Vision-based interface for grasping intention detection and grip selection : towards intuitive upper-limb assistive devices

TL;DR

This paper presents a vision-based interface that detects grasping intentions and assists in grip selection, aiming to make upper-limb assistive devices more intuitive and controllable for users with movement impairments.

Contribution

It introduces a novel user interface that delegates grasping decisions to the device, simplifying control for users with upper-limb assistive devices.

Findings

Enhanced intuitiveness in grasp control

Improved user-device interaction

Potential for better assistive device usability

Abstract

Assistive devices for indivuals with upper-limb movement often lack controllability and intuitiveness, in particular for grasping function. In this work, we introduce a novel user interface for grasping movement control in which the user delegates the grasping task decisions to the device, only moving their (potentially prosthetic) hand toward the targeted object.