This time next week, we’ll be on our way to Hamburg, Germany, to attend IROS, one of IEEE’s mega robotics conference. We’re pretty excited about it, and although I don’t speak German, Google Translate tells me that “zeigen sie mir ihr roboter” is how you say “show me your robot,” which is really all I need to know.

It’s worth mentioning that the few days right before IROS is RoboBusiness out in Silicon Valley, which is going to make a handful of people extraordinarily jetlagged. We’re expecting at least a few announcements from RoboBusiness next week, and we’ll have our customary tons of cool stuff from IROS the week after. And then we’ll probably keel over and die, but it’ll have been worth it.

We’re not there yet, though, so here’s your weekly injection of steaming hot robot videos.

Everything you need to know about this video is that it’s a quadcopter taking a quadruped for a walk. Or the other way around.

[ ETH ]

We were introduced to SRI’s magnetically actuated micro-robots over a year ago, but this video shows real-time end-to-end assembly of a cubic truss segment, along with some new (as far as I know) videos showing the robots cutting wire, integration of electronics (like LEDs), and 1024 robots operating at once:

[ SRI ]

Hmm, looks like Clearpath is maybe, just maybe, working on something new and subtle:

Something about flexible warehouse automation and intralogistics? Now you know as much as we do.

[ OTTO ]

Clearpath would also like to remind you that they have lots of other research robots that you can buy and use and skip the whole spending half a decade building a platform thing:

Available in any color you want as long as it’s black and yellow.

[ Clearpath ]

In case you missed our nice big article on Wednesday, iRobot has released its most intelligent robot vacuum ever:

[ iRobot Roomba 980 ]

How many drones at once is ::too:: many drones at once? Certainly not just 50:

Stop. Just stop. You had me back at “50 v. 50 air war.”

Via [ New Scientist ]

Robotiq has announced a brand new 2-finger gripper, able to lift up to 2 kilograms of something 14 centimeters (!) wide:

I love that trick of dynamically adjusting grip strength on deformable objects.

[ Robotiq ]

If you don’t live close enough to Google to steal one of their self-driving cars, Robotnik has another option for you:

Note that its rear wheel drive system uses Ackerman kinematics, which means I get royalties whenever it drives anywhere.

[ Robotnik ]

The Bristol Robotics Lab has a new project called the Anchor Robotics Personalised Assisted Living facility, designed to help robotics researchers test out solutions for robotic home assistance. The testing environment is an apartment that’s way bigger than mine:

[ Bristol Robotics Lab ]

“RoboThespian RT4 demonstrates its adaptive grip, the under articulated finger design accommodates a wide range of objects. Large soft rubber surfaces allow the hands to grip heavy objects with minimal pressure.”

NO. BAD ROBOT. Next time, you RECYCLE.

[ RoboThespian ]

Watching this video of highly maneuverable smooth underwater robots has made me the most relaxed I’ve been all week:

[ MIT d’Arbeloff Lab ]

Did you know that if you look at a blinking light, the blinking frequency imprints itself on your brainwaves? With a brainwave sensor, you can leverage this to brain-select different blinking robots by just looking at them:

[ Thymio ]

Why ::wouldn’t:: you want a ROS-powered six-legged robotic spider that only costs $400 and will be delivered by Christmas?

[ Indiegogo ]

Nice to see Rethink Robotics’ Sawyer hard at work doing useful things:

I didn’t notice this before, but I really like the fact that it blinks.

[ Sawyer ]

Meanwhile, Baxter is doing some delicious assembly tasks at NC State (pay attention at around 1:15):

Robots building robots is cool, but PANCAAAAAAAKES!!!

[ Research Baxter ]

“[Former] DARPA Robotics Challenge (DRC) Program Manager Gill Pratt and Tactical Technology Office Director Brad Tousley recap the DRC, highlighting near-term accomplishments and long-term legacies in the field of robotics and the mission of disaster response.”

[ DRC ]

We’ll end with a talk from the CMU Robotics Institute Seminar Series by Parag Batavia from Neya Systems with some (non-technical) tips on how to bootstrap a robotics company:

[ Neya Systems ]

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
LightGreen

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