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

Scenarios in which Tesla FSD Beta 9.0 fails

twitter.com

Post reply on HN
Print view View original

331–340 of 502 posts

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#331

Post by nullc »

CyanLite2 wrote: post #296
Animats wrote: post #203

Earlier quoted context omitted.

The monorail video is jaw-dropping. Yes. Pause the video and look at the car's screen. There's no indication on screen of the columns. A car on the other side of the row of columns is recognized, but not the columns. It's clear that Tesla has a special-purpose recognizer for "car". The columns are a solid obstacle almost impinging into the road, one that doesn't look like a car. That's the standard Tesla fail. Most h…

LIDAR cost is coming down, but Tesla has almost no margins on cars. So adding a $500 part per car for LIDAR is out of the question. Even the cheap radar parts were removed from production going forward. However, it's good to see other automakers like Volvo going the LIDAR route on their 2022 electric models and are offering Level3 autonomous driving.

Teslas' margins are several times larger than other automakers ... but the company valuation isn't particularly justified even at the current high margins.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#332

Post by cromwellian »

All of the Tesla fanboys saying you don't need LIDAR, RADAR, or Maps as a kind of "ground truth" and you can get by on video only should take this as a huge repudiation of brag by Musk.

Look, Radar, Lidar, and Maps aren't perfect. A map can be wrong, Radar can have false echos, Lidar can have issues in bad weather, etc. But if you're depending on visual recognition of one-way signs, having a potentially out-of-date backup map to check your prediction again, and err on the side of caution, is better than having no Map at all.

Ditto for radar and lidar. Radar enabled cars have collided with semis, remember, because they're aimed low (underneath the semi). But in the case of these planters, or road cones, or monorail poles, the radar is going to be a strong signal to the rest of the system that it isn't seeing something.

There's no way FSD should be allowed on public roads, it's not even CLOSE to ready. The other car companies are behaving far more responsibility: full sensor suite, multi-sensor fusion, comparison with detailed road maps, and limiting operation to safe areas, and expanding as safety is proven.

Who the hell cares if it's not FSD driving if its so dangerous? I'll take 75% FSD that only operates on highways and long commutes or road trips, over 100% FSD that has so many disengagements and "woah" moments as to be unusable.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#333

Post by marvin »

BugsJustFindMe wrote: post #186
AlexandrB wrote: post #157

Earlier quoted context omitted.

The monorail posts and planters would be trivially handled by LIDAR. Tesla's aversion to time of flight sensors often strikes me a premature given our level of planning/perception technology.

They should be trivially handled by stereopsis and structure from motion as well. Stereo+time photogrammetry has been solved well enough to not steer directly towards large obstacles for decades. Overreliance on machine learning pixel models to classify everything in view is the real problem.

If it's so easy, there must be a reason why Tesla's team hasn't accomplished it. They're not idiots.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#334

Post by paulryanrogers »

schmorptron wrote: post #285
jazzyjackson wrote: post #209

Earlier quoted context omitted.

I feel like the Xbox Kinect from 2010 would be a better vision solution than what they’ve got here, at least for the 20 feet ahead of you.

Until you have multiple cars trying to project multiple arrays of infrared dots onto objects 20 meters away in bright sunlight and then getting an accurate reading on which of the array kerfuffle is theirs.

Does radar have this crosstalk problem as well?

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#335

Post by TheParkShark »

cromwellian wrote: post #332

All of the Tesla fanboys saying you don't need LIDAR, RADAR, or Maps as a kind of "ground truth" and you can get by on video only should take this as a huge repudiation of brag by Musk. Look, Radar, Lidar, and Maps aren't perfect. A map can be wrong, Radar can have false echos, Lidar can have issues in bad weather, etc. But if you're depending on visual recognition of one-way signs, having a potentially out-of-date b…

I see this argument a lot. This is a small beta test and I have yet to see anything better on a larger scale. Most drivers shouldn’t be allowed on public roads yet here we are. Why are you so full of fear and anger over this? Isn’t this a place for open discussion?

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#336

Post by CyanLite2 »

Invictus0 wrote: post #310
CyanLite2 wrote: post #296

Earlier quoted context omitted.

LIDAR cost is coming down, but Tesla has almost no margins on cars. So adding a $500 part per car for LIDAR is out of the question. Even the cheap radar parts were removed from production going forward. However, it's good to see other automakers like Volvo going the LIDAR route on their 2022 electric models and are offering Level3 autonomous driving.

Tesla's Full Self Driving package was between 8 and 10,000 dollars per vehicle. That should cover it.

The hardware suite is the same on every car nowadays. They want FSD to be a downloadable app like a subscription. Which means you would have to put LIDAR on every car even if it didn't convert to FSD.

Also, Elon has gone on Twitter rants several times before against LIDAR. That horse has already left the stable and it ain't coming back.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#337

Post by edude03 »

mritun wrote: post #123

Question: Would it be awesome if FDA allowed Pharma to conduct drug-tests like this? Put a "beta-2.9" on the vial and let people try it out... Some may die, be disabled or may linger in vegetative state life-long, but it was their choice afterall and the it can argued that medicinal side-effects are very small cause of mortality and hence long-term the "public beta tests" will make drugs more effective and save more…

I'm pretty sure this is a logical fallacy. In the case of medications it's actually a fairly common situation where a patient has a terminal illness that there is no treatment available for, but you can get it on "the blackmarket" and in that case, it's either die for sure, or maybe not die, and in that case having a beta makes sense - it ensures you're atleast getting the thing you think you're getting.

To me autonomous vehicles are similar - the people who have access to them know they're not perfect, but they're willing to spend the money because they think it's better than the alternative

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#338

Post by nullc »

These aren't even the worst examples I've seen by far-- but I suppose they're the worst people have posted with the latest software.

As someone in another thread said:

Driving with Tesla FSD is like being a drive instructor for a narcoleptic student driver who is currently tripping balls.

I don't want to share a road with these things. I try to stay as far away from every tesla on the road as I can.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#339

Post by marvin »

Invictus0 wrote: post #312
zaroth wrote: post #267

Earlier quoted context omitted.

We have actual statistics on how well humans do with Tesla ADAS and it’s remarkably well. The accident rate numbers are hard to compare apples-to-apples since miles driven with all ADAS features active are different from miles driven without the full ADAS active, but the numbers show that the software is absolutely not “1000x more dangerous”. > In the 1st quarter [2021], we registered one accident for every 4.19 mill…

> one accident for every 4.19 million miles driven Not really a great metric. We should be looking at disengagements per MM.

If you're evaluating the system as a L5 autonomous driving system. Not if you're evaluating it as a safety assistance feature.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#340

Post by TheParkShark »

nikhizzle wrote: post #3

Does anyone have any insight as to why regulators allow a beta like this on the road with drivers who are not trained to specifically respond to it's mistakes? IMHO this puts everybody and their children at risk so Tesla can beta test earlier, but I would love to corrected.

Everyone and their children seems a bit hyperbolic. There hasn’t been an accident involving FSD beta 9, but I’m sure someone has been killed at the hands of a drunk driver today. I am failing to find any comments from you arguing for alcohol to be removed from shelves across the country? Why aren’t you pushing your regulators for that?
Post reply on HN