Author Topic: Experimental AI Powers Robot Army!  (Read 2445 times)

Scotty

  • Black Monk
  • ***
  • Posts: 129
  • Karma: +6/-4
Experimental AI Powers Robot Army!
« on: September 14, 2006, 12:46:24 PM »
Wired News | September 14, 2006
By David Hambling

Darpa's Grand Challenge may have looked tough, but it was a piece of cake compared to the challenge facing robots currently being developed by the U.S. Air Force.

Rather than maneuver driverless through miles of rough desert terrain, these will have to find their way into underground bunkers, map unknown facilities in three dimensions and identify what's in them while avoiding detection -- all without any human control.

This is well beyond the capability of any existing system, but the Air Force Research Laboratory, or AFRL, is putting its hopes on new software that lets robots learn, walk, see and interact far more intelligently than ever before.

It's based on work by Stephen Thaler, who came to prominence 10 years ago with his brainchild the Creativity Machine. This is software for generating new ideas on the basis of existing ones, and it has already written music, designed soft drinks, and discovered novel minerals that may rival diamonds in hardness.

The software is a type of neural network with two special features. One introduces perturbations, or "noise," into the network so that existing ideas get jumbled into new forms. The second is a filter that assesses the new ideas against existing knowledge and discards those that are unsuitable. Current applications range from detecting intruders in computer networks to developing new types of concrete and optimizing missile warheads.

Recently, Thaler has been working for the AFRL on what he calls Creative Robots, which joins his brand of AI to robotic hardware.

“Dr. Thaler's approach is clever and should have some interesting properties,” said Michael Rilee, a NASA researcher who is working on a neural networking project to use bot swarms in space and planetary exploration, known as Autonomous Nano-Technology Swarm, or ANTS. “The chief novelty is in its use of neural nets to train other neural nets.”

Self-learning and adaptability will be the key to success, and this is where the Creativity Machine excels. Give it any set of robotic limbs and it will master locomotion within minutes without any programming, swiftly finding the most efficient way of moving toward a goal. It will spontaneously develop new gaits for new challenges. (Thaler recounts how a virtual robotic cockroach adopted a two-legged gait and ran on its hind legs, not unlike basilisk lizards, when it needed to move faster.)

Perhaps the most impressive -- and spookiest -- aspect of the project is the swarming behavior of the robots. In computer simulations, they acted together to tackle obstacles and grouped together into defensive formations where needed, Thaler said. They also worked out how to deal with defenders, and spontaneously devised the most efficient strategy for mapping their environment, he added.

"This approach has less chance of getting stuck than any other" when dealing with unpredictable obstacles, according to Lloyd Reshard, a senior electronics engineer at AFRL.

Thaler declined to describe his results in detail, but said his system has produced unspecified "humanlike capabilities."

"I can relate the results of virtual-reality simulations, where swarms of Creativity Machine-based robots have deliberatively sacrificed one of their kind to distract a human guard, enabling the remainder to infiltrate a mock facility," he said.

Owen Holland, a researcher at the University of Essex who is building an “ultraswarm” of miniature Bluetooth-connected helicopters, said neural networks can be very effective for dealing with changing circumstances: "If you rip a leg off, they'll work out what's happened, and re-evolve a different gait that works."

Still, he admitted the swarm approach has its limits. "The fundamental problem with the swarm intelligence approach is that we cannot usually go from a knowledge of what we want the system to do to a knowledge of the simple rules that will automatically produce the desired result when loaded onto the robots,” he said. “I can't see us ever being able to do more than repeat the process using artificial evolution or some other open-ended search technique."

Thaler’s current project, which should be completed over the next six months, will develop a piece of software called CSMARRT (for Creative, Self-Learning, Multi-Sensory, Adaptive, Reconfigurable, Robotics Toolbox). The software can be used to design and model virtual robots that can be placed in virtual environments to learn and develop. The user can then view the result to see how neural network modules have “knitted” themselves into complex control architectures.

This toolbox can create software to control any robotic hardware, handling locomotion, sensors and intelligent behavior to carry out a mission including swarming. The AFRL will make this available to its customers -- other branches of the U.S. military.

“The biggest challenge is computing power,” Reshard said.

Desktops PCs are more than powerful enough to run CSMARRT, but the aim is to get something that will run on as little computing power and fit into as small a package as possible. Exactly how small is anyone's guess, but AFRL left the impression of a scale of inches rather than feet.

The Air Force robots may look like cockroaches, or they may be "snakebots" like those currently in development. Thaler has carried out validation tests by using the software to control small H3 "robot cockroaches." The results are classified, he said.
Like in the days of Noah....It shall come to pass, on a Fiery-day...

prezhorusin04

  • Monstropedian
  • Realized Monster
  • *******
  • Posts: 607
  • Karma: +6/-1
  • Deep in a Cave
    • http://www.nwowatcher.com
Re: Experimental AI Powers Robot Army!
« Reply #1 on: January 11, 2007, 12:40:49 AM »
Interesting article...... :-)

Robots could demand legal rights
21 December 2006, 13:54 GMT
http://news.bbc.co.uk/2/hi/technology/6200005.stm

In Pictures: Robot menagerie
http://news.bbc.co.uk/1/shared/spl/hi/picture_gallery/06/technology_robot_menagerie/html/1.stm
 
Robots could one day demand the same citizen's rights as humans, according to a study by the British government.

If granted, countries would be obliged to provide social benefits including housing and even "robo-healthcare", the report says.

The predictions are contained in nearly 250 papers that look ahead at developments over the next 50 years.

Other papers, or "scans", examine the future of space flight and methods to dramatically lengthen life spans.

"We're not in the business of predicting the future, but we do need to explore the broadest range of different possibilities to help ensure government is prepared in the long-term and considers issues across the spectrum in its planning," said Sir David King, the government's chief scientific adviser.

"The scans are aimed at stimulating debate and critical discussion to enhance government's short and long term policy and strategy."

Robot rights

The research was commissioned by the UK Office of Science and Innovation's Horizon Scanning Centre.

The 246 summary papers, called the Sigma and Delta scans, were complied by futures researchers, Outsights-Ipsos Mori partnership and the US-based Institute for the Future (IFTF).
 
The reports also explored the future of manned space flight

The papers look forward at emerging trends in science, health and technology.

The scans explore a diverse range of areas from the future of the gulf stream and the economic rise of India, to developments in nanotechnology and the threat posed by HIV/Aids.

As well as assessing the current state of thinking the research also examines the possible implications for society.

The paper which addresses Robo-rights, titled Utopian dream or rise of the machines? examines the developments in artificial intelligence and how this may impact on law and politics.

The paper says a "monumental shift" could occur if robots develop to the point where they can reproduce, improve themselves or develop artificial intelligence.

The research suggests that at some point in the next 20 to 50 years robots could be granted rights.

If this happened, the report says, the robots would have certain responsibilities such as voting, the obligation to pay taxes, and perhaps serving compulsory military service.

Conversely, society would also have a duty of care to their new digital citizens, the report says.

It also warns that the rise of robots could put a strain on resources and the environment.

"These scans are tools for government to identify risks and opportunities in the future," said Sir David.