MIT smart glove teaches you how to play the piano

The Massachusetts Institute of Technology is a powerhouse in constant motion, from which notable innovations emerge. A recent sample is a smart glove that teaches tasks through tactile sensations. Such ingenuity could revolutionize various sectors. Among others, musical performance, interaction with robots and experience in virtual environments.

The solution designed by researchers from MIT’s CSAIL division—specialized in computing and artificial intelligence—has the shape of a traditional glove. But unlike an ordinary one, it is equipped with sensors coupled with a very delicate sewing process. In addition, it operates in conjunction with a machine learning program. How do you teach tasks to users? The key is haptic feedbacka technology similar to that included in the controls of video game consoles, which launches personalized vibrations.

According to the main author of the study on the smart glove, Yiyue Luo, human beings learn mainly through visual and/or auditory information. “Normally, we don’t share physical interactions with others. Instead, we do it by observing movements. For example, in piano and dance classes,” says the doctoral student in the Department of Electrical Engineering and Computer Science at MIT and a CSAIL affiliate.

This is how the smart glove works that uses touch to teach subtle tasks

The video above this paragraph shows behind the scenes in the production of the ingenious and unusual wearable device. Researchers use a special embroidery machine, capable of integrating touch sensors and haptic actuators in textiles. As we pointed out, this is a technology that we find in video game controllers and also in mobile phones. It is what we perceive, for example, when a specific sector of the screen returns a small vibration.

The MIT CSAIL specialists observe a relevant detail: the smart glove must be made in a personalized way, according to the characteristics of each hand. The good news is that this process is dynamic, since the final product is manufactured in approximately 10 minutes. Otherwise, Can be used in just 15 secondsin which it collects information from the new user.

The team led by Luo foresees that this type of device will offer its benefits beyond the hands. The technology could be extended to the feet, hips and other parts of the body, with stronger feedback systems.

MIT’s technological glove would “democratize” piano learning

smart glovesmart glove
Yiyue Luo is a PhD student in the Department of Electrical Engineering and Computer Science at MIT and an affiliate of CSAIL. (Credit: Courtesy)

“This development proposes a novel approach to learning movements and physical abilities, in optimal form,” comments Luo in dialogue with Hypertextual. The possible uses of this invention generate excitement, and one of the most charming is its ability to teach piano playing. In this case, the smart glove vibrates in one of the fingers and indicates that you should press a specific key on the instrument.

In laboratory tests, an expert pianist recorded a melody using the glove, which captured the sequence of the fingers. A specially designed artificial intelligence system then translated the series of movements into haptic feedback. Finally, the textile device was used by students of the instrument, who followed the instructions, that is, the vibrations.

Wojciech Matusik, professor of electrical and computer engineering at MIT and head of the Computational Design and Manufacturing Group within CSAIL, celebrated the advances made by the smart glove. “It is the first step to building personalized artificial intelligence agents that continuously capture data about the user and the environment. (This invention) helps perform complex tasks, learn new skills and promote better behaviors,” he noted in a statement.

More uses of the smart glove: robotics, virtual reality, manual arts and aviation

smart glovesmart glove
The researchers plan to use the smart glove for various tasks in addition to teaching piano playing. (Credit: Courtesy)

The innovation developed at the American institute is wide-ranging. In addition to being used to learn piano, researchers are evaluating other uses and scenarios. One of them is the teleoperation robots. In tests, they discovered that the smart glove can transfer sensations to mechanical arms, allowing the automatons to perform delicate tasks. The step is not trivial, given the challenges that robots have so far exhibited when manipulating fragile objects and interacting with people, without risk of injury. “It’s like teaching them to behave like humans,” Luo says.

The MIT glove also knows what fun is about. In one of the experiments, it was used for a racing video game. Users collected coins as their car moved at full speed. To the researchers’ surprise, players who used haptic feedback achieved higher scores compared to participants who used traditional input methods.

In addition, the smart glove would serve to create more immersive virtual reality experiences. In practice, it would allow users tap digital environments with more personalized mechanisms. There’s more, and that breadth is really lovely. According to the experts involved, A device of this type will be useful for surgical medicine courses, craft workshops, and even for the training of airplane pilots..

The plans that MIT CSAIL already has for the revolutionary glove

The glove’s sensors are attached using a specialized embroidery machine. (Credit: MIT CSAIL/Nature)

What news is there for the future of this development? Following Luo, the current system only comprises simple movements. In what follows, they plan to incorporate additional data for the appearance of more personalized devices, which allow addressing complex tasks.

“We are using the adaptive feedback optimization process. This allows us to address the challenges, being that everyone tends to use the gloves differently and has a characteristic reaction to the same feedback,” Luo closes in dialogue with this publication.

The results of the research were recently published in the journal Nature. The work was supported by a grant from the MIT Schwarzman College of Computing, through Google. He has also received a grant from GIST-MIT, and additional help from Wistron, Toyota Research Institute and the firm Ericsson.

Receive our newsletter every morning. A guide to understanding what matters in relation to technology, science and digital culture.

Processing…

Ready! You are already subscribed

There was an error, refresh the page and try again

Also in Hipertextual:

 
For Latest Updates Follow us on Google News
 

-

NEXT 5 Stardew Valley-type games for Android mobiles