The Jetson’s Rosie gets a bit closer to reality

Posted by ljmacphee on June 29, 2007 under artificial intelligence in the news, robotics | 2 Comments to Read

I’ve come to love my Roomba and Scooba. Between them and the dumber machines ( dishwasher, clothes washers and dryers ) house work is now just putting stuff away and feeding machines for the most part. A robot to scrub the bathrooms and kitchens is high on my wish list.

I haven’t seen any progress yet on my bath and kitchen scrubbing robot but MIT and Stanford labs are much closer to developing one that can load the laundry and dishwasher and put things away.

Domo uses artificial intelligence to grasp the bag of coffee and locate the shelf.
In a robotics lab at the Massachusetts Institute of Technology (MIT), the torso of a robot grabs a box and holds it out to a roboticist as he cleans up the lab. We may consider it mindless work, but Aaron Edsinger says it takes intelligence for this robot named Domo to lend a helping hand with household chores.

The Stanford team was able to recently demonstrate how STAIR could be asked to retrieve a stapler from one room and deliver it to the person in another. This not only pulls in manipulation research, but also voice recognition, navigation, and other previously separate fields of research. “For the STAIR project, it was time to revisit bringing these artificial intelligence tools back together. Taking tools from different threads of AI for a general purpose robot,” Ng says.

Household Robots

See also:
Pretty soon I’ll be housekeeping like Jane Jetson

Song of the neurons

Posted by ljmacphee on June 27, 2007 under artificial intelligence in the news | Be the First to Comment

“Song of the Neurons”, soon to be available on iTunes, contains 14 songs created by a ‘Creativity Machine’ trained by Thaler. Creativity Machines are neural nets that learn by the feedback you give to them. He sat with his machine and gave it smiles or frowns for the noise it made. Eventually the noise became music and 14 songs were created.

Thaler’s Creativity Machines know as much about music as he does — pretty much nothing. He didn’t program them. He didn’t give them examples of music to study. He simply listened to sounds the programs spontaneously generated and offered a simple critique.

Thaler holed up in his basement for eight hours one day with his musical Creativity Machine and a webcam. He turned on the Creativity Machine — an untrained artificial intelligence computer known as a neural network. The neurons in the computer brain are mathematical entities instead of brain cells. Thaler started the creative process by tweaking the mathematical connections between the neurons. That set off a cascade of calculations that were translated as sounds.

Thaler sat in front of the webcam and listened. He indicated his likes with a smile and displeasure with a frown. A critic program connected to the music-generating program learned by watching the emotions play on his face what Thaler liked and gave him more of that. It learned what he didn’t like and gave him less of that.

Computers compose personalized music

Testing the limits of AI in Games

Posted by ljmacphee on June 25, 2007 under artificial intelligence in the news, game ai | Be the First to Comment

Much of cutting edge artificial intelligence is being done in games as it has been for several decades. The newer massively multiplayer online games are showing the glaring flaws in traditional game characters. The main one being the ability to carry on intelligent conversation.

But those bright people writing software that better mimics human intelligence are running smack into an interesting new trend: online virtual worlds like Second Life, and “massively multiplayer online games” such as World of Warcraft, in which characters are inherently pretty intelligent because they’re being controlled by other humans. Players in those games design their own characters and then enter the game realm to interact with one another. Their strategies and dialogue seem authentic — because they are.

“In some ways, all of these massively multiplayer games have shone a light on the deficiencies of artificially intelligent characters in games to this point,” says Hank Howie, chief executive of Blue Fang. Howie’s company makes Zoo Tycoon, distributed by Microsoft, in which players build and operate a virtual zoo. Now the company’s focus is on using artificial intelligence to create more believable animals for future products.

Game designers test the limits of artificial intelligence - Boston Globe

CLARAty

Posted by ljmacphee on June 22, 2007 under artificial intelligence in the news, robotics | Be the First to Comment

Too Cool!

CLARAty is the Coupled Layer Architecture for Robotic Autonomy. The first release of its software, version 0.10-beta, is now available publicly at http://claraty.jpl.nasa.gov.

CLARAty is an integrated framework for reusable robotic software. It defines interfaces for common robotic functionality and integrates multiple implementations of any given functionality. Examples of such capabilities include pose estimation, navigation, locomotion and planning. In addition to supporting multiple algorithms, it provides adaptations to multiple robotic platforms. CLARAty development was primarily funded by the Mars Technology Program and it serves as the integration environment for the program’s rover technology developments.

JPL Robotics: News

CLARAty

Uncanny AI

Posted by ljmacphee on June 20, 2007 under artificial intelligence in the news, game ai | Be the First to Comment

Normally, the Uncanny Valley theory is used to critique graphical realism in games, but it also applies to AI. In this latest exclusive Gamasutra feature, designer David Hayward examines AI’s Uncanny Valley, citing games such as Valve’s Half-Life 2 and Vivendi’s supernatural shooter F.E.A.R.

More information:
Gamasutra - Uncanny AI: Artificial Intelligence in the Uncanny Valley