Search and Rescue Dog Deploys Robot Snake via Bark Control

It takes a very well trained dog to be comfortable running around with a giant robot snake strapped to its chest

2 min read
Search and Rescue Dog Deploys Robot Snake via Bark Control

Many animals, including some humans, seem to have an instinctual aversion to snakes. Many animals, including some humans, also seem to have an instinctual aversion to robots. Couple that with a (totally understandable) instinctual aversion to running around in disaster zones, and it's remarkable that this robosnake-deploying disaster dog even shows up for work in the mornings. 

Disaster areas offer some of the trickiest types of terrain for anyone (robots or humans) to safely navigate. Quadrupeds are one of the most adaptable platforms in situations like these, which is one reason why we use trained dogs to search for earthquake survivors. Problem is, while dogs are great at getting around over the top of rubble and finding places where humans might be buried, they're too big to get down into nooks and crannies, and even if they could fit down in there, for their sake you probably wouldn't want to send them.

This kind of dangerous work is just exactly what robots are around for, and by giving them rides on trained disaster dogs, they can get exactly where they need to go quickly and safely. Watch a dog deploying a tethered snake robot in a disaster training exercise in the video below:

Carnegie Mellon University's Biorobotics Lab teamed up with Ryerson University's Network-Centric Applied Research Team (NCART) Lab and a (very well trained) dog named Freitag for this demo. While Freitag was lucky enough to be running around with a robot snake this time, the system can be adapted to deploy just about anything, and apparently, deployment is controlled by the dog: whenever it starts to bark (which it does when it smells a human), the robot jumps out of the dog's chest-pack and starts exploring. Cool!

For more information on the CARD (Canine Assisted Robot Deployment) system, you can check out a 2010 paper on IEEE Xplore at the link below.

[ Canine Assisted Robot Deployment for Urban Search and Rescue ] via [ CMU ]

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

“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