Introduction

Navigation tasks, and particularly robot navigation, are tasks that are closely associated with data collection. Even a tourist on holiday devotes extensive effort to reportage: the collection of images, narratives or recollections that provide a synopsis of the journey. Several years ago, the term vacation snapshot problem was coined to refer to the challenge of generating a sampling and navigation strategy (Bourque and Dudek, 2000). The notion of a navigation summary refers to a class of solutions to this problem that capture the diversity of sensor readings, and in particular images, experienced during an excursion without allowing for active alteration to the path being followed.

An ideal navigation summary consists of a small set of images which are characteristic of the visual appearance of a robot's trajectory and capture the essence of what was observed. These images represent not only the mean appearance of the trajectory but also its surprises.

In the context of this chapter, we define a navigation summary to be a set of images (Figure 11.1) which minimizes surprise in the observation of the world. In Section 11.3, we present an information-theory-based formulation of surprise, suitable for the purpose of generating summaries. The decisions of selecting summary images can be made either offline or online. In this chapter we will discuss both versions of the problem, and present experimental results which highlight differences between the corresponding methods.

In Section 11.4, we present two different offline strategies (Figure 11.2) for picking the summary images.