The University of Sussex

General visual robot controller networks via artificial evolution

Dave Cliff, Inman Harvey, Phil Husbands

We discuss recent results from our ongoing research concerning the application of artificial evolution techniques (i.e. and extended form of genetic algorithm) to the problem of developing "neural" network controllers for visually guided robots. The robot is a small autonomous vehicle with extremely low-resolution vision, employing visual sensors which could readily be constructed from discrete analog components. In addition to visual sensing, the robot is equipped with a small number of mechanical tactile sensors. Activity from the sensors is fed to a recurrent dynamical artificial "neural" network, which acts as the robot controller, providing signals to motors governing the robot's motion.


Download compressed postscript file