Evolving Optimal Obstacle Avoidance

Posted 28 Oct 2005 at 20:41 UTC by steve Share This

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.

See more of the latest robot news!

Recent blogs

30 Sep 2017 evilrobots (Observer)
10 Jun 2017 wedesoft (Master)
9 Jun 2017 mwaibel (Master)
25 May 2017 AI4U (Observer)
25 Feb 2017 steve (Master)
16 Aug 2016 Flanneltron (Journeyer)
27 Jun 2016 Petar.Kormushev (Master)
2 May 2016 motters (Master)
10 Sep 2015 svo (Master)
14 Nov 2014 Sergey Popov (Apprentice)
Share this page