A robotic agent operating in an unknown and complex environment may employ a search strategy of some kind to perform a navigational task such as reaching a given goal. In the process of performing the task, the agent can attempt to discover characteristics of its environment that enable it to choose a more efficient search strategy for that environment. If the agent is able to do this, we can say that it has "learned to navigate" — i.e., to improve its navigational performance. This paper describes how an agent can learn to improve its goal-finding performance in a class of discrete spaces, represented by graphs embedded in the plane. We compare several basic search strategies on two different classes of "random" graphs and show how information collected during the traversal of a graph can be used to classify the graph, thus allowing the agent to choose the search strategy best suited for that graph.

The authors consider the multiple applications of vision in the solution of dynamic robot and positioning problems such as catching, hitting, and intercepting a moving object. They propose a framework for qualitative reasoning about such problems, and then present a robust vision-based control strategy that uses a Kalman filter to track image features. In the formulation, a given positioning problem is transformed into one of constrained trajectory planning on a topological surface defined by the relationship between positions of the robot and observable image features. By considering only the qualitative properties of this surface, the need for precise calibration of the various components of the system is eliminated.>