[Cue Don LaFontaine voice]

Imagine a world… In which the last human boxers… Have been crushed… By machines. Mechanical titans rule the ring… And one man’s destiny… Lies… With them. This… Is the world… Of… Real Steel.

I didn’t make that up. Here’s a bunch of other stuff that I didn’t make up:

The story, set in 2020, features Jackman as an out-of-work fighter who bonds with his estranged son when they go to work rescuing a junkyard find named Atom, and grooming it as a potential champion in the World Robot Boxing league.

“The heart of the story is this father and son relationship and in comes this junkyard robot called Atom that the kid’s in love with,” Jackman says. “I abandoned the kid pretty much at birth. But we come together because the boy’s mother has died. We have a lot of distance to make up. It’s through this mutual interest in robot boxing that they find a way to come together and form a bond.”

The one immediately redeeming feature of this move is that it’s not all CGI… Nineteen eight-foot tall boxing robots were created for the human actors to interact with. So, that’s cool, I guess.

Real Steel will be in theaters in November of 2011.

VIA [ USA Today ]

Mech Warfare is so awesome that the concept has made the jump across the pacific to Japan. The Trial of Survival Game puts multiple armed robots in combat with each other, and just like Mech Warfare, the bots are controlled strictly via remote camera systems. The Japanese version is a bit less structured… Multi-legged bots aren’t penalized with extra target plates, and wheeled vehicles are allowed. Either way, looks like fun:

The tinfoil hats, by the way, cover the hit sensors for the robots.

Or maybe they’re actually there to keep the government from brain controlling armed robots.

Or aliens.

(It’s aliens).

VIA [ Biped Robot News ]

AUVSI’s Autonomous Surface Vehicle Competition (or, RoboBoats) was held over the weekend. Autonomous robotic boats attempted to navigate around a small pond, avoiding obstacles and completing tasks. The course was pretty complicated, and the tasks weren’t easy either… Here’s an overview of how things were set up:

I’m not sure if spectators in orange shorts or the occasional hapless duck knew what they were in for, but apparently, one or two of the boats decided that they were either part of the course. Or threats. All I can say is, it’s a good thing there were no ducks in orange shorts, or things would have gotten ugly.

First place on Sunday (and $8000 in prize money) went to the University of Michigan, with the University of Central Florida and the University of Rhode Island taking second and third.

[ AUVSI ASVC ]

Thanks Michael!

Human World Cup Soccer (that’s football, to most of you) is fun to watch (even if it is on at 4am here in California), but as far as evolution goes, we humans have pretty much peaked. Really, the only thing about the game that evolves reliably from cup to cup is the ball (and that’s not always a good thing). Robots, on the other hand, have no such limitations. Carnegie Mellon’s CMDragons small-size robotic soccer team have taken another step towards robot domination by teaching their small size soccer bots the physics of ball movement. The demonstration below pits a robot that knows physics against a robot that doesn’t; keep in mind that the robots are entirely autonomous, controlled by a computer that watches the action on an overhead camera:

Without modeling the physics of the ball, the computer just tries to position the robots on the ball without taking the movement of the ball into account. A physical model allows the computer to move the robot predicatively, greatly improving dribbling skill:

Call me crazy, but these robots look to be demonstrating the same basic skills as talented human soccer players: win the ball, keep your body between the ball and your opponent, and then get an angle, get around him, and shoot.

Here’s a video of the CMU team competing in 2008, without the physics based planning software… Two years ago is a long, long time in the world of robots, but even so, the passing and shooting is impressive:

And if soccer’s not your thing, the same basic skills make the robots highly effective at playing minigolf:

I guess now we know what soccer robots do for fun in their spare time.

RoboCup 2010 starts in Singapore on June 19.

[ Stefan Zickler ] AND [ CMU Robot Soccer ] VIA [ Robots.net ]

It’s just like the walking iPhone, except bigger! Oh, and accelerometer-controlled googly eyes FTW.

VIA [ Robots Dreams ]

LuminAR, designed by Natan Linder, is not the first robotic desk lamp to come out of MIT. In 2007, I wrote about AUR, a 5 DoF robotic lamp designed to follow your movements around a desktop, changing the color, intensity, and focus of its light to help keep you organized and productive. LuminAR is quite similar in concept, except it’s significantly more complex, incorporating a pico projector along with a vision system to allow for a large degree of interactivity.

Fortunately, the interactivity looks to be intuitive rather than overbearing… There’s a point at which more features and more options are not necessarily a good thing. This tends to be a problem for robots in general: there’s just so much that you can do with them, that sometimes it’s hard to restrict yourself to a reasonable balance of simplicity and functionality.

[ LuminAR ] VIA [ DVICE ]

Folding towels was very cool, but UC Berkeley has much bigger plans for their PR2:

Towels were only the beginning of Berkeley’s work with non-rigid materials and laundry. Berkeley’s researchers will use the next two years to work on taking it to a whole new level: doing the full laundry cycle, from dirty clothes in a laundry basket to clean, folded clothes. This will present multiple, more difficult challenges. One of the challenges in folding towels was identifying the correct places to grab a crumpled towel and straighten it into a flat, foldable towel. With clothes, Berkeley will have to improve their techniques to handle more difficult and varied shapes. The PR2 will also have to operate with greater robustness and complete new tasks in order to finish the full laundry cycle.

In the area of perception, the Berkeley team will work on improving the PR2′s ability to find and interact with real-world objects. Some of the research areas Berkeley will work on include recognizing transparent objects, like glasses, finding people, and determining the correct way to grasp objects.

PR2 doing laundry from start to finish? Sign me up.

More info and an in-depth presentation at the link below.

[ Willow Garage ]

It’s been 2 years since we last checked out a robot arm controlled by a monkey brain. That arm (from back in 2008) had only four degrees of freedom, and this one is a whopping seven, but that doesn’t seem to phase the monkey much, as it deftly uses brain control to grasp a knob with the arm and receive a tasty reward.

At this point, the monkey is relying on two brain implants (in the arm and hand areas of its motor cortex) to interpret nerve impulses and use them to control the arm. The fantasy is (as least, as this technology applies to people with disabilities) is to make the controller non-invasive, and some of the technology is sort of there. Sort of. But perhaps more importantly, this experiment shows just how capable and adaptable a brain is, and the potential is very exciting. Or at least, my brain is excited… My body, on the other hand, is getting a little worried about its potential obsolescence.

[ MotorLab ] VIA [ IEEE ]

Geez, is there anything that you can’t do with LEGO Mindstorms? This biped isn’t dynamically balancing itself or anything (it’s held up by string), but that gait looks pretty natural. Plus, if you get bored with it walking, you can just rip it to pieces and then teach it to solve Rubik’s cubes or make a sweet spaceship or something.

[ University of Jena Locomotion Lab ] VIA [ Make ]

People use Roombas (generally, Creates) as bases for all kinds of robots… They’re not often used for bigger (heavier) bots, but if you stick four of ‘em together, you can apparently support a payload of up to 20kg or one Robotinho android. The Roomba QuadDrive was developed by University of Bonn’s Autonomous Intelligent Systems Lab, and consists of four Roomba 530s bolted together, and as far as mobile bases go, I imagine it’s probably pretty cheap and reliable. The top speed of 0.5 mph isn’t going to shock and awe, but it’s fine for tooling around a museum and scaring little kids:

And of course, the floors of that museum are damn clean. Quadruply damn clean.

[ Bonn AIS ] VIA [ Hizook ]