Japanese MH-2 Shoulder Robot Wants To Be Your Friend, Literally

This 20-DOF miniature humanoid acts as a shoulder-mounded remote-telepresence avatar

2 min read
Japanese MH-2 Shoulder Robot Wants To Be Your Friend, Literally

Nobody likes being alone, and Japanese researchers from Yamagata University are developing a robot to make sure you’ll never have to be alone again: the MH-2 wearable miniature humanoid lives on your shoulder and can be remotely inhabited by your friends from anywhere in the world. 

MH-2 (that’s “MH” for “miniature humanoid”) is a wearable telepresence robot that acts as an avatar for a remote operator. With two 7-DOF arms, a 3-DOF head and 2-DOF body, plus one additional DOF for realistic breathing (!), MH-2 is designed to be able to mimic human actions as accurately and realistically as possible. Think Telenoid, except it can actually do stuff besides wiggle around semi-creepily.

This may seem a little bit weird at first, but here’s the idea: you’ve got a friend or a relative that you want to share an experience with. Like, you’re traveling or something, and you want some company. Instead of having said friend come along with you (we’ll assume that they’re busy as opposed to just antisocial), you can bring along an MH-2 instead. Back home, your friend puts on a 360-degree immersive 3D display and stands in front of some sort of motion capture environment (like a Kinect, for example). Then, they get to see whatever the MH-2 sees. Meanwhile, the robot on your shoulder acts like an avatar, duplicating the speech and gestures of your friend right there for you to interact with directly. Ultimately, this is what the MH-2 is going for:

For all this to work convincingly, gestures need to be reproduced accurately and quickly, at a speed equivalent to a human being making gestures in real time. This is why MH-2 is so complicated and requires that gigantic backpack full of servos, which control its joints by tugging on wires:

This backpack doesn't look like it's probably a whole lot of fun to carry around for extended periods of time, which is why the researchers are trying to find ways to reduce the bulk of the 22 (!) actuators that are currently required to operate the MH-2. Until that happens, you'll just have to accept the fact that using the MH-2 could possibly make you look like a little bit of a robot geek. Possibly.

The 20-DOF Miniature Humanoid MH-2: a Wearable Communication System, by Yuichi Tsumaki, Fumiaki Ono, and Taisuke Tsukuda, from Yamagata University in Japan, was presented this month at the 2012 IEEE International Conference on Robotics and Automation, in St. Paul, Minn.

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

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

"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.

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