Video Friday: Robohand, Entropy-Powered AI, and Bad Breath Bot

It's Friday, and we know what you need: robot videos

3 min read
Video Friday: Robohand, Entropy-Powered AI, and Bad Breath Bot

It's been a week filled with robot videos. Evan's dispatches from ICRA featured 3D-printed inchworm bots, IKEA furniture assembly robots, quadrotors with tilting propellers, a six-legged acrobatic robot, a robot with whiskers, and PR2 fetching coffee. But wait: the week is not over yet, and we know exactly what you need: more robot videos, of course!

This is a fantastic, inspiring story involving 3D printing technology and a carpenter from South Africa who'd lost four fingers. This is what happens when brilliant technology and brilliant human beings come together.

Via [ MakerBot ]

A researcher creates a new kind of AI that starts to demonstrate complex, intelligent behaviors. No, we're not talking about Skynet. A researcher with ties to MIT and Harvard has actually created what he says is a powerful artificial intelligence that, in simulations, was able to "walk upright, use tools, cooperate, play games, make useful social introductions, globally deploy a fleet, and even earn money trading stocks, all without being told to do so," as the video below explains. And here's where things get even weirder: the AI, called Entropica, is based on equations derived from the second law of thermodynamics, suggesting a link between entropy and intelligenceSome observers are skeptical. Others are skeptical of the skeptics. Is it for real? Only time, and entropy, will tell.

[ "Causal Entropic Forces," Physical Review Letters ] via [ BBC ] and [ io9 ]

What happens when you mix circus, high voltage, robots, lasers, games, and a man with a mohawk? The result is Two Bit Circus, an exhibit/performance created by a troupe of Los Angeles artists and builders. One of the cofounders is Brent Bushnell, who we profiled last year. To fund their "carnival of the future," they're looking for supporters through a Kickstarter campaign.

Via [ Tech Talk ]

HERB, the Carnegie Mellon robot butler that loves Oreos, has learned to use color video, a Kinect, and some non-visual data to discover more than 100 objects in a home-like laboratory, including computers, plants, cooking items, and a box of donuts.

Via [ Gizmag ]

Japanese researchers from a group called Crazy Labo (we are not kidding) have created a female robot named Kaori that is capable of detecting if you have bad breath. Just breathe on her face and she'll give you instant feedback, like "Yuck! You have bad breath!" Or, in the worst case scenario: "Emergency taking place!"

[ Asahi Shimbun ] via [ Kotaku ]

Quince is a nimble crawler robot that Japan deployed in the aftermath of the 2011 tsunami and earthquake. Search and rescue personnel used the robot to look for survivors and inspect damage. Since the disaster, Japanese researchers have continued to improve the robot, and they've recently demonstrated the newest design, which features additional sensors and camera systems.

[ fuRo ]

Are robots on track to defeat the human world champions by 2050 (that's the goal of Robocup)? It's clear that hardware for adult-size humanoids will need huge improvements, but things on the software side look much better. This video, a match during the Robocup German Open 2013, shows how the quality of individual and team play is improving. Sure, these robots are no Kaka or Messi. But never underestimate a robot. Game starts at 4:20.

Thanks, Thomas!

All we can say about this project is that it's called robuPINGU. And it's from France. And that the Uncanny Valley definitely applies to penguins!

Robosoft ]

Photo: MakerBot Industries

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