An artificial tactile skin that mimics human tactile recognition processes

Researchers have created an artificial tactile sensing system that mimics the way in which humans recognize objects in their surroundings via their sense of touch.

They use particle-based polymer composite sensors and a signal-converting system.

Biological sensory systems convert tactile stimuli into action potentials through a process. Subsequently, they transmit these signals to the brain via afferent nerves.

To emulate the human tactile system, they utilize sensors that respond to pressure and vibration. The data they collect resembles information gathered by human sensory neurons; thus, they ultimately produce signals that look like human tactile nerve signals.

To evaluate their artificial skin system and prove that it can be integrated within real biological systems, they evaluated it on mice. The results were very promising.

In addition, the researchers evaluated its ability to analyse and recognize the texture of surfaces. To do this, they laminated artificial ridges that mimic the structure of a human fingertip on their T-skin device. They found that this system could sense complex textural patterns. The team combined it with a deep learning technique that can classify surface structures, achieving a remarkable texture classification accuracy of 99.1%.

The approach can also be used to predict unknown textures on the basis of the trained model.