i-GSI: A Novel Grasp Switching Interface Based on Eye-Tracking and Augmented Reality for Multi-Grasp Prosthetic Hands
Chunyuan Shi, Dapeng Yang, Siyang Qiu, Jingdong Zhao
Abstract
Controlling multi-grasp prosthetic hands remains challenging due to the lack of an intuitive and efficient interface for enabling a suitable grasping pattern. To solve this problem, we propose an eye-tracking based grasp switching interface (i-GSI) that integrates the “GazeButton” from augmented reality (AR) to elicit the intended grasp patterns from eye movements. The i-GSI is fully implemented in HoloLens 2 (Microsoft, USA), and its user can easily switch between six grasp types with just a glance at the GazeButtons. Experiments on eight healthy subjects shows that the average switching time is nearly 0.84 s, with a success rate of 99.0% and a learning efficiency of 93.5%. Results on a congenital amputee also shows a similar outcome (switching time 0.78 s, success rate 100%). Compared with the other three traditional methods, our i-GSI achieved the best performance. The i-GSI also shows a superior adaptability to different users with various amputation levels, when combining with a simple myoelectric control (such as, two-sites proportional control).
BibTeX
@inproceedings{ral2023_igsianovelgrasps,
title = {i-GSI: A Novel Grasp Switching Interface Based on Eye-Tracking and Augmented Reality for Multi-Grasp Prosthetic Hands},
author = {Chunyuan Shi and Dapeng Yang and Siyang Qiu and Jingdong Zhao},
booktitle = {RA-L 2023},
year = {2023}
}