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

Self-Driving Teslas Are Fatally Rear-Ending Motorcyclists More Than Any Other

fuelarc.com

Post reply on HN
Print view View original

411–420 of 449 posts

Re: Self-Driving Teslas Are Fatally Rear-Ending Motorcyclists More Than Any Other

#411

Post by ModernMech »

plun9 wrote: post #318
ModernMech wrote: post #181

Earlier quoted context omitted.

I'm a roboticist who had learned from researchers involved in the 2007 DARPA urban challenge. The key takeaway from that event was that every single car that finished the race was equipped with the 3D velodyne LIDAR. It was that technology that enabled driverless cars to work as a concept. Why? Because it provided information that people had to infer, and that you couldn't easily get from camera. So absent the human…

Tesla's camera-based self-driving system is still likely at least five years away from being ready, Hall said. Still, he said, "Elon Musk is right about not needing lidar." https://www.bizjournals.com/sanjose/news/2022/11/09/heres-wh...

Hall was ousted from velodyne. He's salty.

  He began selling shares because he didn't like the direction of the company and was unhappy about being forced out of it, he told the Business Journal. From almost the moment he was pushed out until this spring, he fought a war with Velodyne in the press, at shareholder meetings and in the courts. Although the lawsuit he filed against the company is ongoing, he eventually decided the company was a "dump" and couldn't be salvaged.
https://archive.is/oxwoh

Re: Self-Driving Teslas Are Fatally Rear-Ending Motorcyclists More Than Any Other

#412

Post by tim333 »

bryanlarsen wrote: post #92

Prediction: over the next 4 years we're going to see lots of stories like this. Some of the stories will be fair, some won't. "Musk bad" stories get clicks. The next administration will be very anti-Tesla. Coincidentally, by that time self-driving will be considered mature enough to warrant proper regulation, rather than the experimental regulation status we have now. Combine the two, and the regulations will be writ…

>ultimate regulatory lock in monopoly...

In fairness to the regulators they have been pretty reasonable so far.

Re: Self-Driving Teslas Are Fatally Rear-Ending Motorcyclists More Than Any Other

#413

Post by tim333 »

marxisttemp wrote: post #381
Workaccount2 wrote: post #156

Earlier quoted context omitted.

What gets me is that there are no other brands in Tesla's league. Tesla is the only consumer car that has "FSD" level ability. The competitors have to use pre-mapped roads and availability is spotty at best. There is also risk as Chevy already deprecated their first gen "FSD", leaving early adopters with gimped ability and shutout from future expansions.

Aren’t you ignoring Waymo?

It's not 'consumer'.

Re: Self-Driving Teslas Are Fatally Rear-Ending Motorcyclists More Than Any Other

#414

Post by ModernMech »

kjkjadksj wrote: post #376
crote wrote: post #246

Earlier quoted context omitted.

There is a huge difference between measuring the distance to a single target a few miles away, and measuring the distance to dozens of moving, accelerating, and overlapping objects in close proximity to each other and to the reference point. Besides, rangefinding optics weren't exactly amazing in the 1940s either. It's why the introduction of radar made such a massive difference in naval warfare.

Autofocus systems are designed to stop race cars in travel today already. And besides, why argue hypotheticals here when I look out my window and I see teslas self driving just fine? The system is proven despite your feelings about it. And if it was truly unsafe or compromised we'd have seen a good deal of evidence a this point what with the amount of users self driving and the mileage they've been traveling, not to…

> why argue hypotheticals here when I look out my window and I see teslas self driving just fine?

I'll reiterate:

  2019 - Tesla didn’t fix an Autopilot problem for three years, and now another person is dead
That's not a hypothetical. How do you figure this result indicates the Tesla theory of camera-only navigation is working out "just fine"? This level of professional negligence should be considered a crime.

> And if it was truly unsafe or compromised we'd have seen a good deal of evidence

We see that evidence all the time. Teslas veering into oncoming traffic, hitting parked vehicles, driving through loony tunes walls where other cars stop, being fooled by smokescreens where other cars are not, and decapitating multiple people in a similar way that would have been mitigated by LiDAR. And now apparently real-ending motorcyclists.

This whole self driving scam is an exercise in the 80/20 rule. They spent 20% of the time to get 80% of the results, and that's why you claim "I see teslas self driving just fine"

But Tesla has been promising the other 20% will be here in 5 years for 10 years. That last 20% is the difference between the system being "Full" self driving and a fraud. Right now what we see is a vaporware fraud, and they're not going to be able to deliver.

Re: Self-Driving Teslas Are Fatally Rear-Ending Motorcyclists More Than Any Other

#415

Post by Workaccount2 »

sroussey wrote: post #174
Workaccount2 wrote: post #156

Earlier quoted context omitted.

What gets me is that there are no other brands in Tesla's league. Tesla is the only consumer car that has "FSD" level ability. The competitors have to use pre-mapped roads and availability is spotty at best. There is also risk as Chevy already deprecated their first gen "FSD", leaving early adopters with gimped ability and shutout from future expansions.

FSD meaning level 2? Lots of those.

Please, I'd love to know because I want an FSD like system and don't want to buy a Tesla.

As far as I am aware, everyone else's offerings only work in pre-mapped areas, i.e. Chevy's system only covers half my commute.

Re: Self-Driving Teslas Are Fatally Rear-Ending Motorcyclists More Than Any Other

#416

Post by bumby »

Retric wrote: post #313
bee_rider wrote: post #247

Earlier quoted context omitted.

There are cases where cars do need to move. * train tracks as mentioned by another comment * getting out of the way of emergency vehicles or following instructions from emergency workers I don’t think this detracts from the overall point—if the uptime is very good then the times when LiDAR doesn’t work and the car needs to move might practically never happen. Or the car might be able to move forward to a safe positio…

The same basic questions arise for things like a tire blowout. At minimum cars need to handle being on a curve when LiDAR or vision etc cuts off. Stopping on a freeway or railroad is a real risk even if people can get out, but now you’re doing risk mitigation calculations not just trying to handle normal driving. “What if someone is asleep in a level 5 car?” is a question worth considering, but we’re a long way self…

We absolutely should expect safety critical software to mitigate risk. The idea of “welp, the software is confused so just toss it back to a human” is a cop-out in risk mitigation. At the most generous, it constitutes an “administrative” control, which is the least preferred option, tantamount to giving directions in the users manual. The general control hierarchy is: remove the hazard, engineering control, PPE, administrative control.

Re: Self-Driving Teslas Are Fatally Rear-Ending Motorcyclists More Than Any Other

#417

Post by jamincan »

plun9 wrote: post #342
fsh wrote: post #20

This problem has been solved more than a decade ago by radar sensors (standard on many mid-range cars at the time). They detect imminent collisions with almost perfect accuracy and very little false positives. Having better sensor data is always going to beat trying to massage crappy data into something useful.

This isn't true. You can try using adaptive cruise control with lane-keeping on a radar-equipped car on an undivided highway. Radar is good at detecting distance and velocity, but can't see lane lines. In order to prevent collisions, you would need to know precisely the road geometry and lane positions, which may come from camera data, and combine that information with the vehicle information.

I do this all the time with no problem at all. I drive a 2023 VW Taos, for what that is worth.

Re: Self-Driving Teslas Are Fatally Rear-Ending Motorcyclists More Than Any Other

#418

Post by jamincan »

senkora wrote: post #248

I see a lot of people saying that this isn't statistically significant. I think that that is probably true, but I also think that it is important to do the statistical test to make sure: tesla.mult = c(1/(5:2),1:5) data.frame(tesla.mult = tesla.mult, p.value = sapply(tesla.mult, (function(tesla.mult) { poisson.test(c(5, 0), c(tesla.mult, 1))$p.value }))) tesla.mult p.value 1 0.2000000 0.0001286008 2 0.2500000 0.00032…

Even though other manufacturers may not be reporting these numbers, Level 2 ADAS systems are pretty common as far as I can tell. Wouldn't any vehicle with adaptive cruise control and lane-keep assist be considered Level 2 ADAS?

Re: Self-Driving Teslas Are Fatally Rear-Ending Motorcyclists More Than Any Other

#419

Post by turnsout »

tordrt wrote: post #407
turnsout wrote: post #166

Earlier quoted context omitted.

His biographer estimates his IQ is 100-110. [0] [0] https://x.com/SethAbramson/status/1892710698683142638

Thats ridiculous. His SAT scores puts him in the top 2 percent https://www.noahpinion.blog/p/only-fools-think-elon-is-incom...

[flagged]

Re: Self-Driving Teslas Are Fatally Rear-Ending Motorcyclists More Than Any Other

#420

Post by whiplash451 »

bitmasher9 wrote: post #58
whiplash451 wrote: post #35

Earlier quoted context omitted.

Why are we moving the goal posts to « other manufacturers drive less miles so statistically it’s still OK to kill people »?

I would like the goal post somewhere around “Is safer in every situation than a skilled and concentrated human driver”

Right, and so by that standard, self-driving companies should have literally zero death attributed to them per year given how few miles they drive compared to human drivers.

That is: until self-driving cars ride much more, obviously.

Post reply on HN