The Defibrillator Drone Is Another Good Drone Idea But Will It Work?

Medical emergency drones are a fantastic idea, but that doesn't mean that we're going to get them

2 min read
The Defibrillator Drone Is Another Good Drone Idea But Will It Work?
Image: TU Delft

Problem: Many people who go into cardiac arrest could be helped with an automated external defibrillator (AED)—as well as CPR from someone who knows what they’re doingbut most of the time, an AED isn’t handy. Solution: Turn a drone into a flying AED, and then send it to rapidly respond to emergency calls reporting a heart attack event. It’s a great idea, and its originator, TU Delft engineering graduate Alec Momont, has even built a functional flying prototype. But it is realistic?

It’s starting to feel like our job around here is to take things like drones and commercial robots and just list all the depressing reasons why they almost certainly will not work as well as we all want them to. Before you call us robo-phobes, remember: we love robots. The thing is, robots are extraordinarily compelling, but we don’t want people to get false hopes about robotics and feel misled if it doesn’t deliver on its promises. 

There’s a vague belief with robots (and with startups and drones especially) that just because something is awesome, and because it’s technically possible, it’s both necessary in the short term and inevitable in the long term. For some applications, this may be true. For other applications, it’s important to say, “Okay, a robot might be technically capable of doing this, but realistically, should it?”

I think that this flying defibrillator is one case where a robot is both capable of performing the task, and it can perform the task in a way that’s significantly better than any other method, such that it’ll make a tangible, valuable difference to end users (at least until Apple announces an iPhone with an AED built in).

In practice, though, there are all kinds of problems that are as yet unsolved involving drones that want to operate in urban environments. Namely, your drone needs more than just GPS to navigate and detect obstacles, and in most places, operation out of line of sight is both illegal and usually a bad idea. Also, landing next to panicky humans with six spinning blades of death.

The defibrillator drone has not solved these problems yet. At the moment, it’s a speedy hexacopter that, according to The Daily Mail, can “get a defibrillator to a patient within a 12 square kilometer zone within a minute,” improving the chance of survival from 8 percent to 80 percent. The drones would live at central dispatching points and use GPS to navigate to the location from which an emergency cell phone call was made. The commercial version would cost about US $19,000, and could hypothetically include all kinds of other handy things, like insulin or oxygen. It also includes a camera and speakers, so that people at the scene can be instructed on how to properly use said things.

Alec Momont says that he hopes the drone will “save hundreds of lives in the next five years,” but he’s got a lot of technology and regulation to work through before he can make that happen. We hope he’s successful.

[ Alec Momont ] via [ CNET ]

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

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