Design World – August 2019

90 August 2019 http://www.designworldonline.com
DESIGN WORLD http://www.designworldonline.com August 2019 91

Robotic Hand

The goal of the robotic hand system is to enable wearers to conduct everyday tasks without additional commands.

| Seoul National University BioRobotics Lab

through the collection of user arm

behaviors and hand-object interactions.

The machine learning model used

in this study — Vision-based Intention

Detection network from an EgOcentric

view (VIDEO-Net) — is designed based on

this hypothesis. VIDEO-Net is composed

of spatial and temporal sub-networks,

where the temporal sub-network is to

recognize user arm behaviors, and the

spatial sub-network is to recognize hand-

object interactions.

An SCI patient wearing the soft

wearable hand robot Exo-Glove Poly II

successfully grasped various objects. The

patient was able perform day-to-day

tasks, such as drinking coffee, without

any additional help.

The SRRC team said its innovative

system can detect user intentions

without requiring any person-to-person

calibrations or additional actions. This

enables the wearable hand robot to

interact with humans seamlessly.

The research was published in the

January issue of Science Robotics. The

research team explained more about the

system.

How does this system work?

This technology aims to predict user

intentions, specifically grasping and

The research team

at the Soft Robotics

Research Center

(SRRC) in Seoul

has proposed a new

intention-detection

paradigm for soft

wearable hand

robots.

SRRC_EXOGLOVE_Robot Report 8-19_Vs4.LL.indd 91 8/5/19 1:13 PM