Biocompatible, directly printed, meta-learning, human-machine input nanomesh

Stanford researchers in Zhenan Bao's Group have developed a nanomesh sensor printed directly on the hand that uses an AI-trained model to detect multiple movement types from a single sensor. Current movement sensing technologies are bulky, complex, and require multiple sensors on a substrate. The Bao Group nanomesh is made from biocompatible materials that can be directly printed on a person's skin. It mimics human cutaneous receptors by translating electrical resistance changes from fine skin stretches into proprioception. A single nanomesh simultaneously measures finger movements from multiple joints. A time-dependent contrastive learning algorithm differentiates between different unlabeled motions. The meta-learned information rapidly adapts to various users and tasks, including command recognition, keyboard typing and object recognition.

Stage of Development – Prototype
The Bao Group developed and tested the sensor system on human users in a lab setting.