Hyperedge- . IoT, Embedded Systems, Artificial Intelligence,

A great number of activities require the precise application of force with the fingertips. When playing a guitar, for example, you must exert the proper amount of force to push a string against the fret board. Training is difficult, because new guitarists don’t know how much force to apply. This wearable system controls fingertip force to help users learn how to perform new activities.

Developed by NTT Corporation researchers, the system needs two parts to enable fingertip force control: stimulation and feedback. EMS (electronic muscle stimulation) handles the former by pulsing a small amount of electric current through the user’s muscles, forcing them to contract. That is commonplace technology today, with uses ranging from legitimate medical therapy to more homeopathic remedies. For feedback, the system utilizes bioacoustic technology (a transducer and piezoelectric sensor) to determine the amount of force applied by a user’s finger.

An Arduino Uno Rev3 board paired with a function generator gives the system precise control over the EMS unit, allowing it to adjust muscle stimulation as necessary. It does so in real-time in response to fingertip force estimated by a machine-learning regression model. An expert in the activity could use the system to train it on the proper amount of force for an action, then the system could provide the amount of stimulation necessary for a new student to replicate the expert’s force. With practice, the student would gain a feel for the force and then could perform the activity on their own without the aid of the system.

Additional details on the project can be found in the researchers’ paper here.


Read more about this on: Arduino Blog