A Smartphone Is the Brain for This Autonomous Quadcopter

University of Pennsylvania researchers partner with Qualcomm to turn a smartphone into the brains of a flying robot

2 min read
A Smartphone Is the Brain for This Autonomous Quadcopter
Photo: Evan Ackerman/IEEE Spectrum

At CES 2015, we stopped by the Qualcomm booth to check out a collaborative project with University of Pennsylvania researchers led by Vijay Kumar: it’s a quadrotor that uses a smartphone for a brain for autonomous flight, using only on-board hardware and vision algorithms, no GPS. Impressive.

Just to be clear on this, the only thing that the quadrotor has in terms of electronics is a motor controller and a battery. All of the clever stuff is being handled entirely by the phone, which is just a stock Android smartphone with a Qualcomm Snapdragon inside. In other words, this is not a special device (like Google’s Project Tango phone, which the UPenn researchers used in a demo last year); it’s something that you can pick up for yourself, and the UPenn guys only half jokingly offered to install their app on my phone and let it fly the robot.

This is a fantastic example of just how far smartphones have come: they’re certainly powerful computers, but it’s the integrated sensing that comes standard in almost all of them (things like gyros, accelerometers, IMUs, and high resolution cameras) that makes them ideal for low-cost brains for robots. What’s unique about the CES demo is that it’s the first time that a sophisticated platform like this (vision-based real-time autonomous navigation of a flying robot is pretty darn sophisticated) has been controlled by a very basic consumer device.

So, what’s next? Vijay Kumar tells us where they’re headed:

“What we’d like to do is make these kinds of robots smaller, smarter, and faster. When you make things smaller, the number of things you can do increases, and that’s where we hope to use lots of these guys. So think about a single flying phone that you have today; tomorrow, you’ll see a swarm of flying phones. That’s what we’re working towards.”

A swarm of flying phones? Where do I sign up?

[ UPenn ] and [ Qualcomm ]

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

“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