Herself’s Artificial Intelligence

Survival research labs creates real life battle bots for robot wars that are performed live.  SLR’s tagline is ‘Producing the most dangerous shows on earth’.

. . . “He’s trying to create a strong message about fear,” said Dr. Ken Goldberg, an associate professor of robotics at the University of California at Berkeley. “That’s what Mark is doing, igniting fear in the audience, with flying metal.”

While the use of what has become known as “Whitman’s tower” might be offensive to the sensibilities of the locals, what has consistently gotten Pauline in trouble over his 23-year career is his penchant for creating large, potentially lethal robots under the guise of modern performance art.

His group was recently banned from Japan after unveiling the pitching machine — a device with two rotating tires and the end of a funnel, which normally throws baseballs and softballs, that now hurls two-by-fours at 150 mph.

Just hours before the Austin Fire Marshall would run Pauline and his merry group of 60 out of town for violations — such as shooting 20-foot walls of flame toward hundreds of people, setting off rockets, and creating a general disturbance, the man stood silent -– his mission accomplished. . . [ read more Igniting Fear with Flying Metal ]

More information:
SRL
SRL Blog
SRL Flickr Set
Survival Research Labs - tribe.net

Video:
SRL YouTube Video
You Tube: Mark Pauline Show

We’ve all heard of UAVs. Over in Iraq they have played a huge helping role to US troops. Lesser known is their benefits to scientists exploring ocean life, and the Antarctic. More recently they have begun to show up in the news as ways to patrol the US/Mexico border and the city of Miami.

UAVs have been used along the US Mexico border and are soon to join the Miami police. ( pending FAA approval ) One of the problems we’ve had with Predators used along the border is crashes. FAA approval will depend on whether Miami’s police can convince the FAA they won’t be dropping UAVs on grandma’s car.

A more troubling question that we will have to answer if we allow UAVs over US cities is do we want our police to have weapon laden UAVs? The ones in Miami do not have weapons now but it is just a matter of time before some one finds a good reason to blow up several blocks in a US city. And it is far more likely to be our own guys than any terrorist.

Miami police could soon be the first in the United States to use cutting-edge, spy-in-the-sky technology to beef up their fight against crime.

A small pilotless drone manufactured by Honeywell International (HON.N), capable of hovering and “staring” using electro-optic or infrared sensors, is expected to make its debut soon in the skies over the Florida Everglades.

If use of the drone wins Federal Aviation Administration approval after tests, the Miami-Dade Police Department will start flying the 14-pound (6.3 kg) drone over urban areas with an eye toward full-fledged employment in crime fighting.

“Our intentions are to use it only in tactical situations as an extra set of eyes,” said police department spokesman Juan Villalba.

“We intend to use this to benefit us in carrying out our mission,” he added, saying the wingless Honeywell aircraft, which fits into a backpack and is capable of vertical takeoff and landing, seems ideally suited for use by SWAT teams in hostage situations or dealing with “barricaded subjects.” . . . [ read more Spy in the sky drone sets sights on Miami

More information:
PaparazzI The Free Autopilot, open source auto pilot software
DIY Drones ( in case you want to build your own )
Giz Mag: UAV news

See also:
Powerline urban sentry finds a hack around battery problems

Sparse distributed memory first appeared in 1998 as a model of long term memory in humans. The main idea is that distances between concepts in our brains can be represented as distances between points in a high dimension world. Since distances between points are far apart in many dimensions, the distance between concepts is large. The large distance between concepts means I only have to come closer to it than another idea for a match to be made.

For example if I give each letter of the alphabet its own dimension then map it by position in a word then ‘aeple’ is closer to ‘apple’ than ‘ample’ and I can guess that the correct word for the mistyped word. Or a four legged creature that is tall and is spotted is closer to a giraffe than a short legged spotted leopard.

This type of storage of data means you can store far fewer examples you need to match allowing you to store more information in a much smaller memory footprint.

All input is represented in binary form in sparse distributed memory. The algorithm works by calculating the ‘Hamming distance’ between data input and existing examples in memory.

Books:
Reinforcement Learning: An Introduction (pdf download )

More information:
Sparse Distributed Memory
Kevin Kelly ‘Out of Control’ Chapter 2
Sparse Distributed Memory and Related Models Chapter 3 (pdf)

Papers:
Kanerva’s Sparse Distributed Memory An associative memory algorithm well suited to the connection machine. (pdf) ( exellent starting point )
Kanerva’s Sparse Distributed Memory, Multiple Hamming Thresholds ( pdf )