Experience-based learning of task representations from human-robot interaction

We present an approach that allows a robot to learn task representations from its own experiences of interacting with a human. The robot follows a human teacher and maps its own observations of the environment into a representation of what has constituted the human's demonstration. The robot then builds a representation of the experienced task in the form of a behavior network. To enable this we introduce an architecture that extends the capabilities of behavior-based systems by allowing the representation and execution of complex and flexible sequences of behaviors. We demonstrate this architecture in a set of experiments in which a mobile robot learns representations for multiple tasks and is able to execute the tasks, even in changing environments.