunk and drive down highways in the wrong direction.

Right now I would trust this over me driving tired or drunk but not sober. Give it 5-10 years and better hardware and I think it will be a better driver than I am.

Re: Why emergency braking systems sometimes hit parked cars and lane dividers

#57

Post by drblast »

I don't follow this that closely and I've tended to think of self-driving cars as an inevitable thing that results from march toward a "perfect" system.

But I think one of our blind spots as a culture is the assumption that nothing bad will happen if you drive a car correctly and follow all of the rules, and I think that assumption might prove to be wrong and that collisions are an inherent aspect of driving a car in an unpredictable world.

We as humans like to feel like we're in control of our lives, and I think that we have a prejudice toward looking at situations as if that were true, and that bad outcomes are the result of bad decisions instead of bad luck.

Re: Why emergency braking systems sometimes hit parked cars and lane dividers

#58

Post by forapurpose »

newnewpdro wrote: post #34
Merad wrote: post #30

Earlier quoted context omitted.

My parents bought a new 2018 Camry a few weeks ago that came with a manual roughly an inch thick. Expecting anyone to read it is bordering on delusional. I say this as someone who often does read manuals (because I’m a nerd).

Not even bothering to flip through a meager 1" thick manual for a newly acquired automobile strikes me as negligent. At least review the sections covering features you've never had in a vehicle before, geez.

> Not even bothering to flip through a meager 1" thick manual for a newly acquired automobile strikes me as negligent.

Perhaps, but then almost everyone is negligent. The car designers (and the whole world) know that well, so to depend on people reading the manual is disingenuous and dangerous.

Re: Why emergency braking systems sometimes hit parked cars and lane dividers

#59

Post by YeGoblynQueenne »

>> So the people designing the next generation of autonomous driving systems are going to need a fundamental philosophical shift. Instead of treating cruise control, lane-keeping, and emergency braking as distinct systems, advanced driver assistance systems need to become integrated systems with a sophisticated understanding of the car's surroundings.

My understanding was that self-driving systems are trained end-to-end to do simultaneous localization and mapping (a.k.a. SLAM [1]). In other words, the same model would control breaking, accelerating, lane keeping and everything else.

In fact, I thought this was why Uber had switched off its car's built-in breaking system- because their AI had taken over breaking and the AEB on the car would interfere with the self-driving.

Perhaps that is not the case for Tesla in particular, though?

_______________

[1] https://en.wikipedia.org/wiki/Simultaneous_localization_and_...

Re: Why emergency braking systems sometimes hit parked cars and lane dividers

#60

Post by smogcutter »

dchichkov wrote: post #52
rayiner wrote: post #31

What this shows is that Tesla isn’t even on the path to self-driving technology. It sounds like “Autopilot” has no world model (or an extremely basic one)—it ignores stationary objects because it can’t tell whether it’s approaching something on the side of a road that curves away versus an obstacle in the lane. It can’t tell because it doesn’t know what the car is going to do and what the lane is going to do. That’s…

It might be even worse than that. They likely think that they are on the path, because they are running a massive data-collection campaign on the sensor suite installed on the fleet. But the reality might be different. Running a data collection campaign is easy. Engineering products with machine learning is hard. Most of the teams don't even know what they need to know, to do it right. And so they engage into classic…

I mean, I'm also pessimistic about self driving cars, but I think it's reasonable to assume that Tesla engineers are aware that machine learning is hard.
Post reply on HN