Gemini-Scout Will Be the First One In to Rescue Trapped Miners

Sandia National Labs has developed the Gemini-Scout robot to deliver air, water, hope, and portable gaming systems to trapped miners

1 min read
Gemini-Scout Will Be the First One In to Rescue Trapped Miners

Nobody wants to venture into a mine after an accident, but the people who least want to be in there are those who might be already trapped inside. Rather than ask for human volunteers to go in and check things out, Sandia National Labs has developed a robotic platform that doesn't have a choice, called Gemini-Scout.

Collapsed mines offer all kinds of obstacles that threaten to suffocate, burn, crush, drown, electrocute, or otherwise impede even the toughest of robots. With this in mind, Sandia has done their best to mine-proof Gemini-Scout, which can clamber over rubble, wade through up to 18 inches of water, and not cause huge methane gas explosions thanks to sealed and spark-free electronics.

As capable as Gemini-Scout is, it doesn't come with an attached multidimensional quantum escape tunnel or anything. While the robot is theoretically capable of dragging a human behind it, its primary mission is to scout ahead to send back video and sensor readings to help an actual rescue team safely and quickly get where they need to go. In the short term, the robot can also deliver vital supplies such as food, water, medicine, air packs, radios, and Sony PSPs to any miners who may be trapped out of immediate reach.

It sort of seems like a robot with Gemini-Scout's capabilities would be good for more than just working in mines, and that may be the case, but Sandia seems to be pretty focused on optimizing Gemini-Scout for this one task. Their primary customer at this point is the Mine Safety and Health Administration, and miners can look forward to having a robot ready and willing to help them out when Gemini-Scout enters service next year. 

Via [ Sandia ]

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