Behavior Evaluating Indices for Robot Behavior Learning and Evolution

M. Suzuki and S. Taneshima (Japan)

Keywords

Robot learning, Behavior evaluation, Behavior complexity, Learning difficulty

Abstract

This work is concerned with the behavior evaluating in dices introduced to establish a method for quantitative eval uation of robot behaviors. The indices are defined using terminology in the Intelligent Composite Motion Control, ICMC. The ICMC aims for intelligent robots that can step by step realize highly complex behaviors from fundamental motions. By applying the indices to a robot soccer problem by legged robots we present how the index values change as the behavior evolve from fundamental motions to com plex behaviors, and study the cross relationship between them. The validity and usefulness of the indices are then discussed.

Important Links:



Go Back