A lifelong learning perspective for mobile robot control

Abstract

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 the author presents 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. The author illustrates a particular leaning 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.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>