Designing robots that learn by themselves to perform complex real-world tasks is a still-open challenge for the field of Robotics and Artificial Intelligence. In this paper we present the robot learning problem as a lifelong problem, in which a robot faces a collection of tasks over its entire lifetime. Such a scenario provides the opportunity to gather general-purpose knowledge that transfers across tasks. We illustrate a particular learning mechanism, explanation-based neural network learning, that transfers knowledge between related tasks via neural network action models. The learning approach is illustrated using a mobile robot, equipped with visual, ultrasonic and laser sensors. In less than 10 minutes operation time, the robot is able to learn to navigate to a marked target object in a natural office environment.
@INCOLLECTION{Thrun95k,
AUTHOR = {S. Thrun},
YEAR = {1995},
TITLE = {A Lifelong Learning Perspective for Mobile Robot Control},
BOOKTITLE = {Intelligent Robots and Systems},
EDITOR = {V. Graefe},
PUBLISHER = {Elsevier}
}