Genetic programming for real world robot vision

Abstract

The vision subsystem of an autonomous mobile robot was created using a form of evolutionary computation known as genetic programming. In this form, individuals are algorithms represented as parse trees. The primitives of the representation were specifically chosen to capture the spirit of existing vision algorithms. Thus, the evolutionary computation can be viewed as searching roughly the same space that researchers search when developing their system using trial and error. Traditional image operators such as the Sobel magnitude and a median filter were combined in arbitrary ways, and images from an unmodified office environment were used as training data. A hand written obstacle avoidance algorithm used the output of the best vision algorithm to avoid obstacles in real time. It performed as well as the existing hand written combined navigation and vision systems.