Sandia National Labs Gives Roboticists a Hand

Sandia's new robotic hand offers all the degrees of freedom you want at 10% of the cost

2 min read
Sandia National Labs Gives Roboticists a Hand

Sandia National Labs is one of those secret places that does a lot of cool stuff with robots, but that we don't always get to hear about. They were initially responsible for that jumping robot as well as nine other robots that the Smithsonian snapped up a while back, and as part of DARPA's ARM program, Sandia has partnered with Stanford to create a dexterous robot hand on the cheap.

As Sandia puts it, "the Sandia Hand addresses challenges that have prevented widespread adoption of other robotic hands, such as cost, durability, dexterity, and modularity." The modularity and dexterity are easy to see in the video (you can even attach other tools, like screwdrivers or flashlights or laser cannons), and the modular design also makes the hand durable, since the fingers will just fall off if something smacks into them. If this happens, don't panic! As principle investigator Curt Salisbury explains, "if a finger pops off, the robot can actually pick it up with the remaining fingers, move into position and resocket the finger by itself.” Neat trick. Also, the "skin" of the hand is designed to mimic the flexibility of human tissue, providing some shock absorption and allowing the hand to more firmly grasp objects.

So that's all good stuff, but the cost bit is where the hand really comes through: in low volume production, the Sandia Hand should only cost about $10,000. Total. Fingers included. For the record, Sandia's press release says that's about 90% less than other commercially available robot hands with similar independently actuated degrees of freedom. Yes, that means that you can buy ten hands when you might have only been able to afford one. Ten. Just imagine what kind of robot you could build with TEN HANDS! Like, you could build a robotic octopus with hands on all of its tentacles and then still add on TWO EXTRA HANDS to make it a DECAPUS! WOW! Thank you, Sandia, for making such things possible.

[ Sandia Labs ]

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