Meka and UT Austin Developing 'Hyper-Agile' Bipedal Robot

If Meka and UT Austin have their way, Hume could give PETMAN a run for its money

1 min read
Meka and UT Austin Developing 'Hyper-Agile' Bipedal Robot

Meka Robotics and the University of Texas at Austin, have already teamed up on one very cool robot, and they've just announced another: Hume, a "bipedal robot for human-centered hyper-agility." Hyper-agility, you say? Tell us more!

Hume is designed to study "planar rough-terrain locomotion," which means running at relatively high speed over uneven ground, something that humans are good at. And like humans, Hume will rely on minimal perception: when we run, we're not staring at the ground for every step, but rather adapting passively to small terrain variations without having to devote a lot of brain power to not falling on our faces.

To accomplish this, Hume relies on legs powered by compliant, force-controlled series-elastic actuators. The robot isn't running yet (or doing parkour, as the paper mentions it may eventually), but check out these legs:

If Hume looks a little bit like a certain other advanced bipedal humanoid we've met recently, that wasn't lost on the researchers, who mention in their paper that "we are aware of the new PETMAN robot by Boston Dynamics which delivers high mechanical power and speed but its detailed architecture is uncertain to us." A lot of things about PETMAN are uncertain, that's for sure, but it's pretty cool that we're getting to watch the parallel development of Hume at the same time, and we can only hope that we'll get to see the robots compete in a 100-meter dash some day.

[ Paper (PDF) ] via [ Hizook ]

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