A breakthrough in the world of artificial intelligence has been reported, through a mechanical AI arm being able to identify different materials by touching the surface. This can completely change the manufacturing industry as these robots can now carry out tasks such as sorting and quality control.
The AI arm was recorded to identify certain materials with a 90% accuracy rate. This is because of their triboelectric touch sensors gain information about the surface of an object, such as its temperature. It was trailed 100 times and used 12 materials including wood, glass, plastic and silicon and combined with machine learning-based data analysis achieved approximately 90% accuracy rates.
The device works with 4 square sensors made up of different plastic polymers, chosen for several electrical properties. When sensors move close enough to the surface of an object, electrons from each square interact with the surface in a slightly different way which can then be measured.
Researchers suggest this can be a breakthrough in the world of robot manufacturing, however, will become more effective when combined with other sensors that can detect more precise things such as roughness, edges, or friction.
Additional researchers also suggest that these machines can also be used as prosthetics however Tamar Makin at the University of Cambridge states that 'for technology that is human controlled, we don’t need this level of sophistication.'