David Pierce, Benjamin Kuipers
Using the methods demonstrated in this paper, a robot with an unknown sensorimotor system can learn sets of features and behaviors adequate to explore a continuous environment and abstract it to a finite-state automaton. The structure of this automaton can then be learned from experience, and constitutes a cognitive map of the environment. A generate-and-test method is used to define a hierarchy of features defined on the raw sense vector culminating in a set of continuously differentiable local state variu bles. Control laws based on these local state variables are defined for robustly following paths that implement repeatable state transitions. These state transitions are the basis for a finite-state automaton, a discrete abstraction of the robot’s continuous world. A variety of existing methods can learn the structure of the automaton defined by the resulting states and transitions. A simple example of the performance of our implemented system is presented.