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

Hacked billboards make Teslas see phantom objects causing them to swerve or stop

newsweek.com

Post reply on HN
Print view View original

131–140 of 264 posts

Re: Hacked billboards make Teslas see phantom objects causing them to swerve or stop

#131

Post by adrianN »

roamerz wrote: post #122
aeroplain wrote: post #29

Earlier quoted context omitted.

Having to invest is specialized infrastructure for self-driving cars defeats the whole point of them. Any money spent on infrastructure for self-driving cars would be better spent on public transportation.

Any money spent on public transportation would be better spent upgrading infrastructure to serve autonomous vehicles. Our bus system where I live travels with many busses nearly empty. This is what happens when they are funded by a percentage of property taxes rather than individuals paying per ride. A perfect example of government waste.

If nobody is using your public transport, that usually means that it's crap, not that it's overfunded. The vast majority of functioning public transport systems (that people actually use!) are not profitable. That is perfectly fine, because a public transport system, like many other types of infrastructure, has many positive externalities.

Re: Hacked billboards make Teslas see phantom objects causing them to swerve or stop

#132

Post by nitrogen »

bonestamp2 wrote: post #115
gruturo wrote: post #28

Earlier quoted context omitted.

While I agree with you on mandating it, a LIDAR "only" gives you a 3D point cloud. Great for detecting if an object is in your way - but it cannot read a stop sign, you still need a camera system for that - so they still have to harden it against this hack (and who knows how many to come).

> so they still have to harden it against this hack True, but LIDAR should make that detection more robust. For example, if a stop sign is on the same plane as the object that surrounds it, that's a strong signal that it is not a real stop sign but rather a projected or displayed one. That's much harder to detect with computer vision alone, especially if they're dealing with hackers who can test it with a real car an…

For example, if a stop sign is on the same plane as the object that surrounds it, that's a strong signal that it is not a real stop sign but rather a projected or displayed one.

It's conceivable that in denser or older areas, signs are sometimes placed on structures because there isn't room for a pole.

Re: Hacked billboards make Teslas see phantom objects causing them to swerve or stop

#133

Post by hashtagmarkup »

jvanderbot wrote: post #117

Cars should not detect "obstacles". They should detect roads. They should not seek _exceptions_ to driveable space through classification- or segmentation-first strategies. They should only detect driveable space. Full stop. You either detect a full-stopping-distance's worth of clear road through reliable (non visual) ranging with dense enough samples to preclude wheel-catching voids ... or you will continue to run i…

How did your country eliminate all the hoofed ruminants? Why did they do it? Do you have a death wish?

Re: Hacked billboards make Teslas see phantom objects causing them to swerve or stop

#134

Post by bonestamp2 »

nitrogen wrote: post #132
bonestamp2 wrote: post #115

Earlier quoted context omitted.

> so they still have to harden it against this hack True, but LIDAR should make that detection more robust. For example, if a stop sign is on the same plane as the object that surrounds it, that's a strong signal that it is not a real stop sign but rather a projected or displayed one. That's much harder to detect with computer vision alone, especially if they're dealing with hackers who can test it with a real car an…

For example, if a stop sign is on the same plane as the object that surrounds it, that's a strong signal that it is not a real stop sign but rather a projected or displayed one. It's conceivable that in denser or older areas, signs are sometimes placed on structures because there isn't room for a pole.

Agreed. I didn't say it's definite, I said it's a strong signal. Even strong signals need to be weighed against other available data.

Apple Maps shows stop signs and traffic lights on the map. A database like that would be another strong signal, but also not always accurate.

Re: Hacked billboards make Teslas see phantom objects causing them to swerve or stop

#135

Post by rtx »

fyp wrote: post #91

There are a lot of similar failure modes in humans. Sometimes they're are used for good, like making drivers slow down: https://www.insider.com/optical-illusions-3d-crosswalk-drivi... But other times they cause crashes: https://imgur.com/a/kYr94

Those examples in the first line are so bad, I hope they don't catchup.

Re: Hacked billboards make Teslas see phantom objects causing them to swerve or stop

#136

Post by im3w1l »

jacobsenscott wrote: post #128
mattbee wrote: post #20

This is clever, and Tesla's software is awful, but anyone doing this for real, with intent to divert cars from the road etc. would be committing a pretty serious crime.

There are already billboards with pictures of stop signs, stop lights, etc on them. It doesn't take any criminal intent. Things that were once just billboards are suddenly hazards.

Seems reasonable enough to ban that. Might confuse a tired human too.

Re: Hacked billboards make Teslas see phantom objects causing them to swerve or stop

#137

Post by heavyset_go »

saulrh wrote: post #109
robocat wrote: post #87

Are humans similarly vulnerable?

Yes. Flashing lights at the correct frequency and intensity can cause a noticeable fraction of the population to immediately seize. Emergency vehicles are a known trigger. Less glibly, yes. There are particular arrangements of roads which are known to get people killed by cars. For example, an intersection at a particular angle with particular speed limits cause cars to stay hidden in each others' a-pillars as they a…

It varies from state to state, but in general, people with uncontrolled seizure disorders are barred from driving. They're able to drive if their seizures can be controlled with medication and if they go a certain time period without having a seizure. They're often required to submit medical reports to the state to prove that they can drive safely.

Re: Hacked billboards make Teslas see phantom objects causing them to swerve or stop

#138

Post by jvanderbot »

krainboltgreene wrote: post #124
jvanderbot wrote: post #117

Cars should not detect "obstacles". They should detect roads. They should not seek _exceptions_ to driveable space through classification- or segmentation-first strategies. They should only detect driveable space. Full stop. You either detect a full-stopping-distance's worth of clear road through reliable (non visual) ranging with dense enough samples to preclude wheel-catching voids ... or you will continue to run i…

> They should only detect driveable space. I'm interested to hear how you decide what's drivable without detecting things that decide if roads are undrivable.

You don't need to know it's a "car" or a "cow" or a "corvette" to know that the flat surface you are on ends in less than your stopping distance.

Semantically, it's a meaningless distinction. But in implementation it's much easier to detect the shape of the upcoming terrain using, say, lidar or regular old multi-camera disparity. Flat and following your map: that's driveable. I'm guessing many take this approach, but it's seeming more likely that Tesla does not, and instead trusts monocular or arrayed cameras to track objects though frames from detection-first regimes. Seems dangerous.

I'm glad you were interested.

Re: Hacked billboards make Teslas see phantom objects causing them to swerve or stop

#139

Post by heavyset_go »

gruez wrote: post #46
JKCalhoun wrote: post #43

Earlier quoted context omitted.

I sort of find the idea of self-driving cars as ... selfish? Don't want to drive, take the bus. The idea that we all need our personal chariots (and now robotic chauffeurs) seems to me to be the height of irresponsibility. And, yes, I am guilty of owning a car myself and feel guilt about it. But for some reason the self-driving bit just seems to take it to another level for me. Maybe too there's an air of elitism abo…

But what if self-driving cars were 10x safer than human-driven cars? Seems like your issue is with the personal vehicle bit, not the self driving bit. >Don't want to drive, take the bus. And what if my area has shitty bus service?

> But what if self-driving cars were 10x safer than human-driven cars?

But there is no evidence of this, or that they're even as safe as human drivers. In fact, Teslas are involved in more accidents than other luxury cars.

Post reply on HN