Video Friday: Ollie Rolling, RoboRaven Flying, TurtleBot Curling

After Dyson's big announcement, can there possibly be more robotic news this week? Of course

3 min read
Video Friday: Ollie Rolling, RoboRaven Flying, TurtleBot Curling
Photo: Sphero

Dyson sure did deliver this week. They managed to put together a fun little teaser video with just the right amount of truthiness mixed in, and followed it up with an excitingly unique consumer robot. Is it too much to ask that we get this sort of thing every single week from now on?

Probably, yeah.

The consumer robotics isn't quite at the level of, I dunno, the useless app market, where there are new products releases so relentlessly that they make me want to push that scary looking "Destroy Universe" button on my Android phone. What, you don't have one of those? Weird. But anyway, we have hope that one day, we will have the privilege of making announcements about new robots that you can buy much more frequently then we do now.

And then it'll be time to retire! But we're not there yet, so on to Video Friday.


As it happens, there was another consumer robot launch this week. Orbotix, the maker of the Sphero robotic ball, officially unveiled Ollie, a smartphone-controlled wheeled bot. Here are two promotional vids: 

[ Ollie ]



Too lazy to hand launch your flapping wing drone? You'd better get it its own robot:

Robo Raven ]



These ice bucket challenges are getting, um, involved. And it's probably not a coincidence that they're both from MIT.

CSAIL graduate student Ross Finman is nominated by his former colleague Hordur Johannsson to take the ALS Ice Bucket Challenge, but Ross soon discovers that Hordur is not the only oneor only thingthat wants him to participate...

And from MIT's department of mechanical engineering:



While we're on about MIT, here's a pair of videos from the MIT DRC team. The first shows ATLAS dragging a truss around like it's a comfort object, and the second shows a beautiful stereo depth fusion visualization:

This video demonstrates two features:

1) The use of stereo depth fusion using Kintinuous (originally used to build large maps with Kinect data) to a quality which matches LIDAR data. The heightmap shown was used to place the required footsteps a priori while stationary.

2) State estimation is provided by a highly tuned estimator developed by MIT. In this case it is running open loop (and not using any laser info). In open loop mode it drifts about 4cm in this total walking motion.




The IMAV 2014 conference included a competition for, you guessed it, MAVs. Tasks included mapping, recognizing and observing targets, rooftop landings, window entries, interior inspections, and acting as a flying WiFi relay, all autonomously:

[ IMAV 2014 ]



How do you make the sport of curling even weirder? Turtlebots:



This video demonstrates some of the basic capabilities of the Vaultbot, a mobile manipulation system in beginning stages of development at the University of Texas at Austin. 

The Vaultbot has two UR5 manipulator arms mounted on a Clearpath A200 Husky base, and is equipped with a Sick LMS511 LIDAR. Other components to be added include an RGBD vision sensor and various tooling for the manipulator end effectors.

[ UT Austin ]



In collaboration with Lockheed Martin, a team of research students and staff from Warsaw University of Technology successfully demonstrated the first phase of flight test and integration of unmanned aircraft platforms with an autonomous mission control system. The purpose of the project is to optimize the performance of unmanned aerial vehicles when flying in fleets manned aircraft, in order to make the best use of available assets for any given mission.



We cover a lot (all, if possible) of the research performed in Robert Wood's Harvard Microrobotics Lab, not least because he's working on ROBOT BEES. Usually, we don't ask roboticists personal questions, but the NSF has no qualms about doing so, so it's a bit of a different take on robotic research than we usually get.

[ Harvard Microrobotics Lab ]

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