Herself’s Artificial Intelligence

Flying fish were the inspiration for an unmanned seaplane with a 7-foot wingspan developed at the University of Michigan. The autonomous craft is believed to be the first seaplane that can initiate and perform its own takeoffs and landings on water. Funded by the Department of Defense’s Defense Advanced Research Projects Agency (DARPA), it is designed to advance the agency’s “persistent ocean surveillance” program. [ read more Flying Fish Unmanned Aircraft Takes off and Lands on the Water]

For this robot size matters. Researchers at the lab found that most sea birds were about 20 pounds with a 2 meter wingspan. That’s the sweet spot and what they used for their sea plane. The plane floats until its GPS tells it is too far from home. Then it goes airborne until GPS settings tell it to land.

More Information:
Flying Fish Unmanned Aircraft takes off and lands on water
University of Michigan Hydrodynamics Laboratory
Flying Fish ( home page )

See also:
The terminator for pirates has arrived

Fractals are a fascinating toy, one can easily spend an afternoon lost in Mandelbrot or Julia sets. Mathematicians were aware of fractals as early as the 1700s but it wasn’t until we had computers to do the calculations that we really discovered fractals.

Benoit B. Mandelbrot doing research at IBM was revisiting Gaston Julia’s work with fractals (1917) when he discovered the Mandelbrot set. Fractals are simple equations that are recursively computed. These simple equations create complex shapes.

The Mandelbrot function is z = z^2 + c. z and c are complex numbers, z is set to zero, c is the position on the x ( x, yi ) plane. You recursively compute this function to obtain the Mandelbrot fractal. Black is for the numbers that do not escape to infinity, the other colors represent how many loops it takes to escape.

Fractals have found some use in artificial intelligence. In the world of computer games, fractals create plant life, clouds, mountains and other scenery that would not be possible in such detail. Parkinson’s patients are diagnosed by their gait. In 2004 a sensor was developed that measures the patient’s gait, and analyzes the gait using fractals. 2002 fractals were put to use to help predict natural disasters and better model hurricanes. More recently fractal patterns have been found in solar wind. It is hoped this information will allow us to better predict solar storms.

Fractals have been found in Jackson Pollacks paintings and are being used to try to identify real paintings from fakes. They are also being used in image compression. A more fun way to play with fractals is to use them to predict the stock and commodity markets.

Fractals ( Mandelbrot and Julia in Java – source code )

More information:
Fractal Geometry
Fractals
Math on Display, Science News Online
Genius: Benoit Mandelbrot
3D Mandelbrot images

Papers:
The Fractal Geometry of Nature, Mandelbrot ( pdf/ps )

The scientists present five models describing how animals may receive communication signals, and discuss how signal reception affects the formation of different patterns, both moving and stationary. In doing so, the scientists’ model not only explains five known group patterns, but also reveals five previously unknown patterns. The scientists also suggest that many more exist.“These patterns were obtained through numerical simulations, and they are particularly important from a mathematical point of view,” Eftimie said. “These types of patterns were not observed with previous mathematical models. That is why this model is so important: by displaying so many patterns, some of them already observed in nature, it actually opens a door to further understanding what causes these patterns.” [ read more Animal communication plays an important role in patter formation]

Instead of building the rules for swarms using information from the guy in front, these models use different information from different sources. Some use information from animals in front and behind, some just from the front, some just from behind, some from animals beside themselves. By taking in information from differently positioned other animals different flocking behavior could be obtained.

Some of these patterns are classical, such as stationary pulses, traveling waves, ripples, or traveling trains. However, most of the patterns have not been reported previously. We call these patterns zigzag pulses, semizigzag pulses, breathers, traveling breathers, and feathers.

Paper:
Complex spatial group patterns result from different animal communication mechanisms

Good things occur.

Imagine two foot tall robots traveling at ten mph armed with machine guns that stop on a dime and are accurate from a quarter mile distance. That’s one of the future weapons heading our way. Robotex is developing military robots privately, no gov’t red tape, and doing so quickly and cheaply. At these prices we could drop one on every block in a city. There’s no mention of group intelligence or swarm behavior yet, but who could resist? You know they are thinking about it.

But bad things can happen.

The pros and cons of this are obvious. It gets our soldiers out of harm’s way. The downside is the first time it makes a bad choice and wipes out civilians things’ll get ugly. Can you feel the Terminator coming closer to reality?

More importantly is the development of military weapons privatizing. The upside is we get fantastic weapons sooner and cheaper. But will they go to the US military? What’s to prevent the new privately developed weapons from going to other governments; or more concerning other private groups?

Information is scarce, this is a private company and I’m sure the government does not want much information out there either.

More information:
Ethical implications of robots in war ( pdf )
Killer robots from Silicon Valley could replace soldiers
Military recruits thousands more warbots for new unmanned surge
Who Stole the Plans for iRobots Battle Bots?
Zombie warfare: The rise of the mil-bots

See also:
The terminator for pirates has arrived
Robots of war