Bizarre Soft Robots Evolve to Run

These simulated robots may be wacky looking, but they've evolved on their own to be fast and efficient

1 min read
Bizarre Soft Robots Evolve to Run

This crazy looking thing is a simulated robot, made up of two different kinds of muscles along with bones and soft tissue for structure. This robot wasn't designed, it was evolved over a thousand virtual generations to move as fast, as far, and as functionally as possible.

It's nice that these researchers (including Jeff Clune from the University of Wyoming, who posted this video) are totally aware that these robots are wacky little things, but it's kind of amazing how successful evolution is at creating success out of just a few basic structures. And in the greater scheme of things, 1,000 generations is not a whole lot: in human terms, that's only 25,000 years, while modern Homo Sapiens have been around for ten times as long.

If this whole thing seems a bit familiar, it's because it's from some of the same researchers who worked on the Golem Project over a decade ago, including Cornell's Hod Lipson. Golem took things a step farther by evolving robots and then actually building them with a 3D printer:

The Golem paper, Automatic design and manufacture of robotic lifeforms (one of the coolest paper titles ever), can be read here

The current research has been published in Proceedings of the Genetic and Evolutionary Computation Conference, with the impressive title of Unshackling Evolution: Evolving Soft Robots with Multiple Materials and a Powerful Generative Encoding.

[ Jeff Clune ]

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