SENSORY PREDICTION LEARNING – HOW TO MODEL THE SELF AND THE ENVIRONMENT

Ryo Saegusa, Sophie Sakka, Giorgio Metta, Giulio Sandini

Abstract

For a complex autonomous robotic system such as a humanoid robot, the learning-based state prediction is considered effective to develop the body and environment model autonomously. In this paper we investigate a model of changes detection directly included in the evaluation process of the learning algorithm. The model is characterized by a function called confidence, which returns a high value if the robot’s actual state data match the predicted state data. The robot then creates the confidence map for each sensor based on the prediction error, which allows the robot to notice if the current sensory state is predictable (experienced) or not. We consider the confidence function as the first step to self diagnosis and self adaptation. The approach was experimentally validated using the humanoid robot James.

Keywords

sensory motor prediction, neural networks, learning, humanoid robot, self confidence

Download

IMEKO-TC1-TC7-2008-035.pdf

DOI

-

IMEKO TC

TC1 - Education and Training in Measurement and Instrumentation

Back to the proceedings