Video Friday: Curiosity Learns to Scoop, Robot Tentacle Learns to Grab, iCub Learns About Rolling

It's a learning-filled Video Friday filled with learning, and videos, and robots

2 min read
Video Friday: Curiosity Learns to Scoop, Robot Tentacle Learns to Grab, iCub Learns About Rolling

Nope, we are still not done with our coverage of ICRA, the IEEE International Conference on Robotics and Automation, but we'll take a little bit of a break today to bring you a comprehensive Video Friday, featuring robots learning to do things like humans, and humans learning to do things with robots.

NASA's Curiosity rover still has a couple months of cruise time to Mars, but back here on Earth, its stunt double is working  hard at sample collection practice. The vid gives you a great sense of scale: this is one very big, very complicated robot:


iCub is intended to learn like children do, and that involves a lot of experimentation. Here, iCub is learning about rolling: some things roll, some things don't, and some things like to roll in some directions but not others. Through trial and error, iCub gradually figures this out. Good job!


Another robot that's trying to teach itself things is this Festo bionic handling assistant at the Research Institute for Cognition and Robotics (CoR-Lab) at Bielefeld University, in Germany. By "goal babbling" (a technique based on infant learning), the robotic tentacle figures out how to move in the right way to grab objects.

[ Paper ]


Robots aren't the only ones learning things this week. At MIT, students built and programmed autonomous robots to navigate a maze, collect blocks, and then use the blocks to build a structure. This was the final challenge for MIT's robotics course and it looks like it was probably a huge amount of fun.


The winner of Microsoft's Robotics@Home competition (announced over the weekend at Maker Faire) was Smart Tripod, a robotic  cameraman camerabot that uses a Kinect sensor to track people (and detect gesture commands) as they make their own videos. It works great, and I totally need one.

[ Microsoft ] via [ Engadget ]


Clean solar panels can increase power generation (and revenue or savings) by up to 7 percent. Cleaning solar panels is dull. Robots are okay with dull. Here's a solar panel cleaning robot from Greenbotics that will save you money, it's that simple:

[ Greenbotics ] via [ Treehugger ]


We've taken to occasionally wrapping up Video Fridays with some long academic vids for you hardcore types who've made it this far, and this week, we've got the opening remarks and keynote address from ROSCon 2012, posted courtesy of Willow Garage. The featured speaker is Morgan Quigley, one of the early architects of ROS, and he's talking about the past, present, and future of ROS.

Part two is here.

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