The MemGlove detects hand poses and recognizes objects

– Werbung –
Reading Time: 2 minutes

The MemGlove detects hand poses and recognizes objects

Arduino TeamJuly 14th, 2020

Hand movements have long been used as a computer interface method, but as reported here, the MemGlove from a team of MIT CSAIL researchers takes things several steps further. This augmented glove can sense hand poses and how it’s applying pressure to an object.

– Werbung –
– Werbung –

The wearable uses a novel arrangement of 16 electrodes to detect hand position based on resistance, and six fluid filled tubes that transmit pressure depending on how an item is gripped.

– Werbung –

An Arduino Due is used to sense these interactions, which pass information on to a computer for processing. Pose verification is accomplished with a Leap Motion sensor. By training neural networks with TensorFlow, the glove is able to identify various hand poses, as well as distinguish between 30 different household things that are grasped.

– Werbung –

[youtube https://www.youtube.com/watch?v=6OY83PSr40I?feature=oembed&w=500&h=281]

More details on the MemGlove can be found in the researchers’ paper here.

– Werbung –

Website: LINK

– Werbung –