top of page

Shape Based Grasping Techniques with Eye Tracking Device

The loss of one hand can significantly affect the level of autonomy and the capability of performing daily living, working and social activities. The current prosthetic solutions contribute in a poor way to overcome these problems due to limitations in the interfaces adopted for controlling the prosthesis and to the lack of force or tactile feedback, thus limiting hand grasping capabilities.
For this reason, it was carried out a project to develop a system targeted to be used for a prosthetic hand.
It consists of an algorithm that allows an adaptive grasping based on the shape of the object. This system, first of all, extracts the user’s intention to grab an object through EMG signals using the EMG Myo Armband device. After that, the visual feedback is used to make the appropriate grasping using an Eye Tracking Device. In this way it is possible to identify exactly the object we are observing, which is then recognized using YOLO, a real time object recognition algorithm.
Various experiments were then carried out to test the effectiveness of the system and, finally, possible improvements were proposed.

Algorithm Grasping EMG.PNG
bottom of page