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

Tesla reports another Robotaxi crash

electrek.co

Post reply on HN
Print view View original

111–120 of 165 posts

Re: Tesla reports another Robotaxi crash

#111

Post by Zigurd »

fpoling wrote: post #36
_aavaa_ wrote: post #25

Earlier quoted context omitted.

Having multiple sources of data is a benefit, not a problem. Entire signal processing and engineering domains exist to take advantage of this. Even the humble Kalyan filter lets you combine multiple noisy sources to get a more accurate result than would be possible if using any one source.

Kalman filters and more advanced aggregators add non-trivial latency. So even if one does not care about cost, there can be a drawback from having an extra sensor.

Cars and roads are built for human reaction times. That's why you have low speed limits in urban areas. You can have a pile of latencies attributable to processing a scene and still have superhuman reaction time that contributes to outperforming humans.

It's analogous to communications latency. High latencies are very annoying to humans, but below a threshold they stop mattering.

Re: Tesla reports another Robotaxi crash

#112

Post by _ea1k »

mmooss wrote: post #86
_ea1k wrote: post #74

I spent a little bit of time poking at Gemini to see what it thought the accident rate in an urban area like Austin would be, including unreported minor cases. It estimated 2-3/100k miles. This is still lower than the extrapolation in the article, but maybe not notably lower. We need far higher quality data than this to reach meaningful conclusions. Implying conclusions based upon this extrapolation is irresponsible.

I don't understand how Gemini's fabrication has any validity. What is it based on?

It is at least as reliable as the data in the electrek article. My point is that the data naturally has error margins that are clearly large enough to make drawing concrete conclusions impossible.

Re: Tesla reports another Robotaxi crash

#113

Post by 93po »

Mawr wrote: post #103
93po wrote: post #62

Electrek notoriously lies and fibs and stretches the truth to hate on Tesla and Elon as much as possible when it serves their own best interests. This one is misleading both in that 8 "crashes" is statistically insignificant to draw conclusions as to its safety compared to humans, but also because these 'crashes' are not actually crashes and instead a variety of things, including hitting a wild animal of unknown size…

Tesla is free to provide information that debunks these claims. They're the ones who redacted the details of the incidents in the first place.

This is the state of accepted journalism now? Fabricate ridiculous claims and then make the target of your hit piece responsible for refuting it?

Re: Tesla reports another Robotaxi crash

#114

Post by guywithahat »

karlgkk wrote: post #50
guywithahat wrote: post #43

Earlier quoted context omitted.

What I've heard out of Elon and engineers on the team is that some of these variations of sensors create ambiguity, especially around faults. So if you have a camera and a radar sensor and they're providing conflicting information, it's much harder to tell which is correct compared to just having redundant camera sensors. I will also add in my personal experience, while some filters work best together (like imu/gnss)…

Counterpoint: Waymo > solid engineering defense for moving towards just computer vision COUNTERPOINT: WAYMO

From my previous comment, in case you didn't see it

> Again Waymo's lead suggests this logic might be wrong but I think there is a solid engineering defense for moving towards just computer vision. Cameras are by far the best sensor, and there are tangible benefits other than just cost.

Re: Tesla reports another Robotaxi crash

#115

Post by guywithahat »

ambicapter wrote: post #47
guywithahat wrote: post #43

Earlier quoted context omitted.

What I've heard out of Elon and engineers on the team is that some of these variations of sensors create ambiguity, especially around faults. So if you have a camera and a radar sensor and they're providing conflicting information, it's much harder to tell which is correct compared to just having redundant camera sensors. I will also add in my personal experience, while some filters work best together (like imu/gnss)…

I don’t understand how running into difficulties when trying to solve a problem can be interpreted as “[taking] away from the actual problem”.

In our case if we're spending a lot of time on something that doesn't improve the product, it just takes away from the product. Like if we put 800 engineering hours into sensor fusion and lidar when the end product doesn't become materially better, we could have placed those 800 hours towards something else which makes the end product better.

It's not that we ran into problems, it's that the tech didn't deliver what we hoped when we could have used the time to build something better.

Re: Tesla reports another Robotaxi crash

#116

Post by altairprime »

kevin_thibedeau wrote: post #12
altairprime wrote: post #8

Slap a STUDENT DRIVER bumper sticker on them so we can all give them space!

It should say INDUSTRIAL ROBOT. You wouldn't willingly enter the hazard zone of a KUKA. Why should we casually accept them roaming free?

Most people don’t know that characteristic of industrial robots, so it wouldn’t inspire the wariness necessary to keep the novice robotic vehicles safe from us all assuming predictability of them. And those who do know what it means would assume predictable behaviors, since that’s what industrial robots have, which is doubly problematic since now they’ll be unprepared for SQUIRREL input, RED OCTAGON output neural network misfirings.

Re: Tesla reports another Robotaxi crash

#117

Post by guywithahat »

vjvjvjvjghv wrote: post #101
fpoling wrote: post #40

Earlier quoted context omitted.

Well we know that vision works based on human experience. So few years ago it was a reasonable bet that cameras alone could solve this. The problem with Tesla is that they still continue to insist on that after it became apparent that vision alone with the current tech and machine learning does not work. They even do not want to use a radar again even if the radar does not cost much and is very beneficial for safety.

Human vision is terrible in conditions like fog, rain, snow, darkness and many others. Other sensor types would do much better there. They should have known that a long time ago.

To be fair, lidar is arguably worse in rain and snow. I don't think we know of a sensor yet which works well in these conditions

Re: Tesla reports another Robotaxi crash

#118

Post by phyzome »

_ea1k wrote: post #65
phyzome wrote: post #22

Earlier quoted context omitted.

Converting things to rates is how you understand them in a meaningful way, particularly for things that are planned to be expanded to full scale. (The one thing I would like to see done differently here is including an error interval.)

Yeah, I'm glad that they are trying to do a rate, the problem is that the numerator in the human case is likely far larger than what they are indicating. Of the Tesla accidents, five of them involved either collisions with fixed objects, animals, or a non-injured cyclist. Extremely minor versions of these with human drivers often go unreported. Unfortunately, without the details, this comparison will end up being a c…

With Tesla redacting as much as they are, I think we have to assume the worst.

Re: Tesla reports another Robotaxi crash

#119

Post by phyzome »

dylan604 wrote: post #38
phyzome wrote: post #21

Earlier quoted context omitted.

...why would "more than 10x less safe than a human driver" be "not too bad"?

It could have been 100x or 1000x or...

The entire premise of self-driving cars, at least from a policy perspective, is "safer than human drivers".

Re: Tesla reports another Robotaxi crash

#120

Post by cosmicgadget »

cn-watch wrote: post #95
randoglando wrote: post #92

Earlier quoted context omitted.

He's a complicated figure. He has done so much good as well. EVs in the US and reusable rockets owe a lot to him. OTOH, so does the cesspool that is X.

There are no elon musk museums. There are no elon musk hospitals. There are no elon musk centers for unwed mothers. How could the richest man in the world give so little back.

It probably doesn't help but Elon himself is a center for unwed mothers.
Post reply on HN