How to build a cyborg astrobiologist

Artificial intelligence system looks for signs of life in dead places

The desert Mars
Researchers have built an artificial intelligence-based wearable computer with digital eyes that could help future robots or astronauts "see' and discover signs of life in the desert-like conditions found on Mars or the Moon. 

Specifically, the researchers said they have developed and tested a what's known as an novelty-detection algorithm for robotic exploration of geological and astrobiological fields, researchers stated in a white paper on the system. The novelty-detection algorithm can detect, for example, small features such as lichens as novel aspects of the image sequence in semi-arid desert environments said University of Chicago geoscientist Patrick McGuire who developed the algorithms the system uses to recognize life forms. 

Layer 8 Extra: 12 mad science projects that could shake the world 

The novelty-detection algorithm is currently based upon a Hopfield neural network that stores average color values for each segment of an image segmented with full-color segmentation. The novelty-detection algorithm can learn familiar color features sometimes in single instances, though several instances are sometimes required. The algorithm recognized previously-observed units by their color, while requiring only a single image or a few images to learn colors as familiar, demonstrating its fast learning capability researchers stated. 

The system is fed by a field-capable digital microscope connected to a wearable computer and a hand-held phone-camera connected to a netbook computer via Bluetooth and was field-tested in desert facilities in Spain and Utah. 

While the tests showed the speed and intelligence of the system, researchers said they want to rapidly expand their work to make system see smaller, micro-sized items but also larger geological and astrobiological images via faster computers and the use of more sophisticated cameras. 

The cyborg astrobiologist project is related to other work McGuire has done.  For example, McGuire's team worked on CRISM or the Compact Reconnaissance Imaging Spectrometer for Mars that is onboard NASA's Mars Reconnaissance Orbiter. CRISM can detect infrared and other light  wavelengths to help identify different types of rock and soil. 

Layer 8 in a box

Check out these other cool stories:

NASA: 2 rocket companies win $1.65M moon lander prize

X Prize gets $5.5M of economic stimulus money for 100MPG car

High-tech camera, algorithms fuse for better sleep apnea test

FTC delays identity theft protection rules till June 2010

NASA: A crazy month of changes, challenges

NASA begins to outline future with revamped advisory council

DARPA "balloon hunt" could win you $40K cash

FBI: Ex- CEO of YouSendIt charged in denial of service of attack

Typewriter puts identity thieves in Federal prison

Ultra-endurance spy plane closer to reality

Feds whiffing on millions in electronics waste disposal

Join the Network World communities on Facebook and LinkedIn to comment on topics that are top of mind.

Copyright © 2009 IDG Communications, Inc.

SD-WAN buyers guide: Key questions to ask vendors (and yourself)