You're throwing scissors in the next round? This machine is totally onto you.

Rock-paper-scissors isn't so much a game as a lighthearted decision-maker. You use it, usually, to decide who picks up the bar tab, or who does the dishes. You rarely use it, however, as a legitimately competitive thing -- it's too random, too easy. Though there are ways to play competitively and strategically, sure, if you're an average R-P-S player, multiple rounds of the game will most likely end in the dullest of outcomes: a draw. 

Except, that is, when your particular game of rock-paper-scissors is being played against this handy robot -- in which case, it seems, you will lose every single time. Researchers at the University of Tokyo have developed the robot -- essentially, a camera-connected mechanical hand -- and it is physically incapable of losing at the game. 

Unlike logic-based R-P-S computer programs, which base their moves on statistical averages honed over time, this particular robot reads the shape of its human competitor's hand faster than the human eye ever could -- and then translates that reading into its own preemptive response. As Ishikawa Oku Lab researchers explain in a paper presenting the robot,

Recognition of human hand can be performed at 1ms with a high-speed vision, and the position and the shape of the human hand are recognized. The wrist joint angle of the robot hand is controlled based on the position of the human hand. The vision recognizes one of rock, paper and scissors based on the shape of the human hand. After that, the robot hand plays one of rock, paper and scissors so as to beat the human being in 1ms.

This technology is one example that show[s] a possibility of cooperation control within a few miliseconds.

Though rock-paper-scissors-ing is a cheeky way to show off their technology, the robot is much more than just a toy (or, if you happen to take R-P-S seriously, an ego-dasher). It's a demonstration of the mechanics that could allow human beings and their robot friends to communicate with each other, silently but effectively. The machines read our moves, and respond in kind.

Via @simonowens