Motion Prediction with Artificial Neural Networks Using Wearable Strain Sensors Based on Flexible Thin Graphite Films

Abstract

A human motion prediction system can be used to estimate human gestures in advance to the actual action for reducing delays in interactive system. We have already reported a method of simple and easy fabrication of strain sensors and wearable devices using pyrolytic graphite sheets (PGSs). The wearable electronics could detect various types of human motion, with high durability and fast response. In this study, we have demonstrated hand motion prediction by neural networks (NNs) using hand motion data obtained from data gloves based on PGSs. In our experiments, we measured hand motions of subjects for learning. We created 4-layered NNs to predict human hand motion in real-time. As a result, the proposed system successfully predicted hand motion in real-time. Therefore, these results suggested that human motion prediction system using NNs is able to forecast various types of human behavior using human motion data obtained from wearable devices based on PGSs.