New research from the Institute for Robotics at Carnegie Mellon University could help robots feel for layers of fabric rather than relying on computer vision tools to see them only. Work could allow robots to help people with household tasks such as folding clothes.
Humans use their senses of vision and touch to grab a cup or pick up a piece of cloth. It’s so routine that little thinks about it. However, these tasks are very challenging for robots. It is difficult to quantify the amount of data collected by touch, and it has been difficult to simulate meaning in robots – until recently.
said David Heald, associate professor in the College of Computer Science and chair of the department of robotics realization and doing (R-Pad) lab. “A lot of the sense of touch that humans do is natural to us. We don’t think much about it, so we don’t realize how important it is.”
For example, to fold clothes, robots need a sensor to mimic the way human fingers can feel the top layer of a towel or T-shirt and pick up the layers underneath. Researchers can teach the robot to feel and hold the top layer of fabric, but without the robot sensing the other layers of fabric, the robot will only grab the top layer and never fold the cloth.
“How can we solve this problem?” Hold asked. “Well, maybe what we need is touch sensing.”
ReSkinDeveloped by researchers at Carnegie Mellon and Meta AI, it was the perfect solution. The open source touch-sensing “skin” is made of a thin, flexible polymer embedded in it magnetic particles To measure 3-axis touch signals. In a recent research paper, researchers used ReSkin to help the robot sense layers of fabric rather than relying on its vision sensors to see them.
“By reading changes in magnetic fields from depressions or skin movement, we can achieve tactile sensing,” said Thomas Wing, PhD. A student at the R-Pad Lab, who worked on the project with RI postdoc Daniel Seita and graduate student Sashank Tirumala. “We can use this tactile sensing to determine how many layers of fabric we’ve captured by applying pressure with the sensor.”
Other research has used tactile sensing to grip hard objects, but the fabric is “deformable,” meaning it changes when touched — making the task more difficult. Adjusting the robot’s grip on the fabric changes its shape and sensor readings.
The researchers didn’t know how or where to grab the tissue. Instead, they taught him how many layers of fabric he was holding by estimating how many layers he was holding using the sensors in the ReSkin, then adjusting the grip to try again. The team evaluated the robot picking up one or two layers of fabric and used different textures and colors of the fabric to demonstrate the generalization beyond. Training data.
The thinness and flexibility of the ReSkin sensor allowed robots to be taught how to handle something as delicate as layers of fabric.
“The profile of this sensor is very small, and we were able to do this very precise job, getting it between the layers of fabric, which we can’t do with other sensors, especially optical sensors,” Wing said. “We were able to use it to do tasks that weren’t achievable before.”
There is a lot of research to be done before handing over the laundry basket to a Robot, anyway. It all starts with steps like smoothing out a wrinkled piece of fabric, choosing the right number of layers of fabric you want to fold, and then folding the fabric in the right direction.
“It’s really an exploration of what we can do with this new sensor,” Wing said. “We’re exploring how to make robots feel this magnetic skin of soft things, and we’re exploring simple strategies for handling the fabric we need so the robots can finally do our laundry.”
The team’s research paper, “Learning the Uniqueness of Fabric Layers Using Haptic Feedback,” will be presented at the 2022 International Conference on Intelligent Robots and Systems, October 23-27 in Kyoto, Japan. He also received the Best Paper Award at the conference’s 2022 RoMaDO-SI workshop.
paper: Learn to separate layers of fabric using haptic feedback
Carnegie Mellon University
the quote: Robots That Can Feel Layers of Cloth May One Day Help Laundry (2022, Oct 26) Retrieved Oct 26, 2022 from https://techxplore.com/news/2022-10-robots-layers-day-la Laundry. html
This document is subject to copyright. Notwithstanding any fair dealing for the purpose of private study or research, no part may be reproduced without written permission. The content is provided for informational purposes only.
#Robots #feel #layers #fabric #day #laundry