Explicit Models for Robot Road Following

Abstract

Robots need strong explicit models of their environment in order to reliably perceive and navigate. An explicit model is information directly available to the program itself, used for reasoning about what to look for, how to look for it, and how to interpret what it has seen. We discuss the need for explicit models in the context of road following, showing how road followers built by our own and other groups have suffered by not having explicit models. Our new road tracking system, FERMI, is being built to study explicit models and their use. FERMI includes explicit geometric models and multiple trackers, and will use explicit models to select features to track and methods to track them.1