Gait Neural Network for Human-Exoskeleton Interaction.

摘要: Robotic exoskeletons are developed with the aim of enhancing convenience and physical possibilities in daily life. However, at present, these devices lack sufficient synchronization human movements. To optimize human-exoskeleton interaction, this article proposes a gait recognition prediction model, called neural network (GNN), which is based on temporal convolutional network. It consists an intermediate network, target model. The novel structure algorithm can make full use historical information from sensors. performance GNN evaluated publicly available HuGaDB dataset, as well data collected by inertial-based wearable motion capture device. results show that proposed approach highly effective achieves superior compared existing methods.