Those motors are arranged in opposing pairs, along with non-linear spring systems so that they mimic the opposing muscle structure that gives human hands their dexterity. The team achieved this by making hundreds of MRI scans of real hands in different positions. And apparently this has paid off, since it means the Sensopac hand can snap its fingers, pick up an egg or carry a cup of liquid much like we do.

The really clever bit, though, is in the artificial intelligence that controls the limb. In humans the cerebellum controls sensation and movement, so the team have created a neural-net system that mimics it to control the arm in a more "natural" manner. It's apparently the "first neural-network-based controller that can control the dynamics of a robotic system in its full operational range,” and means that the arm (when perfected) would be able to pick up a cup, sense what the contents feels like and handle it appropriately.

The arm is now in advanced testing, but it'll be a while before robots have a limb that behaves exactly like ours do: that's "still light-years away" according to the project coordinator. Doesn't stop me wondering how long it'll be until there's an entire neural-net robot droid built with this biomimetic tech though. And then there's personality downloads to think about... [ICTResults via Physorg]

An inversion of the normal, the robot was designed by artist Golan Levin to tackle the questions of "What if artworks could know how we were looking at them? And, given this knowledge, how might they respond to us?" So, with some clever electronics, Opto-Isolator looks at its viewer eye-to-eye, dodges long stares and blinks exactly a second after the watcher does.

We've all known moments when eye contact with someone either goes right or horribly wrong, shivers go down your spine, and results are either a make-out session or a thump. Who knows what ogling a robot feels like? People who visited Opto-Isolator when it was shown recently in the Bitforms gallery, New York, I suppose. And any actor who's starred alongside Jim Henson's creatures.

Let's hope someone makes an Opto-Isolator app for cellphones. It would be totally cool to have on my BlackJack, and have it pop up unexpectedly, scaring the crap out of my wife, or freaking out the cat. Maybe other gadgets should be able to give us the eye—tell us which in the comments. [Flong via Oh Gizmo]

Update: We got hold of Opto-Isolator's creator, Golan Levin, and asked him some questions.

KE: What's that creepy shiny black body made of?
Golan: The exterior shell is a 3D print from an FDM machine, with an automotive paint job.

KE: What's inside?
Golan: ...just your usual servomotors and microcontrollers. It might be worth pointing out that the entire unit is self-contained, i.e., it houses a mini-ITX format dual-core Intel PC running custom computer vision software. The only cable coming in is for power. An Arduino microcontroller board (popular with artists and hobbyists) runs the servo-motors (there are 3 motors: x, y, eyelid).

KE: What kind of programing did you do to get it to identify people watching it?
Golan: The software is written in C++ using the OpenFrameworks.cc wrapper and OpenCV libraries for face detection.

KE: Are any of your other artworks inspired by the same idea as Opto-Isolator?
Golan: I'm currently working on a constellation of projects that are all concerned with the theme of gaze as a new mode of human-computer interaction. All of these projects respond in some way to how people look at them.

So there you go, folks: keep your eyes peeled for new eerie, eyeballing artworks sometime soon.