You Can Trick Self-Driving Cars By Defacing Street Signs (bleepingcomputer.com) 272
An anonymous reader quotes a report from Bleeping Computer: A team of eight researchers has discovered that by altering street signs, an adversary could confuse self-driving cars and cause their machine-learning systems to misclassify signs and take wrong decisions, potentially putting the lives of passengers in danger. The idea behind this research is that an attacker could (1) print an entirely new poster and overlay it over an existing sign, or (2) attach smaller stickers on a legitimate sign in order to fool the self-driving car into thinking it's looking at another type of street sign. While scenario (1) will trick even human observers and there's little chance of stopping it, scenario (2) looks like an ordinary street sign defacement and will likely affect only self-driving vehicles. Experiments showed that simple stickers posted on top of a Stop sign fooled a self-driving car's machine learning system into misclassifying it as a Speed Limit 45 sign from 67% to 100% of all cases. Similarly, gray graffiti stickers on a Right Turn sign tricked the self-driving car into thinking it was looking at a Stop sign. Researchers say that authorities can fight such potential threats to self-driving car passengers by using an anti-stick material for street signs. In addition, car vendors should also take into account contextual information for their machine learning systems. For example, there's no reason to have a certain sign on certain roads (Stop sign on an interstate highway).
Easy (Score:2, Flamebait)
You set up snipers in strategic locations across town to cover every and all traffic sign; and you shoot the fucker who dares get even close to it.
Re: (Score:2)
Yeah, in other shocking news, removing stop signs and shooting out stop lights can cause accidents!
Re: (Score:2)
But what if the stop light draws first?
Re: (Score:2)
Then you can label the traffic light a gun nut and ignore it.
Re: (Score:3)
But what if the stop light draws first?
George Lucas will make new ones that don't.
Misleading title (Score:5, Informative)
A better title would be, "Researchers fool Google's TensorFlow library in laboratory tests".
As it turns out, they did NOT test this against actual self-driving vehicle image recognition, but a generic deep neural network library. This seemed obvious, as there are still no commercially available fully autonomous vehicles, but I skimmed the paper to confirm it.
There was another issue I noticed as well. They resized all their training images down to 32x32 pixels. I admit I'm no expert in neural networks, but this seems like it would greatly favor the ability to fool classification algorithms. Maybe someone more knowledgeable can correct me if I'm off base here. Still, my suspicion seems to be confirmed by this little gem:
"Our final classifier accuracy was 91% on the test dataset."
So, their baseline algorithm only worked properly slightly better than 9/10 times. Should we believe that this represents the state of the art that will be applied in actual self-driving vehicles? It seems like the researchers didn't even have a highly robust classifier from the start.
I believe the merits of the paper lie in demonstrating this as a theoretical concern, but this should in no way be construed to represent a definitive threat against actual vehicle systems. You can't necessarily blame the researchers for the crappy headline, of course, as the title is "Robust Physical-World Attacks on Machine Learning Models". But I wouldn't necessarily rate this as the most robust research I've ever seen either.
Re:Misleading title (Score:4, Interesting)
I believe the merits of the paper lie in demonstrating this as a theoretical concern
But that is important, because without this research, the teams of professional engineers designing SDCs would have never even considered that a traffic sign could be smudged or obscured by a tree branch.
Re:Easy (Score:5, Funny)
Here in Texas, they just shoot the traffic sign and skip the middleman. Because freedom has to be irrigated by the blood of patriotic drivers in self-driving cars. Or something. I don't remember the exact quote, but it's in the Second Amendment or the Bible, I'm pretty sure.
https://s-media-cache-ak0.pini... [pinimg.com]
Re: (Score:2)
Here in Texas, they just shoot the traffic sign and skip the middleman.
Way back in 1982 or so I drove from Tampa to Miami and went across the southern, west to east segment of Highway 75 [wikipedia.org] in Florida -- I think it's known as Alligator Alley [wikipedia.org]. Anyway, the road is basically straight all the way across Florida. Along the way were signs that said "Unlawful to discharge firearms within 1/2 mile of road". The signs had all been shot several times.
Re:Easy (Score:4, Informative)
My wife and I drove from Seattle to Anchorage back in the late 1980s - her sister had gotten married, and we went up to meet her husband and his family. Not long after we crossed from Canada into Alaska, we started noticing that pretty much every road sign had been shot multiple times. It got worse, the further into Alaska we travelled. Along the stretch of highway that heads down the peninsula towards Anchorage, many of the signs had so many bullet holes that they were unreadable.
After meeting my (now ex-) brother-in-law and his friends, I ceased to be surprised at the state of the road signs - instead, I wondered why none of them had thought of destroying the signposts using automatic weapons.
You couldn't just post mine, could you? (Score:2)
Re: (Score:2)
I pointed it out on yours, but both cover a topic we looked at 5-months ago [slashdot.org].
I'm not sure why bleepingcomputers is posted at all - every single story is submitted by an anonymous user, pretty hard to accept its not someone from the site spamming Slashdot.
Better solution (Score:5, Insightful)
Re: (Score:2)
Your idea is awesome.
On a practical basis however, it sounds like a cluster-fuck. Just think about that for a little while.
Re: (Score:2)
Why not just have a geospatial database of signs that self-driving cars access? Then it won't matter what's on the sign, or if the sign even physically exists. Why is anti-stick coating the solution that "researchers" suggest?
For one thing, there's a need for temporary signs.
And the sign has to physically exist for everything that isn't a self-driving car.
Re: (Score:2)
And the humans driving won't be fooled at all by fake signs put up by trolls (mostly because humans ignore most of the signs anyway).
Re: (Score:2)
And, as a human driver, you always look at every sign that you see every day? You don't ever become blind to the stop sign at the end of the street you live on? Or perhaps you do use an internal database for the vast majority of your travels?
Self-driving cars will synthesize situation awareness from many sources including their previous experiences and the experiences of all the other vehicles on the road contributing to the database.
The physical stop sign won't rule. When it becomes obscured by the bush gr
Re: (Score:2)
Self-driving cars will synthesize situation awareness from many sources including their previous experiences and the experiences of all the other vehicles on the road contributing to the database.
Self-driving cars will need to synthesize situation awareness from many sources including their previous experiences at least as well as a reasonably good human driver, but I doubt the current algorithms are anywhere close, and getting them there is going to take a lot of time and money.
Re: (Score:2)
getting them there is going to take a lot of time and money.
Traffic accidents cost $870 BILLION per year [pbs.org] in America alone, so this is certainly something worth spending a lot of time and money on.
Stop sign on the interstate (Score:2)
Why not just have a geospatial database of signs that self-driving cars access? Then it won't matter what's on the sign, or if the sign even physically exists. Why is anti-stick coating the solution that "researchers" suggest?
For one thing, there's a need for temporary signs.
And the sign has to physically exist for everything that isn't a self-driving car.
This.
You have to be really carefully how you design this. The self-driving car that refuses to see a stop sign on an interstate is going to absolutely love construction zones.
Re: (Score:2)
And how frequently will this database be updated? And how frequently are downloads of the updates required? Have you noticed that work crews generally erect signs during the day? And that drivers are generally required to follow the sign once it is in place? That means that the database must be updated as soon as the workers declare the sign to have been installed and all cars must download the update immediately because more than one crew could exist in a city and cars are everywhere.
Or perhaps the downloa
Re: (Score:3)
So every sign will have to be accurate and up to date with the database, at all times, across the entire country? Further, you'll have two masters now. What should a car do if/when it encounters a conflict? Should it stop and hand back control, use the database and ignore all signs, or use the signs as posted? All options are messy, other than making sure HAL is as good as a human at reading damaged and defaced signs.
Once you ask these dumb things to navigate back roads, or poorly maintained hellscapes
Re: (Score:2)
...Basically this self driving frenzy is likely to go the way of the VR hype. It will be awesome tech that only a few will shell out money for, and even fewer will make use of.
I hope you're right, but I think at some point it's going to be mandated. Government, especially in the US, is rapidly accelerating both the degree and the granularity of the control it has over its own citizens. And since Joe Average is a sucker for the 'because safety' and 'because security' BS arguments, once the tech is mature and reliable, self-driving cars will be embraced with open arms. Then law enforcement, along with the rest of the authoritarian power-trippers, will have their most compelling wet
Re: Better solution (Score:2)
reliable braking + teenagers (Score:2)
my 1st thought years ago was pranking cars by jumping out in front of them. Crazy to risk it; however, when it becomes predictably safe...
Next thought was some radio nerds experimenting with broadcasting signals towards cars.
Re: (Score:2)
Roadworks are always putting up crazy signs, traffic cones, and all sorts of obstructions:
http://www.inspirational-quote... [inspiratio...-stuff.com]
https://s-media-cache-ak0.pini... [pinimg.com]
Re: (Score:3)
That would be a great idea if the data were available.
Local government authorities know where most of their signs are, and could provide updates when things change. Mapping companies would love to get hold of that data stream, but it's damn near impossible. The local government authorities want them to pay for the data, and they all negotiate separately. Even if they agree, there is no legal requirement for the data to be accurate or timely so at best you might notice they suck and sue them for breech of co
Re: (Score:2)
SDCs do use a database. They also look for signs. If they don't see a stop sign where one is expected, or see one where it is not expected, they will stop. They will also report the discrepancy.
Re: (Score:2)
Dead Reckoning? Yea, that's a self fulfilling prophecy, dead.... Eventually the error between where you THINK you are and where you ACTUALLY are gets too big, you crash and die.
You use "Dead Reckoning" for as short of a distance as possible and use pilotage to correct your position often. That's why, when I fly I always carry a map with the expected course marked on it with check points about every 5-10 min of flying time. Then, as I fly, I verify where I am, update my course on the map as necessary. As
Re: (Score:2)
Autonomous vehicles get it right most of the time (Score:2)
But, the edge cases will become increasingly troublesome as they move from prototype into widespread use
Road signs are commonly missing, rotated, shot, stolen or defaced
I love the idea of autonomous vehicles. I wrote autonomous vehicle software for a major auto manufacturer. This shit is hard
Re: (Score:2)
Road signs are commonly missing,
I feel like a missing stop sign is a problem regardless if your brain is squishy or silicon. In fact there is an unmarked 4 way stop near my office. There is a crash there about once every 2-3 months.
Re: (Score:2)
In fact there is an unmarked 4 way stop near my office. There is a crash there about once every 2-3 months.
If it's unmarked, it's not a 4-way stop. No marking means "yield to the right". Too many people have become accustomed to all intersections being marked to remember the basic rules.
Re: (Score:2)
In fact there is an unmarked 4 way stop near my office. There is a crash there about once every 2-3 months.
If it's unmarked, it's not a 4-way stop. No marking means "yield to the right". Too many people have become accustomed to all intersections being marked to remember the basic rules.
It's not just "yield to the right", it's yield to oncoming traffic, yield to the car that gets there first, and then (maybe) yield to the right.
Some states (like Arizona) treat an uncontrolled intersection as a 4 way stop, which is the only sensible thing to do.
Re: (Score:2)
It's not just "yield to the right", it's yield to oncoming traffic
No, it's not. Oncoming traffic won't cross your path unless they turn left, in which case they have you on their right, and must yield.
yield to the car that gets there first
At least imprecise. If a car has entered the intersection and cannot reasonably be expected to stop before entering your projected path, you have to yield to it, but for a different reason - you're not allowed to cause an accident by intent or negligence. But that doesn't mean the other driver hasn't broken the rules by not yielding to you.
Some states (like Arizona) treat an uncontrolled intersection as a 4 way stop, which is the only sensible thing to do.
Many countries have mainly unmar
Re: (Score:2)
Road signs are commonly missing, rotated, shot, stolen or defaced
Or, like around here, just plain wrong because it costs money to change them and the government doesn't have the cash.
Emergency vehicles (Score:2)
Re: (Score:2)
Re: (Score:3)
That switch is a pulsing light that triggers the traffic signal to change the cycle in the same manner as a pedestrian push button or in ground sensor loop might. It just forces the priority of the change so that the normal green-to-yellow-to-red change starts now instead of a bit later. They are not exactly difficult to fake out. Putting them on every car on the road would be a terrible idea, or not. As long as I am in my manual operated vehicle, having one of those would be quite enjoyable at times. "Hey
Re: (Score:2)
If you honk with the right timing, the car will even send bitcoins to your wallet.
Re: (Score:2)
Once we've eliminated idiot human drivers, cars will no longer need to pull over for emergency vehicles, unless it's a single-lane road. They will simply talk to each other and coordinate priority access. They will be able to clear a space in real-time, like a bubble surrounding the emergency vehicle.
In the meantime, if emergency vehicles aren't already transmitting some kind of signal that can be picked up by autonomous vehicles, that would make me worried. They certainly shouldn't be relying on visual
Re: (Score:2)
Works on human drivers too. I guess that means humans aren't ready to be driving yet.
There's always an exception to the rule (Score:5, Interesting)
"...there's no reason to have a certain sign on certain roads (Stop sign on an interstate highway)."
What about here? [goo.gl] (Cross Island Parkway, New York USA, Exit 31)
Stop signs often do appear on highway entry ramps, especially where they are short. This is true in construction areas, as well as on some older entrance ramps around New York City.
Technically this is a 50 MPH (~80 km/h) Parkway and not an Interstate, but rather than randomly searching the area this was the first that came to mind.
Re: (Score:2)
Can someone please tell me what I'm supposed to do at this intersection?
Seeing this sign it looks like it wants me to take the onramp and then come to a stop and give way before going? But looking at the road markings it appears to be a giveway-merge where I just match the speed of the traffic and then join in.
Forget driversless cars, let's start by making it clear for drivers first. I mean went back and forward along that road, none of the cars appeared to stop for anything.
Re: (Score:2)
There is not enough aligned ramp space there for you to see if there is any oncoming traffic on the main road before you have to collide with it. Extending the ramp would require expanding the bridge at its terminus.
So they expect you to stop, look backwards for a gap, and accelerate hard to get into it. Which can get quite tricky at hours when there is a lot of traffic.
At other intersections you may have to quickly get on before the on-/off-ramp gets you off again, or slow down prior to sharp curves on
Octagon? (Score:5, Insightful)
What horrifically terrible machine learning algorithm sees a red octagon and thinks it's a black and white rectangular speed limit sign? How is the visual machine learning matrix so bad that a triangular yellow sign would be registered as a stop sign?
Do they not train the machine learning algorithms with color images? Considering you can rely on 1-2 seconds of latency for a sign there is no reason to use the same sort of low latency machine learning algorithms used for pedestrian identification or road lines.
Re: (Score:2)
>"What horrifically terrible machine learning algorithm sees a red octagon and thinks it's a black and white rectangular speed limit sign?"
+1 THANK YOU!
I was wondering the same thing. I mean, I know visual AI is complicated, but it is a FREAKING RED OCTAGON!!! What freaking chance does freaking self-driving technology have if it can't freaking deal with something that freaking simple???
Freak!!
Re: (Score:2)
The current state of "AI" is pretty damn crude, and the resulting "trained" system cannot be debugged as such. As best I can tell it is akin to shoving in data, desired behavior, and pressing "optimize". So while we would like to think there is thought and reasoning going on, there is not. If the algorithm has been poorly designed or trained there is no telling how it will react to data that is dissimilar to the training data. Graffiti is pretty random, which is easy to figure out for a human, apparentl
Re: (Score:3)
The machine probably discards colour information, so that it can work at night when colour is either not available or inaccurate.
Sign of the times (Score:2)
For example, there's no reason to have a certain sign on certain roads (Stop sign on an interstate highway).
Except when you do, like when there's construction or accidents, and a guy stands there with a stop sign.
Future Revealed (Score:2)
I can see it now: a company puts up a billboard with a red octagon containing their brand of motor oil, and the car gets thirsty.
It has begun!
There can be stop signs on freeways (Score:5, Interesting)
For example, there's no reason to have a certain sign on certain roads (Stop sign on an interstate highway).
Except during road construction when a signman holds up a "stop" sign and the self-driving car says "You're not fooling me! There are no stop signs on freeways, and even your 15mph speed limit sign is fake, my database says the speed limit here is 75mph. See ya!"
And they will the do that 55 on I-294 when all oth (Score:2)
And they will the do that 55 on I-294 when all others are doing 75+.
Re: (Score:2)
In these situations, obviously the workers would need to be using a transmitter to broadcast updated road speed information in a standardised format to all vehicles. Isn't this just common sense?
Re: (Score:2)
In these situations, obviously the workers would need to be using a transmitter to broadcast updated road speed information in a standardised format to all vehicles. Isn't this just common sense?
If you're going to standardize every construction site in america and give them transmitters that every car listens to, why not just put long distance RFID tags on every street sign and avoid the need to use faulty image recognition in the first place? Just because humans need to use vision to read signs doesn't mean cars should.
They could even be cryptographically signed with the sign's meaning and location/direction to prevent a prankster from moving a 70mph freeway speed limit sign to a residential stre
Re: (Score:2)
You can trick humans by defacing street signs... (Score:4)
You can trick humans by defacing street signs... So... What else is new? This is a "no-duh!"
Re: (Score:2)
It's a LOT harder to trick a human than it is to trick a computer.
Re: (Score:2)
Yeah, the first step is to get the human to look at the sign in the first place.
Re: (Score:2)
Car says," I'm lost." (Score:3)
Instead of a car making horrific errors in judgment, why not have it safely pull over and say, "I'm lost, please ask for directions."
Better yet, set it up so the female voice pulls over and asks for help and the male voice just keeps going until it thinks it reached the destination.
Re: (Score:2)
Better yet, just remove the damn computer and let the human drive it himself.
Re: (Score:2)
Better yet, set it up so the female voice pulls over and asks for help and the male voice just keeps going until it thinks it reached the destination.
No, the male voice would keep driving around in circles while insisting it wasn't lost.
Huh (Score:2)
Should be map info with signs (Score:3)
In addition, the feds should come up with a SINGULAR approach on how to put up secured temporary local notifications.
Perhaps a digital form of NOTAMs.
Why are they reading signs in the first place? (Score:2)
Why are self-driving cars reading signs in the first place? Seriously, don't we have all of this information available digitally? It makes no sense for them to even be attempting to read the signs. If the car needs to travel into an area where we don't have digital information available, it should require manual control. This is just silly.
Re: (Score:2)
temporary signs for roadworks?
Do you REALLY want to play whack-a-mole? (Score:2)
Researchers say that authorities can fight such potential threats to self-driving car passengers by using an anti-stick material for street signs
Spend tons of money covering signs with sticker-proof material and you are again defeated by spray paint and stencils. Or by magnetic graffiti! This is not the most efficient way of thinking to remedy this problem.
Easy to F with humans too (Score:2)
Have a very attractive lady(s) walk on the side of the road. I guarantee there will eventually be a smashup. Most men are suckers that way. I've had multiple close calls due to such "distractions". Plus, it's not illegal to arrange such, unlike sign tampering.
Hmmm, let's see if bot-cars are distracted by R2D2 in lingerie.
News flash (Score:2)
AI is stupid.
News at 11.
and location (Score:2)
Signs vary widely between countries.
Here in New Zealand a stop sign is alway accompanied by a yellow line and the word "STOP" painted on the road at the intersection. Give Way signs are either unmarked or have white lines with a triangle on the road.
I assume that means if the sign is damaged, you always know the difference between a stop sign controlled intersection and a regular give way intersection.
Tesla is already building their driving DB (Score:2)
Every new Tesla car (including Model 3) has the full "Hardware 2" platform for self-driving, and even when it's not being used for self-driving it's on and watching the world. Tesla has said that it is already using "fleet learning" to map out roads. This blog post is talking about how radar has problems but is still useful for self-driving, and they are working around the problems:
These people must not drive on interstates (Score:2)
"For example, there's no reason to have a certain sign on certain roads (Stop sign on an interstate highway)."
I can think of at least two places on I-15 which have a stop sign directly on the interstate, and one on I-40.
Stencil + paint means I can trick YOU (Score:2)
Give me a stencil and some paint, and I can trick YOU by defacing street signs.
The only difference here is that idiots don't need the stencils.
To quote a famous idiot, FAKE NEWS.
Which signs do self-driving cars actually need? (Score:2)
On the kind of mapped terrain where self-driving cars currently mix with manual traffic, most of the information on traffic signs can be coded into the cars' database, such as speed limits on each stretch of road and the location of no-passing zones and crosswalks. Self-drivers must be able to recognize sudden and temporary control changes, such as for construction, weather damage, and police operations. If someone tries to spoof signs in one of these areas or do something like cover up a Stop sign with a p
Re: (Score:3)
Re: (Score:2)
Except that deep ANNs have way better accuracy for OCR and image recognition than hard coded algorithms.
You can also trick humans by defacing and modifying signs.
Re:dumb machines (Score:5, Insightful)
This 'technology' is being rushed way too quickly to market.
I'd like to agree with you, particularly with respect to the semi-autonomous systems presently deployed. I argued for years that having a system that worked most of the time but expected the user to take over when necessary was extremely dangerous. But the thing is that human drivers are extremely dangerous. Tesla has very compelling data showing that, as half-baked as their system is, it's actually better than the human drivers that it's replacing. The same will be even more true of the first fully-autonomous vehicles.
The systems don't have to be perfect, they just have to be better, and the bar is not very high.
Re: (Score:3)
TFS makes this point.. Deface a sign enough and it fails inspection as a sign. Now the intersection has no stop sign as far as the computer's concerned.
Things like this are exactly the kind of corner cases their 'AI' will never be able to deal with, at least not with current solutions.
Re:dumb machines (Score:5, Informative)
Deface a sign enough and it fails inspection as a sign. Now the intersection has no stop sign as far as the computer's concerned.
Nonsense. SDCs are not designed with a single point of failure. When approaching an intersection they do all of the following:
1. Look for a sign or light. ... and also says it requires a stop.
2. Access map data, which shows it is an intersection
3. Access historical data for the intersection that shows other SDCs recently stopped there.
4. Look at the road markings and tire markings that indicate cross traffic.
If these data contradict each other, the SDC will do the safe thing and stop. It will also report the missing and defaced sign.
A human is more likely to drive through the intersection than an SDC.
The actual paper is here: https://arxiv.org/abs/1707.08945v3 [arxiv.org]
They did NOT "trick" any SDCs, nor did they even try. They just defeated an algorithm that they assumed is similar to what SDCs use for #1 in the list above.
Re: (Score:2)
Will humans?
Human drivers deal with it every day, and mostly successfully.
There's a diner nearby that has a stop sign Humans know it's not real because of the store logo above it and the "for a cup of coffee" below it. A bit down the road, someone placed a route sign in front of a speed sign, so it looks like the speed limit is 212. Then there's the sign that's been shotgunned regularly.
Re: (Score:2)
It's not just street signs. I've seen double decker buses decorated with advertising in the style of street signs and other vehicles:
http://l450v.alamy.com/450v/cb... [alamy.com]
http://www.atmediaoutdoor.com/... [atmediaoutdoor.com]
http://l7.alamy.com/zooms/42e4... [alamy.com]
http://www.edinphoto.org.uk/0_... [edinphoto.org.uk]
Some countries actually hire artists to decorate roads and buildings with optical illusion style art:
http://www.dailymail.co.uk/tra... [dailymail.co.uk]
Re: (Score:2)
And that'll fool radar and IR sensors?
Re: dumb machines (Score:2)
In other other news (Score:2)
You can deface human drivers by tricking street signs.
Re: (Score:2)
But not as easily. That was the claim in the article, anyway.
Re: (Score:2)
You can trick human drivers by defacing street signs
Yea, not always. Try to change the signs on a road that I drive every day and you won't trick me. I'm not likely to even look at the things. Robots? Totally different story. They cannot think or reason and have to be programed to look at ALL signs, defaced, false or not. The guy flying the bird next to the sign isn't going to register as anything but a pedestrian to avoid hitting.
Re: (Score:2)
I nearly ran through a stop sign last winter... ...because it was covered with blowing snow.
I got stopped by the police once, and asked whether I hadn't seen the speed limit sign. I told him that I hadn't seen the sign at all, because it was hidden behind a tree...
Re: (Score:2)
Google and Tesla are headquarted in Silicon Valley. What is this thing you call snow? Those people that live where that stuff is just need to move to a climate more appropriate to the use of electric, self-driving cars. It isn't like progress requires massive changes in the way we live.
Re: (Score:2)
There will be services that track all signs along with GPS coordinates and which are updated by planning authorities.
All well and fine, but it's the unplanned authorities that is a worry. Like when road crews have to use ad-hoc stop signs, or police have to make a detour around an accident or flooding.
Re: (Score:2)
How frequently does StreetView get updated?
Re: (Score:2)
My parents built their house and moved in over five years ago. Streetview shows a backhoe in the front yard getting ready to dig the foundation.
Re: (Score:3)
Now, not so often. Once Google deploys self-driving software, every time a connected car with their software goes down your street.
I don't agree that the system will evolve to give up the databases. Rather, the databases will become real-time and include much more than signs. There will be warnings about icy spots that are derived from earlier drivers hitting them, puddles, new potholes, a home that frequently has kids running into the street, etc. Every little thing you can imagine will be communicated. Bu
Re: (Score:2)
The newest StreetView data around here is ten months old, the oldest ten years. Most small towns have coverage of exactly one road; some don't even have that. Even in cities, there are gaps in coverage, and not just minor dead-ends: I'm aware of a three-block gap in a major arterial.
Re: Growing pains (Score:2)
Re: (Score:2)
Hopefully soon all signage will be eliminated entirely, forcing vehicles to rely on standardised digital data provided by local authorities. There will simply be no reason for any driving-related signs to exist. They are unreliable and expensive to maintain. Only signs for pedestrians and bikers should remain in designated areas.
Re: (Score:2)
Bikers share the road you insensitive clod. I need almost all the same signs when I am biking as when I am driving. Pretty much only the speed limits become mostly ignorable.
Also, "soon" will be at least 25+ years. Cars readily last 20 years these days, and you will not have 100% autonomous cars being sold within 5 years (not even close!). You will have a long tail that will include classic car drivers, and those pesky libertarian types who want the right to choose to drive for themselves, or the right
Re: (Score:2)
I got to think that keeping a sign ice free when it's -20F is going to be some kind of expensive...
Re: SNOW (Score:2)
Thanks - I needed the laugh. But in case you're serious, Google "ice storm" and prepare to be amazed as to what a little frozen water will stick to.
Re: (Score:2)
You got that right... Black Ice is NOT much fun to drive on and very hard to see... I've driven on it in the past and lived to tell the tale. It was no fun waiting for the car to slow down from 55MPH without using the brakes, hoping it stayed on the two lane road...
I don't think automation would deal kindly with that....