Bee-havior in a mobile robot: the construction of a self-organized cognitive map and its use in robot navigation within a complex, natural environment

Abstract

A mobile robotic control system is modeled on the spatial memory and navigatory behaviors attributed to foraging honey bees in an effort to exploit some of the robustness and efficiency of these insects. The authors' robot uses a self-organizing feature-mapping neural network to construct a topographically ordered map from ultrasound range images collected while exploring the environment. This map is then annotated with metric positional information from a dead reckoning system. The resulting cognitive map can be used by the robot to localize in the world and to plan safe and efficient routes through the environment. This system was thoroughly tested in simulation and is currently being implemented on the robot.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>