Studying Gaze-based Human Robot Interaction: An Experimental Platform
Stefan Kohlbecher, Eva Wiese, Klaus Bartl, J. Blume, Alexander Bannat, Erich Schneider
- Year
- 2012
- Citations
- 5
- Access
- Open access
Abstract
In this paper, a platform for studying human-robot interaction is presented.Apart from presenting a robotic eye module, which exceeds human performance in terms of velocity and acceleration, we introduce a novel method of controlling a robot's head and eye movements.In a Wizard-of-Oz scenario, a human operator (the wizard) perceives the world from the perspective of a robot through a video link.His eye and head movements are recorded and, in turn, fed back to the robot.This allows for very natural eye and head movements when the wizard virtually interacts through the robot with one or more participants.Additionally the robot can carry out scripted movements to conduct repeatable experiments in a controlled manner.It is also possible to record the gaze behaviors of the participant(s).
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002