Armband Device to Predict Gestures and Control Prosthetic Hands

Researchers from UC Berkeley  have developed a new device that combines wearable biosensors with AI software to help recognize what hand gesture a person intends to make based on electrical signal patterns in the forearm. The device paves the way for better prosthetic control and more seamless interaction with electronic devices. The flexible armband design can read the electrical signals at 64 different points on the forearm. These electrical signals are then fed into an electrical chip, which is programmed with an AI algorithm that can associate these signal patterns in the forearm with specific hand gestures. The team has demonstrated that the system can classify up to 21 different hand signals, including a thumbs-up, a fist, a flat hand, holding up individual fingers, and counting numbers.

Transcript

00:00:00 INSTRUCTOR: This video presents a wearable biosensing system for hand gesture recognition. The flexible electrode array is printed with conductive silver ink on PET substrate. Here you can see the screen-printing process and the resulting array of 64 electrodes. We apply a drop of conductive hydrogel on each electrode to improve the electrode skin impedance. The array is then wrapped around the forearm.

00:00:49 The user is instructed to perform each gesture only once to train the sensor classifier. Here we show the real time inference of gestures, as well as the system in action controlling robots and a prosthetic arm.