iCub learns objects
Author: Angela Chin
This video demonstrates an architecture allowing an humanoid robot iCub to learn new objects presented to it. This is done by adding the concept of object to an existent low-level attention system of the robot. When the robot first encounters an unknown object, found to be within a certain (small) distance from its eyes, it stores a cluster of the SIFT visual features present within an interval about that distance, using depth perception. Whenever a previously stored object crosses the robot’s field of view again, it is recognized and mapped into an egocentrical frame of reference and gazed at. This mapping is persistent, in the sense that its identification and position are kept even if not visible by the robot. More info at mediawiki.isr.ist.utl.pt
Video Rating: 4 / 5
Popular Posts:
- Installing Virtue OLED Board & Laser Eyes in Dye DM9 Paintball Gun
- Bridging Digital and Physical Worlds With SixthSense
- Official Angry Birds 3 Star Walkthrough Theme 3 Levels 1-5
- HTC Schubert
- Hook Your Guitar to Your iPhone and Rock Out with iRig
Tags: 
These things were made in Italy, talk about the modern day Pinocchio
the eyes are scary
Creeepy……
Well, there is a project at IM-CLeVeR.eu but I haven’t seen any videos of the CLEVER-K iCub yet.
One thing is clear: A true learning robot needs a skin. This makes it easy to filter out all those AI cheaters
the human brain’s programmer took a little longer ^_^ (a few million years), and the human robot takes a little longer to enact learning
(a few years)
But we’ll get there ^_^, inevitably
(unless we kill ourselves XD)
there is already neural network that classifies things
ketchup …catsup…ketchup …catsup…
After it has learned everything, you will be amazed as it doesn’t move and flicks its head around like the exorcist, trying to gaze upon everything.
wlorenz65, yeah that’s classified as a toy seriously, a Robot is automatic… what is that? the only thing I see that robot do on it’s own is see the object and turn its head. I’d say it’s 1.8% complete robot.
1 Point for making it turn its head and
0.3 for making it detect something and then the rest for memorizing it.
Human brains find out on their own that it is useful to separate the
enviroment into objects.
iCub instead needs programmers to implement the concept of an “object” in its software.
This means that iCub cannot learn to recognize combinations of objects or procedures as useful. It needs programmers again.
Nice. Now try to figure out how it can understand the “concept” of a cereal box, instead of memorizing every individual box. We humans know thousands of objects and we can recognize stuff we’ve never seen before too.
We need better processors, fast. Can’t wait for those groundbraking memristor chips to come out. Neural network processor units… NNPU’s.
we need open source robots, because i would never buy a close one, because i dont know if it wants to kill me or to capture information about me.
So what does it do ??
Come on smart people… Make something useful
memory is very cheap today, and the representation is very small, we don’t even need to store the actual images, just some numbers (SIFT features)
“what is the purpose of a baby?”
“what is the purpose of trying to create a 3 year old robotic child?”
she has eyelids
shw was just feeling really surprised with all the new objects XD
Fucking creepy!!!
why only the space is limitation? Is there no limit due to memory?
nice on the realistic movements. im assuming this is a demo program tho. it seems a bit odd if it’s only function is too look at each object in turn..
*screams*
i know kids like that..
Advertising coco pops ftw?
The systematic cuteness formula states:
cute = eye_size / head_size
But yes, it does need eyelids.
he owns hes never seen a box of cereal in his robot life XD