The July 2022 issue of IEEE Spectrum is here!

Close bar

RoboCore is a dedicated controller board that’s been designed from the ground up for robots. It’s sort of like an Arduino, except that instead of being a DIY generalist, it’s optimized for building and programming your own robots from scratch. You can plug all kinds of stuff into it, and it’s easy to program while also providing wireless and cloud connectivity without you having to muddle through all kinds of frustrating setup and configuration and customization. Video of how it works, plus more, ’cause it’s Friday Friday Friday.

For something like this to be successful in the way that it wants to, RoboCore needs to hit a critical mass of users where a community can establish itself (like Arduino did). And there are already lots of hardware and software solutions that can be used to build and control robots. It’s true that because of its purpose-built design, RoboCore might be better for some robots, but this also could be an issue with it, since it’s going up against well established communities based around systems that can control robots and a whole bunch of other stuff.

Anyway, if you want more detail on this thing you can get engineering specs here, and you can also head over to Kickstarter to pledge US $90 for one of your very own.

[ RoboCore ]

Valkyriedidn’t have the best time at the DRC Trials, but IHMC has done a huge amount of work into the control software. Here’s a sample of what Val can do now, and keep in mind that this is in real time:

So are we going to see Val compete in the DRC Finals? Please?

Even if we’re just stuck with boring ol’ Atlas (ha), IHMC has been working hard on that robot, too. Again, this is in real time:

Nicely done. We’re looking forward to a very brisk DRC Finals competition.

[ IHMC ]

Robots have been in movies for nearly a century, and that’s a lot of robots. Here’s proof:

Via [ Fusion ]

Thanks Tim!

Instead of racing around a course a ludicrous speeds with a car or an airplane, why not try a drone with some FPV hardware on it? This way, if you crash, the worst thing that happens is that you need a new drone, as opposed to a new body.

Via [ Motherboard ]

We’ve been wondering what Anki was going to do next, since the tremendous amount of funding that they’ve been able to raise suggests that they have some equally tremendous ideas on the horizon. And here it is, their next tremendous idea:

Yeah, it’s a modular track and more cars. I'm sorry, but that’s worth a resounding “meh” from our perspective. Allow me to quote Travis Deyle, from his Anki teardown/review from late last year:

It’s a bit presumptuous on my part, but I don’t believe that Anki sold anywhere near as many devices as they’d intended. If I were them, I would use whatever remains of that $105M in venture money to pivot (quick!). More tracks and cheaper cars won’t dig them out of this hole.

[ Anki Overdrive ]

Marek Michalowski from Beatbots is a long time friend o’ the blog. Here’s what he does all day:

[ Beatbots ] via [ ConnectEd ]

Curiosity has been on a walkabout on Mars, which sounds like fun. At least, it does if you like looking at rocks.

[ Curiosity ]

The University of Manitoba has posted three years worth of their RoboCup qualification videos. It’s kind of interesting to watch them all in order to see how much progression has been made in robot soccer over a relatively short time:

[ Snobots ]

Here’s a very cool idea:

Starting March 5 the custom ROBOCHOP app will allow online users to remotely command one of four giant robotic arms and instruct it to grab and sculpt a prefabricated 50 x 50 x 50 cm durable foam cube using an external hot wire tool.
Once manufacturing is complete each custom object will be packaged and posted to the user anywhere in the world.

I. Want. To. Do. This.

[ Robochop ]

Here’s a maybe even cooler idea:

Via [ Gizmodo ]

PAL Robotics’ Stockbot is, I would say, the most sinister RFID inventory robot in existence:

[ Stockbot ]

The ridiculously long video to end the week is a CMU Robotics Institute Seminar. Jan Peters, from TU Darmstadt, on “Motor Skill Learning: From Simple Skills to Table Tennis and Manipulation.” Enjoy!

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

“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