Chinese Scientists Give Robots a “Sense of Touch”

Guo Chuanfei, a professor in the Department of Materials Science and Engineering at Southern University of Science and Technology, and collaborators have developed a high-resolution artificial sensing system similar to a human finger that can distinguish delicate textures such as twill, corduroy and wool. The results of the study may improve the fine tactile ability of robots and human prosthetics, which is expected to be applied to virtual reality. The study was recently published in Nature Communications.

Humans can caress the surface of an object with their fingers and identify objects by static pressure and high-frequency vibrations. Previous methods used to develop artificial tactile sensors that perceive physical stimuli could only recognize real-world objects based on tactile or multi-sensors. There have been challenges in developing real-time artificial sensing systems with high spatiotemporal resolution and sensitivity.

The researchers reported a flexible slippery sensor that mimics the features of a human fingerprint, allowing the system to recognize tiny features of the surface texture when touched or the sensor glides over the surface of an object. Using machine learning to integrate the sensor into a human hand prosthesis, they found that the sensor could capture small tactile signals and recognize 20 different materials, including linen, nylon, polyester and seersucker, with 100% accuracy.

According to the authors, further research could help improve the robot’s perceptual ability to facilitate the recovery of perception in patients wearing artificial limbs, and apply it to haptic-based virtual reality and consumer electronics. (Source: China Science News Feng Lifei)

A slippery sensor is recognizing its texture on a piece of fabric. Image from: Guo Chuanfei

A prosthetic hand fitted with a slippery sensor. Image from: Guo Chuanfei

Related Paper Information:

Source link

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button