“Watch the claws of humanity’s eventual destruction pour you a drink.”

Scientists at the Tokyo Institute of Technology’s Hasegawa Group have doomed us all to inevitable destruction at the hands of our robot creations by releasing footage of an experimental robot they’ve designed that basically models its behaviour on human cognitive processes, i.e. it learns from its actions, remembers those events and changes its future actions to fit the new information. Key words: It learns, remembers and adapts.

Oh crap, we’re all doomed.

In the clip below, you can watch the robot employ its “Self-Organizing Incremental Neural Network”, or SOINN, to solve a problem.

In this experiment the robot will solve a problem by deciding what actions it should take and in what order. The robot will be told to pour a glass of water, make it cold, and give it to a person. The robot will decide how to do this while being aware of its surroundings and its own situation.

If the robot is told that cold water is wanted, it recognizes that after pouring the water, it can’t pick up ice straight away, because it’s hands are already full with the glass and the bottle. So it chooses to put the bottle down, and then put the ice into the glass.

Okay, maybe I watch too much Science Fiction, but the only icy feeling I’m getting from the Cyber-barman here is down the back of my neck…

“Modori masu.”

[Source: Escapist Magazine, Daily Motion]