Skip to content

Creating a Drag-Friendly Apparel that Changes in Real Time

Creating a Drag-Friendly Apparel that Changes in Real Time

tech innovation 2022

Nathan Straub, a rising senior in computer science, works on a “skeleton” for the project—a network of accelerometers connected to a low-power computer. credit: University of Colorado at Boulder

The latest work from Sara Aguasvivas Manzano and her team has real-world, practical use. Wearable technology for astronauts is being explored in the space industry and large tech companies are eager to improve the inter-connected watches and other personal devices that increasingly support and streamline modern life.

But the CU Boulder team decided to make their project in the wearables space a little more…

The team, called Eschametronicas, is made up of Aguasvivas Manzano, along with rising junior Lily James and rising seniors Nathan Straub and Zixi Yuan. Together they have designed a costume for drag queens that incorporates neural networks and other creative techniques. The idea is that the costume responds and gestures when the queens perform with them on stage. James stated that the garment was thought to be like eye candy especially in terms of visual components, with indexed scales that move depending on the position of the person wearing it.

Aguasvivas Manzano’s research interests include soft robotics – focusing on the design, control and manufacturing of robots made from conformal materials such as hydrogels, fabrics, composites and more. He also has a special interest in the deployment of learning, modeling and control of soft robots that, while effective, cannot accommodate large and powerful computers in their physical design. For example a lightweight garment like this—which reacts to the physical environment in real time—requires a lot of computation and a lot of hardware space at first. However, that aspect is no longer a limiting factor in the overall design and in this case the team built a compiler to translate forward computational computation to neural networks to address those limitations.

“Neural networks are computational models loosely patterned after the human brain and they are very ubiquitous now,” she said. “Here I built a compiler that allowed us to automate the code-writing process. So now we can write code that can be interpreted in microcontrollers—tiny little computers that don’t have much memory or take up much space. ”

James’ personal work as a technically sound drag queen—documented on her YouTube channel—inspired the team to create a project that was decidedly out of the box. When it’s finished there will be various sensor networks throughout the design, including one on the hips, one on each knee, shoulders and sternum, Aguasavias Manzano said.

Aguasvivas Manzano said, “There’s a lot of design building and tailoring, but programming as well as using our compiler (nn4mc) to port neural networks.”

As they move forward with the project, the team will continue to perform more efficient calculations on the garment so that the computer inside doesn’t consume as much power. Doing so will improve usability, functionality and battery life.

Undergraduates are required to write a paper about their work for UROP, but Aguasvivas Manzano said that the team also intends to turn the project into a white paper and add it to the arxiv, as the project demonstrated creative skills and high levels of competence. Quality technical knowledge has shown both- how.

Aguasvivas Manzano earned his Ph.D. This will work for Spring and Apple. She said the team could not have done this type of research without support from the College of Engineering and Applied Sciences, the Correll Lab and the Intelligent Robotics Lab.

“In the five years I’ve been here, I couldn’t be happier with the culture, especially in the computer science department. It was really refreshing compared to other universities,” she said. “My advisor (Associate Professor Nicolas Correll) and the university itself enabled creative thinking—promoting out-of-the-box thinking that I haven’t seen at other institutions.”

James echoed similar sentiments, saying that whatever research she chooses to do is not only allowed, but encouraged.

“The most impressive thing for me was having Sarah for this process,” she said. “I have access to all these really wonderful people and all these resources, but not only that, I feel completely free to use those people or tools and research whatever comes to my mind.”


Carpentry compiler helps woodworkers design objects they can actually make


more information:
Sara Aguasvivas Manzano et al, High-bandwidth Nonlinear Control for Soft Actuators with Recursive Network Models, arXiv:2101.01139 [cs.RO] arxiv.org/abs/2101.01139

Provided by University of Colorado at Boulder

Citation: Creating a Drag-Friendly Apparel that Changes in Real Time (2022, June 21), Retrieved on June 21, 2022

This document is subject to copyright. No part may be reproduced without written permission, except for any fair use for the purpose of personal study or research. The content is provided for information purposes only.

credit source

Creating a Drag-Friendly Apparel that Changes in Real Time

#Creating #DragFriendly #Apparel #Real #Time

if you want to read this article from the original credit source of the article then you can read from here

Shopping Store 70% Discount Offer

Leave a Reply

Your email address will not be published.