We're always caught slightly off-guard when major Asian electronics companies introduce a new robot with virtually zero warning, like Toyota just did with their Human Support Robot, or HSR. Designed to assist disabled people, the HSR looks like it might be good for all kinds of household tasks whether you're disabled or not.

There isn't a heck of a lot of information beyond what Toyota provided in their (translated) press release, but here's what we know: the HSR has a tablet for a head that can be used for telepresence or as a graphical interface, as with Ava. The base is mobile, with a PR2-style articulated torso that can extend from about half a meter in height up to just under a meter and a half. It sort of looks like there's an Xtion in the head, but we're not sure what other sensors might be in there as well. Top speed is 3 kph, and the HSR can make it over 9mm obstacles and climb slopes of 5 degrees.

The arm, which appears to have six or seven degrees of freedom plus the gripper, can lift small objects that weigh 1.2 kilos or less. It's designed to move slowly enough to be inherently safe, but we have no idea what sort of precision or intelligence is built into it.

This is an interesting robot to see from Toyota for a couple reasons. While we don't have any information as to what it might cost, you don't use a tablet brain, an Xtion, and just a single arm unless you're being at least a little bit mindful of what the price is going to end up as. Also, as we mentioned, while acting as an aid to disabled humans is a fine entry point for robots (especially considering that insurance in Japan defrays 90% of the cost), there's no reason that this robot wouldn't be just dandy for doing tasks for those of us who are able-bodied as well, provided that it has the sensors necessary to actually do all the stuff we'd want it to.

Toyota's new robot has been undergoing testing at the Yokohama Rehabilitation Center for the last year, and it'll be on display in Tokyo this week.

[ Toyota ] via [ Gizmag ]

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

“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