A topological map based navigation system for mobile robotics

Abstract

We discuss two forms of cognitive map which are commonly used in mobile robotics when navigation requirements and environmental conditions make them appropriate; namely global metric, and topological. Whilst the former is a more powerful representational form which is suitable for building route plans in static environments, the latter is typically much less computationally intense and may be embedded directly into a behavior-based platform which can cope with local dynamics efficiently. We then focus on a method for extracting a topological map from a metric one, ie. a transformation from spatial non-procedural to symbolic procedural knowledge. Results from simulation experiments are presented.