Slashdot Mirror
Virtual Robots Fooled By Visual Illusions
Roland Piquepaille alerts us to research out of University College London in which virtual robots, trained to "see" as we do, were duped by optical illusions the same way humans are. Here's one of the illusions the software system fell for.
That is just a difference in lighting.
---- Booth was a patriot ----
They could just be programmed to look as if they were falling for it! I smell conspiracy!
622677120
... but I went ahead and verified with a pixel color id program (ColorPix) that they are the same color.
to being able to upset them with goatse. Maybe that is what starts the robot uprising...
From TFA: "The virtual robots in this study were driven solely by the statistics of their training history and used these statistics as the basis of their correct and subsequent incorrect decisions. Similarly, we believe the human brain generates perceptions of the world in the same way, by encoding the statistical relationships between images and scenes in our past visual experience and uses this as the basis for behaving usefully and consistently towards the sources of visual images." So the robot vision was created as a model of human vision, and it succeeded at doing so. That's sort of interesting, I suppose, but what does it tell us? That we were right about the way human vision works? Seems to me that the point here is really that in some ways, human vision is 'broken' and that maybe it isn't the best apparatus for machines to use. If we want to welcome our robotic overlords, we should be improving on the vision model, not trying to give machines the same flawed framework.
I'm not sure about you guys, but at the moment, I'm kind of doubtful in welcoming our new robotic overlords. I mean, I thought they were supposed to be superior to us and not be fool by petty illusions...
and your eyes do it to. Which is why even sodium vapor lights don't look as yellow as they really are by the human eye. Turn off the white balance on the robots and I bet you they will see them as the same color. Add the average inverse color as a background for each color and your eyes will see them totally different. IE blue behind the orange and orange behind the blue. really stupid test.
OMG Ponies!!! with Glitter!!!! I miss Pink
show them a Escher staircase.
Cross your eyes, line up the two squares so they're offset by a few millimeters, and then hit the mask. What I saw was that the squares retained their seeming discoloration--until I uncrossed my eyes.
This is why I turn my auto-white-balance off in my digital camera. If I need to adjust the color, I'll do it later in Photoshop. (Another reason to shoot in RAW mode.) -- Carey
But then again, being color blind makes a lot of things look the same that shouldn't be...
XML is like violence. If it doesn't solve the problem, use more.
they are also susceptible to the illusion of "beer goggles"? ...Next thing you know, your personal robot's software has it waking up in bed with your new Dyson vacuum and a strange Toaster! [There must be a Bender joke in here somewhere] http://en.wikipedia.org/wiki/Bender_(Futurama)
Arrrooooo!
...that's a difference in surrounding lightning.
...WHEN those colors are ISOLATED. (i.e: putting the name "red" "orange" "purple" on a color you see alone).
Human visual system (as most other senses) work not by absolute values (i.e.: it doesn't see that the color '#c0ff20' or whatever), but mainly by comparing the signal with signals from the surrounds.
Thus what we technically see is that on the left object the central case looks much more "greener" than its surrounding, in the right object, the central case is "much more orange" than the surrounding. In fact, when the mask is enable, the colours do change from the point of view of the visual system : we were seeing contrast with two different surrounding, now we see a contrast with a third surround (mostly black). We see three different contrasts, even if from the computer's point of view the color is them same (the same RGB triplet / same intensity on your CRT/LCD)
If the scientist are trying to build efficient visual systems, they are probably mimicking this "works-by-comparing" method that the nature is using.
That's why we can recognise the same object, during day, during night, with weird lights, displayed on the screen (worse colour gamut) or on a print out (even worse color range). Because the relative difference stay the same, even if the colour as-seen-by-a-computer change.
The same is valid for any other sens, or in fact, any other information that is processed by neurons. Everything works by comparing (across several signals, across time, etc.). There's no such thing as "an absolute value" in the information carried by neurons.
That's also why all those "but the human eye can only x thousands of colors" (usually mocking the latest 32bit, 48bit, floating point or whatever color depth), are fundamentally wrong.
Yes, the human visual system can only distinguish a hundred or so colors....
When two colors are put next to each other, the human brain can suddenly distinguish much more subtle variations (each color would be considered as "brown" when seen alone, but next to each other, you can use thousands of different shade of brown and the eye will still see the difference).
That's also why radiologist are fond of high contrast / big depth screens : because all those difference in shades of grey *can* be distinguished and *are* revellent for the diagnosis when displaying X-Ray pictures.
"Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
I'm struggling to find the utility of the study. So, if we learned to see differently, we could see the world in a way different enough to not be fooled by certain optical illusions, and probably be fooled by others?
Assuming it is possible to change the way a human sees without breaking the brain. A popular theory on evolution is that we evolved our brains to better analyze visual data coming in. We're not deceived as easily by certain camouflages animals use. Stripes, dots, color, etc.
Confirms what we thought about the way we learn to see, perhaps? That'd make sense.
The general explanation, as I have seen it given many many times previously, is that, rather than write a /. story which links to some science/tech article, roland will paraphrase the article in his blog, and link the /. story to his paraphrase. This is a means of gaining ad revenue for himself and his employers (ZDnet, I think?), but it doesn't give any ad revenue to those who actually did and wrote up the research.
Is this true? I don't know. I never RTFA.
SIGSEGV caught, terminating
wait... not that kind of sig.
Is this true? I don't know. I never RTFA. The links are to the original story. The "Roland Piquepaille" link goes to his blog, but it's unlikely anyone will be clicking on that one unless they're interested in the guy
Incidentally, if there are any ads generating revenue on that blog, I'm not seeing them thanks to adblock. I doubt
you don't want to know
-Clio
Karma: Bad (mostly from not giving a fuck)
Blog: http://clintjcl.wordpress.com
I wonder if you're getting a kind of Persistence Of Color effect.
Here's one my favs:
http://www.johnsadowski.com/big_spanish_castle.php
Cube On! (http://stores.ebay.com/PuzzleProz)
These days, Roland's links go to the original story. Originally, his links went to his blog, as others have described. I don't his current posts. His previous ones, though, were just a bit self-serving.
Program Intellivision!