The Battle of Wits Has Begun!

Yeah, I’ve made the mistake of getting involved in a land war in Asia once or twice… Bad times.

As always, you can catch the other Bots With Stuff from last week over on The Shoebox Blog, including a robot with that blue stuff that you put combs in, and a robot with the only ticket to Space Butter 3000.

[ Bots With Stuff ]

Remind you of anything? This latest Roomba is still lagging a little bit when it comes to defensive systems, though… Unlike the QQ3, it can’t boast “anti-aircraft fire performance.” But it does eat people, so it’s certainly good for something.

VIA [ Robots Dreams ]

This painting was created on an iPhone using the Brushes app by none other than Crabfu. Geez, this guy does everything. One more, after the jump. (Read more…)

Those baseball playing robots we watched in action on Monday utilize 1000 FPS cameras and high speed motors to duplicate (and improve upon) what humans can do. But the system is capable of much more than just baseball… This video showcases just some of the talents of these robots, and it’s clearly way beyond what we’re capable of in both speed and precision.

[ Ishikawa Komuro Lab ]

Instead of designing one single generalized fire fighting robot, QinetiQ has developed an entire specialized team to tackle especially dangerous fires involving acetylene gas cylinders. There are three different ROVs, each with a specific task: a modified Talon equipped with thermal imaging cameras that does reconnaissance, a larger bot with wheels called Black Max that carries a high pressure water hose, and the Brokk 90, which is a robotic mini-digger that can shove debris and obstacles out of the way to get at the cylinders themselves.

The BBC has a video of the robots in action, but like all BBC embedded programming, it doesn’t seem to work in Firefox. Bleh.

[ QinetiQ ] VIA [ Ubergizmo ]

In May, we posted about a group of researchers from Georgia Tech who have been working on an “ethical governor” for military robots. Dr. Ronald Arkin, director of Georgia Tech’s Mobile Robot Laboratory, was interviewed by H+ magazine on the subject, and we’ve got some choice excerpts below:

In his recent book, Governing Lethal Behavior in Autonomous Robots, Dr. Arkin explores a number of complex real-world scenarios where robots with ethical governors would “do the right thing” — in consultation with humans on the battlefield. These scenarios include ROE and LOW adherence (Taliban and Iraq), discrimination (Korean DMZ), and proportionality and tactics (urban sniper).

Arkin’s “rules” end up altering Asimov’s rules to look more like these:

1. Engage and neutralize targets as combatants according to the ROE.
2. Return fire with fire proportionately.
3. Minimize collateral damage — intentionally minimize harm to noncombatants.
4. If uncertain, invoke tactical maneuvers to reassess combatant status.
5. Recognize surrender and hold POW until captured by human forces.

Dr. Arkin and his colleagues at Georgia Tech have developed a “proof-of-concept” prototype ethical governor. His software architecture is likely years away from use on the battlefield.

h+: Some researchers assert that no robots or AI systems will be able to discriminate between a combatant and an innocent, that this sensing ability currently just does not exist. Do you think this is just a short-term technology limitation? What such technological assumptions do you make in the design of your ethical governor?

RA: I agree this discrimination technology does not effectively exist today, nor is it intended that these systems should be fielded in current conflicts. These are for the so-called war after next, and the DoD would need to conduct extensive additional research in order to develop the accompanying technology to support the proof-of-concept work I have developed. But I don’t believe there is any fundamental scientific limitation to achieving the goal of these machines being able to discriminate better than humans can in the fog of war, again in tightly specified situations. This is the benchmark that I use, rather than perfection. But if that standard is achieved, it can succeed in reducing noncombatant casualties and thus is a goal worth pursuing in my estimation.

This is pretty much exactly what we were saying back in February when the media freak-out of the week was killer robots: in a nutshell, you can program a robot soldier just as well as, and in some cases more effectively than, a human soldier in specific combat situations. We can’t do it yet, but that’s why robots currently don’t have direct unsupervised control over their own weaponry.

More, after the jump. (Read more…)

We wrote about Coandâ effect flying saucers years ago over on OhGizmo, but not much has been heard regarding development of these UAVs until this video popped up on YouTube a few days ago. The Coandâ effect is the tendency of air (or any fluid) to stick to a curved surface. In the case of the UAVs in the video above, a propeller at the top of the UAV thrusts air downward over its curved body to create lift. Why bother? Simple: the rotor is completely enclosed and smaller than the diameter of the UAV, which means that the UAV can bump into things while maintaining a hover, ideal for use indoors or in any other restricted environment where exposed blades would be a bad thing. You know, like around humans, with our soft, fleshy necks.

Those of you with a passing familiarity with helicopters, or a knowledge of basic physics, are probably wondering a.) why the body of the UAV isn’t spinning out of control in the opposite direction to the rotor blade and b.) how the heck it steers. The vanes you see around the sides of the UAV are slightly rotated, directing the downward thrust sideways to counteract the torque. Some of the vanes are movable, and in combination with flaps around the bottom of the UAV, you’ve got your pitch, yaw, and roll. Another big advantage over helicopters is that a Coandâ effect UAV is dynamically balanced, making it much more resilient to impacts or failures.

So why isn’t everybody and their dog using one of these things? Generally, they’re not nearly as efficient as a helicopter, which means significant reductions in both payload capacity and endurance. But as engine efficiency increases, the advantages of Coandâ effect UAVs are going to pay off, and I imagine we’ll be seeing a lot more of these things in the future.

[ AESIR ] VIA [ Danger Room ]

This unnamed humanoid (or “uh” for short) from Iowa State University’s Developmental Robotics Lab is trying to figure out how the world works in the same way as a 2 year old does: by attempting to break stuff. Well, not exactly break stuff, but the robot does manipulate objects in a variety of different ways to try to establish their physical characteristics. It pushes things, shakes things, and drops things, and gradually builds a mental picture of sorts of what kind of object its playing with.

This type of experimentation is a distinctly biological method of learning, and has the advantage of not relying to heavily on one type of sensor… Robots tend to focus on visual information (in some wavelength or other, anyway), but when a human gets introduced to a new object, we’re more inclined to grasp it and turn it over in our hands while looking at it. We then store all of the characteristics of the object, and if we encounter something similar, we can make inferences about what other characteristics it might have. Unnamed humanoid is pretty good at doing the same thing, using what it’s figured out about a set of objects to identify them with an accuracy of 99%.

The next step that’s currently being worked on is experimentation with a goal in mind. For example, the robot is given a pencil and has to figure out how to draw something. If you later give the robot a pen, it should be able to determine that the pen is much like the pencil and use it the same way. And differences are equally important to discover, since differences generally provide important information about specific functions. Eventually, researchers hope to create some kind of robot butler that’s able to teach itself new tasks largely without your help.

There’s a video after the jump, with some decent footage that’s almost, but not quite, entirely spoiled by a TV host. (Read more…)

Okay, BotJunkies: here are the results of our contest to decide what to call a group of robots. Each of our judges has their top ten picks, and it wasn’t easy… Steve Rainwater and David Calkins have sent along explanations of why they chose the terms they did, and as you read through them, you’ll understand just how much thought all the judges put into their decisions. Lem Fugitt’s picks are right here, and you’ll find Steve and David’s picks after the jump, along with a few of my favorites and the overall second and first place winners.

Lem Fugitt, Editor of Robots Dreams:

I was extremely surprised and pleased with the large number of entries and the creativity. Readers obviously took the contest seriously and put some thought into their selections. The entries ranged from obvious to obscure to hilarious, which made the process of narrowing them down quite a challenge.

My top 11 (I hate arbitrary round numbers) are:

Battery, Quandary, Singularity, Sprocket, Gear, Waldo, Meme, Future, Foundation, Discovery, Matrix

Of those, my favorites are:

#3 Discovery
#2 Singularity
#1 Waldo

A waldo of robots, first submitted by StephenMS.

The rest of the results, after the jump. (Read more…)

Robots might not be quite ready to play soccer against humans, but from the looks of this video, professional robot baseball is not too far away at all. These industrial robots are using baseball to demonstrate their ability to work together while dynamically adapting to rapidly changing situations. The pitcher uses a robot arm from MIT coupled to a high speed three fingered hand from the University of Tokyo, and it’s capable of throwing a ball into the strike zone at 25 mph 90% of the time. The batter, meanwhile, is only 11 feet from the pitcher, but using camera eyes running at 1000 frames per second, it has plenty of time to decide when and where to swing, and boasts a “near perfect” batting average against strikes. In the future, the pitcher will be able to throw a variety of pitches at over 90 mph, while the batter will be programmed to repeatedly hit to the same place.

Now, the problem here is that these robots are already just about at the point where watching them play an actual game of baseball would be pretty dull. The robot pitcher will always throw strikes, and the robot batter will always hit it wherever it wants. Home run every time? Sure, no problem. Barring a mechanical malfunction, the robot players wouldn’t make it out of the top of the first. The only solution would be to limit the capabilities of the robot, either mechanically or by introducing some kind of stupidity or randomness into the AI… But I think maybe instead we should just agree that baseball is a game best played by us humans with our charming flawed brains and slow reflexes.

[ Mainichi (Translated) ] VIA [ Pink Tentacle ]