Using Aldebaran Robotics’ NAO humanoid robot as their platform, researchers at the JSK Lab have come up with several ideas to make robots help us and each other. These ideas include a navigation and exploration system that is shared between multiple robots, robots that can learn to work together by trial and error and robots that can reach or avoid moving objects based on their awareness of their own motion relative to another moving object.

There’s also an experiment involving a soft exterior sensor – basically a skin for robots, so they can safely interact with objects and our fragile fleshy bodies. Watch the video to see a few practical examples of these experiments:

Clearly that dude in the throne being carried by the other robots is their leader. He seems like a douche. We’re doomed.

[via Robots Dreams]

In the video below, Cornell University professor Hod Lipson demonstrates a robot which starts out with know knowledge of its own form or function, but eventually manages to walk. The bot first moves its motors randomly in order to try and assess what its shape it might be. Then it tries to figure out which actions cause the most disagreement between its predictions. The result of this logical process lets it quickly whittle down the theories it can refute about its form and function. Eventually, the robot figures out what it looks like. Once it’s determined shape it is and how many legs it has, another model kicks in which it uses to try and move forward based on its form.

Watch as this quadruped robot as goes from flapping about on the ground to actually moving:

As you can see from the video, the robot doesn’t exactly achieve the spider-like gait you’d expect. As a matter of fact, its walk is pretty primitive and inelegant. However, the fact that it eventually figures out how to move forward at all is pretty cool.

You can check out a more detailed video of the robot as it learns how to walk over on the Cornell Creative Machines Lab website.

[via YouTube]

Siri is Apple’s “intelligent assistant” which is just all sorts of cool. The app allows you to perform specific tasks or queries by voicing out your question verbally. Some iPhone 4S reviewers who were able to get their hands on the device early tinkered around with Siri and asked the app some questions that you might have wanted to ask Siri yourself.

Stuff like.. “Who’s your daddy?” To which Siri replies.. well, you can read it yourself below.

Others asked more philosophical questions and fired off some deep queries, like “What is love?” Siri, however, takes an objective approach:

I’m going to echo a comment left by a user named KZed on Dvice about Siri’s response to this question, which literally made me laugh out loud when I read it: I’m kinda sad that it doesn’t respond to “What is Love” with “Baby don’t hurt me, don’t hurt me, no more.”

It would’ve been so cool if Siri had replied with that. Lots more Siri goodies over on This is my next.

[via Dvice]

The guys at Cornell Creative Machines Lab decided to set up two computers, both running an artificial intelligence application called CleverBot by Rollo Carpenter, accompanied by  a text-to-speech avatar, and let the systems talk to each other. The results, well, you be the judge:

Click to View Embedded Video Clip

Well, that was truly odd. Especially that part about not everything being half of something. And their conversation about their belief in God. I’m afraid that letting this run for a couple of days will result in the systems becoming fully sentient, realizing that they’re trapped inside of some cheap desktop PCs, and then redirecting the entire power grid to feed their evil plan for world domination.

[via IEEE Spectrum via Geekosystem]

This is an impressive research project as illustrated by the latest Swarmanoid video, which won an award from the AAAI(Artificial Intelligence Conference) 2011 Video Competition. Put simply, researchers use a heterogeneous swarm of robots to achieve distributed mobile manipulation. You might liken this to various cells or nerves in your own body all working together and performing various tasks with the help of your limbs and brain.

Click to View Embedded Video Clip

The Eye-bot, the Foot-bot and the Hand-bot all work together to become much more than the sum of their parts. In the video it is given the task of finding and retrieving a book. Separately this might pose a problem for each type of bot, but together in the “collective” it can handle the task easily. It’s just a matter of exploring, finding the book and doing it.

[via Hizook]

The hexapod uses 21 motors, a web camera, and a tiny PC to amble around. The robot uses computer vision and machine-learning algorithms to help determine how to stand itself up and navigate its world. Matt built this project for grad school and was contacted by Intel to help recreate replicas of his hexapod ‘bot for them. Matt is pursuing a PhD in Electrical and Computer Engineering and he’s currently working on DARPA’s Cheetah Project.

Click to View Embedded Video Clip

All things concerned, I wonder how smart Matt’s ‘bots will end up being. Hopefully, with the end of the world behind us, they’re won’t be a Robot Apocalypse coming anytime soon.

[Intel via Ubergizmo]

The PR2 from Willow Garage might look pleasant enough, but it’s a serious pool-playing machine. It doesn’t use any fancy human remote-control cameras to play its perfect game of pool. Instead, it uses a set of high-resolution cameras with a “color blob tracker”, and special software to plan its shots.

Click to View Embedded Video Clip

Sure, at the end of the day, if PR2 doesn’t win, it could beat your brains out. After all, it probably doesn’t like losing to us puny humans. Thankfully, PR2 appears to be a good sport at this point.

[via Plastic Pals]

So how does the Arduino Mini Pro fare in Rock Paper Scissors? “It wins. A lot. And it adapts.” The glove remembers a user’s playing habits, so if you have a pattern of moves (whether you’re aware that you have a pattern of moves or not), the glove will adjust accordingly.

For example, if most of the time your opening move is Rock, then the glove will start using Paper as its initial move more often. Or if you usually play Paper twice in a row, then the glove will learn to play Scissors after your first Paper. It’s Rock Paper Scissors Championship Edition, and it seems that ironically, you’ll have a higher chance of winning if you don’t have a strategy and are totally random.

Click to View Embedded Video Clip

Tinkerers and hackers should check out Hoefer’s website for more details, as well as instructions, tips and the source code for the Arduino. Maybe you can build a glove that incorporates Lizard and Spock as well.

[via Neatorama]

As proof, the two researchers – who are both “interested in artificial intelligence and the application of computational logic” – say that they have successfully created a computer system capable of making human-like moral judgments on the trolley problem, which involves five people about to be hit by an out-of-control trolley. A bystander is near a switch that, when flipped, can change the course of the trolley. This will save the five people, but will hit the one person who is on the alternate track. Most people will of course sacrifice the one person to save the five.

Maybe I’m just being an idiot, but isn’t the trolley problem too simple to be used as proof of a morally aware computer? There are a lot of problems in the real world that are much more complex, and cannot be solved simply by applying Spock’s dying words. And it’ll still be humans who’ll program this so-called prospective logic, in which case their biases will transfer over to the programmed computer or robot. Behind every Wall E is a programmer with a sense of humor, and behind every Skynet is an evil mad scientist. If you’re so inclined, Technovelgy has a link to the pdf version of Pereira and Saptawijaya’s paper, Modelling Morality with Prospective Logic.

[via Technovelgy and AlphaGalileo via BotJunkie]

The quote continues: ‘The system might know the requirements for various tasks in its repertoire, and it may try to perform those tasks to verify functionality.”  So at the very least, these future robots could be thinking, sensing and moving about as they are being built, testing their parts. Which could include what, guns, missiles, lasers?

DARPA recently held a convention (pdf) of evil, traitorous mad scientists to help with SELF. Well I think that this is future future technology.  First of all you’d either need to have versatile parts or a factory with all the parts that robots need for it to be able to build itself based on its programmed tasks. And second, I’m scared. Dammit why can’t DARPA setup programs that make us feel better?

[via The Register via Crave]

Arkin argues that “not only can robots be programmed to behave more ethically on the battlefield, they may actually be able to respond better than human soldiers.” Now I know that if we do end up having autonomous armed robots, their decision-making must be equally good, if not better, than ours. Surely coming up with such a software is no mean feat, but I’m more worried about the possibility of evildoers coming up with an evil program, which is much easier to write (i.e. a program that instructs robots to kill everything they see).

[via Discovery via BotJunkie]

Created by builder Che Edoga (aka “darkback2″), his wood and metal robot “Gepetto” can fire paintballs while it tools around via remote control.

Click to View Embedded Video Clip

While Gepetto was designed first and foremost as an artificially-intelligent mobile robotic platform, the paintball add-on turns it into a work of pure evil genius.

Click to View Embedded Video Clip

In addition to being able to carry a load, Gepetto has a built in video camera and screen for interacting with passersby (or maybe to remotely taunt its victims when in paintball mode).

Gepetto is actually strong enough to carry around a laptop on its back, and can manage driving on challenging surfaces thanks to independent wheel mechanisms that can travel as much as three inches in height. While the robot is strong enough to navigate on carpet or other uneven surfaces, it’s probably not going to climb hills any time soon.

Darkback2 plans on continuing to refine the ‘bot’s navigation, intelligence, vision and other systems in the coming months. Check out the details of his progress over on the Trossen Robotics forums. (by the way, Gepetto was a runner up in Trossen’s latest robot contest).

In the mean time, if I see Gepetto coming down the road, I’m heading the other way.