Automatic selection of task spaces for imitation learning

Authors:
Manuel Mühlig;Michael Gienger;Jochen J. Steil;Christian Goerick
Affiliations:
Research Institute for Cognition and Robotics, Bielefeld University, Bielefeld, Germany and Honda Research Institute Europe, Offenbach, Main, Germany;Honda Research Institute Europe, Offenbach, Main, Germany;Research Institute for Cognition and Robotics, Bielefeld University, Bielefeld, Germany;Honda Research Institute Europe, Offenbach, Main, Germany
Venue:
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Year:
2009

Citing 4
Cited 3

A Model of Saliency-Based Visual Attention for Rapid Scene Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
2006 Special issue: Mirror neurons and imitation: A computationally guided review

Neural Networks - 2006 Special issue: The brain mechanisms of imitation learning
Optimization-based trajectory planning of the human upper body

Robotica
Task-level imitation learning using variance-based movement optimization

ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation

Interactive imitation learning of object movement skills

Autonomous Robots
Designing robot learners that ask good questions

HRI '12 Proceedings of the seventh annual ACM/IEEE international conference on Human-Robot Interaction
Fast motion planning from experience: trajectory prediction for speeding up movement generation

Autonomous Robots

Quantified Score

Hi-index	0.00

Visualization

Abstract

Previous work [1] shows that the movement representation in task spaces offers many advantages for learning object-related and goal-directed movement tasks through imitation. It allows to reduce the dimensionality o f the data that is learned and simplifies the correspondence problem that results from different kinematic structures of teacher and robot. Further, the task space representation provides a first generalization, for example wrt. differing absolute positions, if bi-manual movements are represented in relation to each other. Although task spaces are widely used, even if they are not mentioned explicitly, they are mostly defined a priori. This work is a step towards an automatic selection of task spaces. Observed movements are mapped into a pool of possibly even conflicting task spaces and we present methods that analyze this task space pool in order to acquire task space descriptors that match the observation best. As statistical measures cannot explain importance for all kinds of movements, the presented selection scheme incorporates additional criteria such as an attention-based measure. Further, we introduce methods that make a significant step from purely statistically-driven task space selection towards model-based movement analysis using a simulation of a complex human model. Effort and discomfort of the human teacher is being analyzed and used as a hint for important task elements. All methods are validated with realworld data, gathered using color tracking with a stereo vision system and a VICON motion capturing system.