Advertisement
Science
ChinaScience

Chinese scientists create machine fingers that touch and feel like human hands

  • A new sensor that mimics a human fingertip can tell users what texture they are touching in real time
  • Eventually, scientists hope to take it to the next level and allow people with prostheses to feel what the sensor detects

Reading Time:2 minutes
Why you can trust SCMP
1
Chinese scientists have created a sensory system that might one day give the sense of touch to people using prostheses. Photo: Guo Chuanfei
Holly Chik
A new sensory system that mimics a human fingertip has been created by a team of Chinese scientists, with the hope that one day it could bring the vivid sensation of touch to a robot or to a patient who has lost their hand.
Developed by researchers from the Southern University of Science and Technology (SUSTech) in Shenzhen, Xidian University in Xian and University of Houston, the sensor’s AI technology can recognise different textures, including wool, linen, nylon, polyester and twill, with results shown to users in real time.
“The sensory system integrated on a prosthetic fingertip can identify 20 different commercial textiles with a 100 per cent accuracy at a fixed sliding rate,” the team wrote in an article published in the peer-reviewed journal Nature Communications on Wednesday.

“Such a system is expected to promote the sensing technologies of robotics and prosthetics, and is potentially useful for the sensory recovery of patients wearing artificial prostheses, haptics-based virtual reality and consumer electronics,” the researchers said.

The sensor is attached to the fingertip of a prosthetic hand. When it slides on various textiles, the signal is sent to a computer and analysed by a machine learning method. Currently, the recognition result is shown on a screen.

The sensor can be worn on a prosthetic finger and tells the user what texture they are feeling. Photo: Guo Chuanfei
The sensor can be worn on a prosthetic finger and tells the user what texture they are feeling. Photo: Guo Chuanfei

In the new study, the team has developed a sensor that detects both static pressure and high-frequency vibrations. The researchers said this single-sensor system was more simple and robust than existing ones that required two sensors integrated with two sets of data acquisition systems.

Advertisement