Artificial evolution algorithms have proven to be a powerful tool in a number of fields, finding optimal solutions much like thier natural counterpart in the real world does. A newly released paper (PDF format) presented at last year's International Symposium on Computational Intelligence and Industrial Applications (ISCIIA) conference details the application of evolutionary optimization to obstacle avoidance. Normally evolution-based algorithms have been considered to slow to adapt to computer vision. The authors demonstrate a technique called The Fly Algorithm to solve computer vision problems using small grain decomposition of a scene following principals of Darwinian evolution. Using their algorithm, a 2GHz Pentium with stereo CCD cameras was able to analyze outdoor scenes quickly enough to be used for obstacle avoidance on an autonomous robot.