Lockheed's Drones Cooperate to Autonomously Put Out Fires

Stalker and K-MAX talk to air traffic control to safely operate while detecting and dousing fires

2 min read
Lockheed's Drones Cooperate to Autonomously Put Out Fires
Photo: Lockheed Martin

Last year, Lockheed Martin demonstrated (semi) autonomous firefighting capabilities with an unmanned K-MAX cargo helicopter and a small quadrotor. There were still humans in the loop, though, and the whole test was carefully monitored to make sure that there were no conflicts with other aircraft in the area. Last month, Lockheed held another firefighting demo, this time with even more autonomy and real-time integration with air traffic control.

Usually, when big drones are doing big drone stuff, the Federal Aviation Administration sets up a Temporary Flight Restriction (TFR) around them, and air traffic control makes sure that no other aircraft get close. This is a good way of maintaining safety, but it’s super annoying for pilots, because it can turn straight line routes into slaloms. To be successful, unmanned aircraft systems (UAS) are going to have to learn how to play nice with other aircraft, and that means talking to air traffic control just like human pilots do.

img Lockheed Martin’s K-MAX unmanned helicopter and Stalker XE fixed-wing drone. Photo: Lockheed Martin

During Lockheed’s firefighting demo, both the K-MAX unmanned helicopter and Stalker XE fixed-wing drone used experimental UAS traffic management capabilities to maintain real-time communications with the local air traffic control system. This likely includes information like “here I am” and “here’s where I’d like to go,” along with an interactive component that allows the drones to respond to basic instructions from controllers.

For the actual firefighting part of the demo, the Stalker XE drone used its infrared camera to identify the fire, and then relayed its location to the autonomous K-MAX helicopter, which nailed the fire with a well-targeted water drop:

Fire spotting (and remote firefighting in general) is an excellent task for drones. It’s important to catch fires as soon as possible, since smaller fires are easier to manage, but the best we can do right now is to send out humans in light aircraft to wander around looking for smoke. Midsize fixed-wing drones could easily take over this task, covering enormous areas far more than humans can, equipped with dedicated fire spotting sensors to make them more effective as well. And since the drones would be operating only in remote areas, it wouldn’t be too much of a burden to our air traffic control infrastructure.

The Stalker XE can fly for 8 hours at a time, day and night and in all weather, and the K-MAX is also capable of anytime, all-weather operation, meaning that it could probably conduct water drops in the middle of a monsoon, if you wanted it to for some reason. But seriously, having robots like these available could mean that human firefighters on the ground get triple the amount of aerial support that they do now, relying on manned aircraft, which leads to fewer fires as well as increased safety for the people fighting them.

[ Lockheed Martin ]

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