Towards Learning and Evolving of a Team of Sony Legged Robots

Abstract

This paper presents a hybrid approach to learning and evolving of a team of Sony legged robots (AIBO) in the robot football domain. These advanced walking robots aim to participate in the Sony Legged Robot League within the RoboCup competition. To achieve this goal, three important issues have been addressed in the paper:(i) multi-sensor based distributed perception, (ii) behaviour based approach to individual basic skills such as passing, shooting and ball control, (iii) system evolving and learning from experience. Some preliminary experimental results are presented to show the progress of our project.

Author-supplied keywords

Cite this document ^(BETA)