Department for Automation, Biocybernetics and Robotics





Goal-directed action synthesis using a library of example movements

Project duration: 2009 - 2012
Project area: Laboratory of Humanoid and Cognitive Robotics
Project type: Research
Project funding: Research Agency
Project leader: Aleš Ude

Abstract

The aim of the project is to develop a new methodology that will enable home robots to learn new goal-directed actions in a natural way and without requiring experts to help during learning. Thus no physical models of the task will be assumed to be available because only experts can provide such models.