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

A Tragic Loss

teslamotors.com

Post reply on HN
Print view View original

121–130 of 511 posts

Re: A Tragic Loss

#121

Post by mdorazio »

TaylorGood wrote: post #14

As most of you have already seen, Autopilot has detected similar situations: https://www.youtube.com/watch?v=9X-5fKzmy38

It's only similar in terms of "vehicle pulls in front of the Model S". The type of vehicle (car vs. truck), time of day, traffic pattern, etc. all seem to be quite different based on the sparse information in the article. I will also point out that as you have already seen, Autopilot failed in a "similar situation" as well: http://www.digitaltrends.com/cars/tesla-s-summon-under-trail...

Re: A Tragic Loss

#122

Post by krschultz »

Johnie wrote: post #89
krschultz wrote: post #41

Earlier quoted context omitted.

Autopilot uses a forward facing camera & radar. It sounds like the truck came in at a perpendicular angle. It may have been in the cone of sight for the camera but not the radar depending on how those are setup. The 360 degree sensors on the Tesla are for parking only ( Personally when I worked on a self driving car we were going with 360 degree camera and doing path planning based on that, but Tesla has opted not to…

Doesn't a 360 degree camera require it to be placed on top of the car?

You could merge multiple cameras in software, it's actually pretty straightforward to stitch them together in OpenCV. Basically just have to correct for the difference between cameras & their physical locations, but that is trivial since they are statically mounted on the car.

Re: A Tragic Loss

#123

Post by angusb »

BinaryIdiot wrote: post #21

I mean I understand Tesla has to make a statement here and I understand they want to ensure everyone that it's not really their fault but to title a post "A Tragic Loss" and then spend the majority of the post discussing all of your car's safety features and how it wasn't your fault just seems tone deaf and distasteful to me. Maybe they had to do it for legal reasons I don't know (I'm certainly not a lawyer) and I'd…

It's not just about Tesla though.

They have to defend autopilot not only to protect the brand but to protect the public's perception of autonomous vehicles in general.

Self driving tech is poised to save many many lives. So from a utilitarian perspective, it's probably justified to take extraordinary measures to make sure reactionary media and public whim doesn't kill it off, however uncomfortable that might seem in the short term.

Whilst this case is incredibly sad (and I don't want to downplay that in any way), if you're trying to minimise the overall amount of fatal crashes, exonerating the tech is the priority (if it is truly not at fault).

Re: A Tragic Loss

#124

Post by Splines »

All I can say is that I would not want to be a Tesla engineer on the Autopilot feature.

And I know what you're thinking - it's not because I think some poor engineer is going to get the axe (ok, maybe that's not what you're thinking). It's because I would not want to be responsible for the code that needs to deliver millions of people billions of miles in their car. It's a daunting responsibility.

Re: A Tragic Loss

#125

Post by vkou »

coralreef wrote: post #52
fixermark wrote: post #12

Earlier quoted context omitted.

the fact that they could. Imagine how many press releases there'd be per day if another auto company felt compelled to do one for each accident their cars were involved in.

This release only happened because Tesla knew it would make headlines, and wanted to get out in front before a sensationalized story gets out first. Other auto accidents are non-interesting to the public, but this one involved automated driving.

What's sensationalized about 'Tesla's autopilot that encourages inattentive driving misses a big white trailer crossing the freeway'?

This is as bad as it sounds.

Re: A Tragic Loss

#126

Post by gjem97 »

mozumder wrote: post #97
jackpirate wrote: post #11

Earlier quoted context omitted.

This statement is also disengenuous: This is the first known fatality in just over 130 million miles where Autopilot was activated. Among all vehicles in the US, there is a fatality every 94 million miles. Worldwide, there is a fatality approximately every 60 million miles. The wording implies that these numbers are directly comparable, but they are not. I would guess that Autopilot is much more likely to be activate…

Also, the US fatal accident rate is one death per 108 million miles, which includes motorcycles and teens and drunk people. Not only that, you'd expect drivers in the higher-income demographic of US auto customers to have less fatal accidents. The real comparison should between a model S and cars like the Mercedes S-Class, since this is all about car marketing anyways.

> Not only that, you'd expect drivers in the higher-income demographic of US auto customers to have less fatal accidents.

What? Why?

Re: A Tragic Loss

#127

Post by agumonkey »

The situation is a bit confusing, did the tractor cross in a hurry just before impact ? was the victim really blinded by the colors ? maybe it's just vocabulary, a tractor trailer seems huge and hard to ignore.

Even though I'm eager to see SDV benefits, Autopilot seems like way too much hassle for such possible consequences. An overengineered auto cruise.

Re: A Tragic Loss

#128

Post by mdorazio »

BookmarkSaver wrote: post #86
return0 wrote: post #8

Tesla should not allow autopilots. They have nothing to gain by the negative publicity they will get from cases like these. Regardless of how bad luck the driver had, tesla can always be blamed for relaxing the driver's reflexes by giving a false sense of safety. It doesnt matter if it was by default turned off or hidden in menus. What other companies use this kind of driving assist system? The ones i know are only h…

>Tesla should not allow autopilots. They have nothing to gain by the negative publicity they will get from cases like these. This is literally the only way to develop such systems. And regardless of incidents like this, these systems will be developed sometime in the fairly near future and whichever company is on the leading edge of them will command a massive new market that will probably start growing incredibly ra…

This is just factually incorrect. Google is developing self-driving tech just fine without releasing it to consumers as a "beta". So is Delphi. So, presumably, is Uber now. Personally I am also of the opinion that releasing autopilot in its current state (especially with the weak sensors) was not a good move in terms of safety for drivers. Great move for PR and gaining data, yes, but we can now make a very plausible argument that it has killed at least one person.

Re: A Tragic Loss

#129

Post by krschultz »

mikeash wrote: post #104
krschultz wrote: post #85

Earlier quoted context omitted.

I don't think it's nasty, I think it's realistic. I also think that it aligns with the research that shows humans take a significant amount of time to adjust to taking back over control from autopilot. This is one of the primary design considerations behind the Google self driving car having absolutely no steering wheel or brake. The illusion of humans being able to be the fallback when they're not physically capable…

I don't think it's realistic to rampantly speculate about a situation where so little information is available. And I absolutely think it is nasty to talk ill of the dead when there is zero evidence for what's being said. For all we know the driver had half a second to react before he died. Or maybe he had five minutes. The point is, we don't know. To start from that position and say it's "likely... the driver was sc…

Fair, I wasn't reading it as a knock on the driver. I read it as a mistake for Tesla to hide behind the driver having ultimate responsibility when the reality is no driver is going to actually be attentive or even capable of taking over.

Re: A Tragic Loss

#130

Post by calvinbhai »

mikeash wrote: post #45
petercooper wrote: post #16

Neither Autopilot nor the driver noticed the white side of the tractor trailer against a brightly lit sky, I'm intrigued that the color is relevant in the car's case - wouldn't it be using some sort of radar to detect and map objects rather than vision? I appreciate I am probably missing something.

Tesla's Autopilot uses a radar unit, a front-facing camera, and twelve ultrasonic sensors on the front and back bumper. The ultrasonic sensors are short range and are for detecting adjacent cars and obstacles while parking, the camera is used for detecting lanes, and the camera and radar work together to detect cars. The radar is low to the ground and probably doesn't pick up a trailer that's high off the ground. The…

This is pretty much what I was told during a Model S test drive recently, by the store associate. He was quite clear on what it can and cannot do.
Post reply on HN