Learning what is relevant to the effects of actions for a mobile robot

Abstract

We have developed a learning mechanism that allows robots to discover the conditional effects of their actions. Based on sensorimotor experience, this mechanism permits a robot to explore its environment and observe effects of its actions. These observations are used to learn a context operator difference table, a structure that relates circumstances (context) and actions (operators) to effects on the environment. From the context operator difference table, one can extract a relatively small set of state variables, which simplifies the problem of learning policies for complex activities. We demonstrate results with the Pioneer 1 mobile robot.