Robots taught to “feel” objects through the artificial skin

Robotics is not standing still. Engineers have taught a robot to understand human speech and to walk independently. But still there is the problem of tactile feedback when the smart mechanism will not only be able to move the object, but also feel it. Scientists have created a new sensor which works on the principle of human skin, distinguishing brittle, soft, hard and other properties of objects.

Developed by researchers from ETH Zurich, the sensor consists of an elastic silicone skin with colored plastic microbeads and conventional cameras fixed on its bottom side, says Slashgear.

How does the technology

Thanks to computer vision, robot “sees” what part of the skin comes in contact with the subject. Lens-type “fish eye” captures the size and depth of dents on the silicone skin, hoping the force required to hold the object depending on its characteristics.

Silicone skin able to distinguish between several types of impacts on the sensor surface, calculating the appropriate level of efforts to retain high accuracy. Also the robot will be able to identify the specific direction that you want to put more or less effort. After the robot thus studied the properties of different objects, machine learning allows it to more accurately identify the pattern on the skin with its size, weight and density.

Video about the sensor, which allows the work to “feel” the touch:

Now a team of researchers is working on new sensors that will teach the robot to recognize objects, as well as considering miniaturization of the sensor.

More news on the events from the world of technology, gadgets, artificial intelligence, and space, see Techno