Electronic Skin Sensor Decodes Complex Human Motion

Researchers from KAIST  have developed an electronic skin sensor powered by deep learning that can capture human motion from a distance. The measuring system extracts signals corresponding to multiple finger motions by generating cracks in metal nanoparticle films, using laser technology. The sensor patch is then attached to a user’s wrist to detect the movement of the fingers. The rapid situation learning (RSL) system collects data from arbitrary parts on the wrist and automatically trains the model in a real-time demonstration with a virtual 3D hand that mirrors the original motions. The sensory system can track the motion of the whole body with a small sensory network and facilitate the indirect remote measurement of human motions, which has applications in wearable VR/AR systems.