The July 2022 issue of IEEE Spectrum is here!

Close bar

Robot Helps You Put Your Shirt On

If you've ever gotten stuck in a t-shirt, this robot is for you

2 min read
Robot Helps You Put Your Shirt On

If you've ever gotten stuck in a t-shirt, this robot is for you.

For most people, putting on a t-shirt isn't a chore, but researchers at Nara Institute of Science and Technology in Japan have identified this important task as particularly difficult for the elderly or disabled with limited arm movement.

A cross-laboratory team led by Tomohiro Shibata and Takamitsu Matsubara developed a two-arm robot to slide a shirt over and onto a person's head and torso. Since a person's neck or arms may not be in the exact same position each time, a scripted movement could potentially cause distress.

Enter the team's reinforcement learning approach. Just like a child learning through experience, the robot is taught once how to clothe a human user, and then is given several attempts to put the shirt on by itself. The success is measured with motion capture system at the end of each trial, which lasts about 10 seconds.

In the video, we see that after three learning trials, the robot has learned the trajectory to place the shirt on without any trouble. According to Shibata, Japanese reporters who tested out the system gave it a thumbs up, saying it makes it easy to put on.

For now, the system has been tested with only a couple of different t-shirts and with several subjects including a few patients. The next step, says Shibata, is to try out the system with more subjects and patients, and with different t-shirts. "Our approach could be applied to other types of important clothing tasks such as pulling up/down pants."

Shibata, Matsubara, and their colleagues T. Tamei and A. Rai presented a paper, "Reinforcement Learning of Clothing Assistance with a Dual-arm Robot," describing their results at the 2011 IEEE-RAS International Conference on Humanoid Robots held in Bled, Slovenia, last week.

Angelica Lim is a graduate student at the Okuno and Ogata Speech Media Processing Group at Kyoto University, Japan.

The Conversation (0)

How the U.S. Army Is Turning Robots Into Team Players

Engineers battle the limits of deep learning for battlefield bots

11 min read
Robot with threads near a fallen branch

RoMan, the Army Research Laboratory's robotic manipulator, considers the best way to grasp and move a tree branch at the Adelphi Laboratory Center, in Maryland.

Evan Ackerman
LightGreen

“I should probably not be standing this close," I think to myself, as the robot slowly approaches a large tree branch on the floor in front of me. It's not the size of the branch that makes me nervous—it's that the robot is operating autonomously, and that while I know what it's supposed to do, I'm not entirely sure what it will do. If everything works the way the roboticists at the U.S. Army Research Laboratory (ARL) in Adelphi, Md., expect, the robot will identify the branch, grasp it, and drag it out of the way. These folks know what they're doing, but I've spent enough time around robots that I take a small step backwards anyway.

This article is part of our special report on AI, “The Great AI Reckoning.”

The robot, named RoMan, for Robotic Manipulator, is about the size of a large lawn mower, with a tracked base that helps it handle most kinds of terrain. At the front, it has a squat torso equipped with cameras and depth sensors, as well as a pair of arms that were harvested from a prototype disaster-response robot originally developed at NASA's Jet Propulsion Laboratory for a DARPA robotics competition. RoMan's job today is roadway clearing, a multistep task that ARL wants the robot to complete as autonomously as possible. Instead of instructing the robot to grasp specific objects in specific ways and move them to specific places, the operators tell RoMan to "go clear a path." It's then up to the robot to make all the decisions necessary to achieve that objective.

Keep Reading ↓Show less