Cloud Robotics Engine Goes Live with Rapyuta Service

RoboEarth's Rapyuta makes your robot smarter through the magic of cloud computing

2 min read
Cloud Robotics Engine Goes Live with Rapyuta Service

The team behind RoboEarth yesterday announced the launch of Rapyuta, a cloud computing platform for robots. Rapyuta is designed to be a combination of a remote processor powerhouse and a giant database storing all robotic knowledge: robots will be able to offload complex tasks to Rapyuta, and they'll also be able to ask Rapyuta for help if they get stuck trying to recognize an object or complete a task (above, a simplified overview of the Rapyuta framework). Here's how it'll eventually all come together:

"The developed Platform as a Service (PaaS) for robots allows to perform complex functions like mapping, navigation, or processing of human voice commands in the cloud, at a fraction of the time required by robots' on-board computers. By making enterprise-scale computing infrastructure available to any robot with a wireless connection, the researchers believe that the new computing platform will help pave the way towards lighter, cheaper, more intelligent robots."

An easy way to think of this is like Google Goggles or Siri: your cellphone doesn't have the power to do voice recognition or image analysis, so it just sends the raw data off to some giant server somewhere, and then gets the answer back. This makes your cellphone a whole lot more useful to you, and as those giant servers get faster and smarter, your cellphone gets better without you having to spend any time or money on it. Such are the benefits of the cloud.

However, there are some things that the cloud is good for, and some things that the cloud is not so good for. The disadvantage of the cloud is that it's remote, and that means you're generally relying on infrastructure that you don't always control to talk to the cloud. You have to deal with Wi-Fi or cellular connections, and then whatever pipe ends up connecting your access point to the Rapyuta server. If you've got a beastly Internet connection and a nice router you're set, but as anyone who's ever tried to use a telepresence robot will tell you, getting the connectivity you need to reliably do anything that requires a lot of bandwidth and low ping is a major headache.

So like, in the video, it may not necessarily be realistic to use a cloud service to build maps at this point, because depending on what hardware you've got, it may involve impractically large data transfers. Folding clothing may also be tricky. Something like grasping could work better: the robot might have to upload just a single 3D image, and for object detection involving barcodes, QR codes, or RFID tags, it should be very quick. Of course, networking issues are out of RoboEarth's control, and fortunately, communications infrastructure is being improved all the time. This means that we're just seeing the first hints of what this service is capable of, and within a few years, it could potentially enable all kinds of complex task solving on even the simplest of robots.

Incidentally, if you're wondering about the origin of, "Rapyuta," it comes from a 1986 animated feature film written and directed by Hayao Miyazaki. In the movie, Rapyuta is a flying city with a giant robot living in it. Here's the trailer.

Rapyuta: The RoboEarth Cloud Engine, by Dominique Hunziker, Mohanarajah Gajamohan, Markus Waibel, and Raffaello D’Andrea, will be presented at ICRA 2013 in Karlsruhe, Germany in May.

[ Paper ] via [ RoboEarth ]

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