A European project called Sensopac, made up of 12 groups, came out today with advances in its robot hand. The hand mimics the flexibility and sensitivity of a human hand and is controlled by a neural-network-based program modeled on the cerebellum.

Scientists at the German Aerospace Centre (DLR) made a robotic “skin” out of a thin, flexible carbon that changes its resistance depending on pressure. This allows the robot hand to tell the shapes of an object, the amount of force placed upon it, and the direction of that force. Thirty-eight opposing motors control the hand’s joints, giving it a touch that ranges from light to forceful. The researchers modeled the robot hand by utilizing hundreds of MRI images of human hands.

As for the robot’s learning ability, the team hopes to improve its understanding of movement and sensation through its neural network. When the robot picks up a cup, it will be able to sense the properties within and adjust its motions depending on whether the cup contains water or flour, for example.

Sensopac, which began in 2006, is a four-year project focused on creating an artificially intelligent robot with sophisticated hand manipulation and grasping abilities.