In this paper I will describe Polly, a low cost vision-based robot that gives primitive tours. The system is very simple, robust and efficient, and runs on a hardware platform which could be duplicated for less than $lOK US. The system was built to explore how knowledge about the structure the environment can be used in a principled way to simplify both visual and motor processing. I will argue that very simple and efficient visual mechanisms can often be used to solve real problems in real (unmodified) environments in a principled manner. I will give an overview of the robot, discuss the properties of its environment, show how they can be used to simplify the design of the system, and discuss what lessons can drawn for the design of other systems.