Planning and Explanations with a Learned Spatial Model

Abstract

This paper reports on a robot controller that learns and applies a cognitively-based spatial model as it travels in challenging, real-world indoor spaces. The model not only describes indoor space, but also supports robust, model-based planning. Together with the spatial model, the controller’s reasoning framework allows it to explain and defend its decisions in accessible natural language. The novel contributions of this paper are an enhanced cognitive spatial model that facilitates successful reasoning and planning, and the ability to explain navigation choices for a complex environment. Empirical evidence is provided by simulation of a commercial robot in a large, complex, realistic world.