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

Tesla influencers tried coast-to-coast self-driving, hit debris before 60 miles

electrek.co

Post reply on HN
Print view View original

361–370 of 410 posts

Re: Tesla influencers tried coast-to-coast self-driving, hit debris before 60 miles

#361

Post by ModernMech »

xnx wrote: post #352
ModernMech wrote: post #248

Earlier quoted context omitted.

100% it would have. One of the main things the LiDAR system does is establish a "ground plane", which is the surface on which the car is expected to drive. Any hole or protrusions in that plane stick out like a sore thumb to a LiDAR system, you'll be able to see it in the raw data without much of a feature detector, so detecting them and reacting is fast and reliable. Contrast with Tesla's "vision-only" system, which…

In addition to detecting the object, Waymo has to make some determination about the material. Rigid heavy metal = slam on the brakes and/or swerve. Piece of tire or plastic bag = OK to run over if swerving or hitting the brakes would be more dangerous. Really hard problem that they're concerned about getting right before they open up highway driving.

LiDAR is also good for that because you can measure light remission and figure out how much of the LiDAR energy the material absorbed. Different materials have different remission properties which can be used to discriminate. Which is a compounding advantage because we tend to paint road line markers with highly reflective paints. This makes line markers blindly obvious to a LIDAR.

Re: Tesla influencers tried coast-to-coast self-driving, hit debris before 60 miles

#362

Post by verzali »

skeeter2020 wrote: post #228
tokioyoyo wrote: post #126

Earlier quoted context omitted.

In America, you fail the second you apologize or take accountability. Ignoring criticism and deflecting all the time gets you further, as it is part of the game. Unfortunately, this is just an accepted social science-y thing at this point. It is a very much cultural thing of the past couple of decades.

It's too bad, because "I'm sorry; this is my fault" is the biggest diffuser of anger and best way to appease mad customers. Try it sometime; the other party goes from ready to kill you to apologetic themselves (if you're genuine). Unfortunately it's seen as a sign of weakness by people like Elon and his cult of impersonators and an admission of liability by the litigious crowd. If you can be strong, confident and rea…

We once had a customer on a project that we'd messed up. I told the customer I was sorry about that and that I'd make an effort to fix the problem. I could see they were happy to hear that. But afterwards my manager called me at home and got mad I'd said sorry to them. His philosophy was never to apologize. Funny thing, later on that customer offered me a better paid position...

Re: Tesla influencers tried coast-to-coast self-driving, hit debris before 60 miles

#363

Post by jjav »

keyle wrote: post #97
SillyUsername wrote: post #60

A lot of apologists say that "a human would have hit that". That's kind of irrelevant, this technology is meant to be safer and held to a higher standard. Comparing to a human is not a valid excuse...

Indeed... You can see the driver reaching for the wheel, presumably he saw it coming, and would have hit the breaks. He left the car to do its thing thinking it knows better than him... maybe.

> presumably he saw it coming

Not presumably, we know for sure since they are talking about it for a long time before impact.

The point of the experiment was to let the car drive so they let it drive and crash, but we know the humans saw it.

Re: Tesla influencers tried coast-to-coast self-driving, hit debris before 60 miles

#364

Post by jjav »

lm28469 wrote: post #5

Two more years guys, just give him two more years, a few more billion, a bit more political power and I promise he'll give you your fancy self driving toy. (Repeat from 2012 ad infinitum)

> Two more years guys, just give him two more years, a few more billion, a bit more political power and I promise he'll give you your fancy self driving toy. (Repeat from 2012 ad infinitum)

The trillion dollar pay package will make it happen, that's what was missing.

Re: Tesla influencers tried coast-to-coast self-driving, hit debris before 60 miles

#365

Post by verzali »

peterfirefly wrote: post #138
tedggh wrote: post #95

Earlier quoted context omitted.

It depends where in the US you drive. It’s a big country with independent state governments. It’s like saying I was driving in Romania and I was shocked by how bad European highways are. I lived in Texas and the stuff I saw on the highway was crazy, vacuum cleaners, decorated Christmas trees and refrigerators. Most parts of the country interstate and highway systems are pretty clean.

Romania has pretty good highways now.

Belgium would be a better example of terrible roads

Re: Tesla influencers tried coast-to-coast self-driving, hit debris before 60 miles

#366

Post by jjav »

curiousObject wrote: post #10

It’s an accident that could also happen to an inattentive human driver. (Ask me how I know :( ) But, if you watch the car’s display panel, it looks as if the car didn’t see anything and just went full speed ahead. That’s not great. It should have slowed down and alerted the driver that something was there. I didn’t watch the complete video so maybe there’s more.

> It’s an accident that could also happen to an inattentive human driver. (Ask me how I know :( )

Anything "could" happen, but it would take an inordinately inattentive driver to be this bad.

They had 7-8 seconds of staring and talking about the debris before hitting it (or perhaps more, the video starts the moment the guy says "we got eh, a something", but possibly he saw it some instants before that).

So a person would need to be pretty much passed out to not see something with so much time to react.

Re: Tesla influencers tried coast-to-coast self-driving, hit debris before 60 miles

#367

Post by guywithahat »

jcranmer wrote: post #227
agildehaus wrote: post #30

A friend of mine who loves Tesla watched this video and said "many humans would have hit that". I feel we'll be hearing a lot of that excuse.

When the self-driving car killed a pedestrian several years ago, the initial sentiment on this site for the first few hours was essentially "those dastardly pedestrians, darting into traffic at the last second, how are you supposed to avoid them?" It took several hours for enough information to percolate through to make people realize that the pedestrian had been slowly and quite visibly crossing the road and the sel…

(Assuming I know which accident you're referring to) The car that killed the pedestrian in Florida wasn't using supervised full self driving, he was using autopilot (which was basically adaptive cruise control at the time).

Re: Tesla influencers tried coast-to-coast self-driving, hit debris before 60 miles

#368

Post by fuzzfactor »

jjav wrote: post #354
fuzzfactor wrote: post #307

Earlier quoted context omitted.

>asking a different question: how good would the FSD system be at completing a coast-to-coast trip? >They made it about 2.5% of the planned trip on Tesla FSD v13.9 before crashing the vehicle. This really does need to be considered preliminary data based on only one trial. And so far that's 2.5% as good as you would need to make it one way, one time . Or 1.25% as good as you need to make it there & back. People will…

> This really does need to be considered preliminary data based on only one trial. Statistically yes, but look at the actual facts of the case. A large object on the road, not moving, perfect visibility. And the Tesla drives straight into it. Not hitting static objects in perfect visibility is pretty much baseline requirement #1 of self driving. And Tesla fails to meet even this.

It does look like lower performance than a first-time driving student.

I really couldn't justify 1000:1 with such "sparse" data, but I do get the idea that these are some non-linear probabilities of making it back in one piece.

It seems like it could easily be 1,000,000:1 and the data would look no different at this point.

Re: Tesla influencers tried coast-to-coast self-driving, hit debris before 60 miles

#369

Post by anonymars »

ryandrake wrote: post #356
anonymars wrote: post #339

Earlier quoted context omitted.

I will never understand why people ask why those who bought a thing expected to get that thing Isn't that the bare minimum requirement for how commerce is supposed to function?

A surprising chunk of HN commenters earnestly believe that "caveat emptor" should be some kind of horrible default way of life. Like businesses should be able to sell anything they want, without regulation, as long as they can convince people to buy those things. And if those things don't work--well it's 100% the customer's fault for being so gullible and not being responsible for the company's quality.

I don't understand why people would want to live that way and argue against those who fight for better.

But my guess is that it's a defense mechanism, essentially the Just World fallacy. "It would really suck to have that bad thing happen to me through no fault of my own. *spoink!* I'm careful (and smart) therefore bad things won't happen to me" (https://dilbert-viewer.herokuapp.com/1999-09-08)

Re: Tesla influencers tried coast-to-coast self-driving, hit debris before 60 miles

#370

Post by foobarian »

jjav wrote: post #353
foobarian wrote: post #253

Earlier quoted context omitted.

What if there is no debris the other 999 times, and the system works fine? The video does not give me that information as a prospective Tesla customer. This looks like a fluke to me.

> What if there is no debris the other 999 times, and the system works fine? This argument makes no sense. I take it that you're saying that if we provide the Tesla a road which contains nothing to hit, it won't hit anything? Well, sure. Also, not interesting. In a real world drive of almost 3000 miles there will nearly always be things to avoid on the way.

> I take it that you're saying that if we provide the Tesla a road which contains nothing to hit, it won't hit anything?

Not quite. I am saying that basing the judgment on a rare anomaly is a bit premature. It's a sample size of 1, but I base this on my own driving record of 30 years and much more than 3000 miles where I never encountered an obstacle like this on a highway.

> Also, not interesting

I would have liked to see the planned cross-country trip completed; I think that would've provided more realistic information about how this car handles with FSD. The scenario of when there is a damn couch or half an engine on the highway is what's not interesting to me, because it is just so rare. Seeing regular traffic, merges, orange cones, construction zones, etc. etc. now that would have been interesting.

Post reply on HN