Action understanding and imitation learning in a robot-human task

We report results of an interdisciplinary project which aims at endowing a real robot system with the capacity for learning by goaldirected imitation. The control architecture is biologically inspired as it reflects recent experimental findings in action observation/execution studies. We test its fu...

Full description

Bibliographic Details
Main Author: Erlhagen, Wolfram (author)
Other Authors: Mukovskiy, Albert (author), Bicho, E. (author), Panin, Giorgio (author), Kiss, Casba (author), Knoll, Alois (author), Van Schie, Hein (author), Bekkering, Harold (author)
Format: conferencePaper
Language:eng
Published: 2005
Subjects:
Imitation learning
Robotics
Dynamic field model
Action understanding
Science & Technology
Online Access:http://hdl.handle.net/1822/4458
Country:Portugal
Oai:oai:repositorium.sdum.uminho.pt:1822/4458
Description
Summary:We report results of an interdisciplinary project which aims at endowing a real robot system with the capacity for learning by goaldirected imitation. The control architecture is biologically inspired as it reflects recent experimental findings in action observation/execution studies. We test its functionality in variations of an imitation paradigm in which the artefact has to reproduce the observed or inferred end state of a grasping-placing sequence displayed by a human model.

Similar Items