Natural Gaze Control for robotic heads (2007~2010)
Gaze is one of the most important nonverbal behaviors in regulating human- human interactions in close encounters. Several approaches have been proposed to design robots that can exhibit human-like natural gazing behavior. Most of the available techniques though are based on careful hard-coding of behavioral rules that are usually extracted from analysis of human-human interaction corpora or theories of gaze behavior in humans.
The major disadvantage of this approach is the difficulty in discovering these behavioral rules specially taking into account cultural and situational effects on gaze behavior.
In this project, we developed a series of gaze controllers that moved from model-based controllers to controllers that are specified up to a vector of parameters that is learned adding more autonomy to the agent. Finally we developed and evaluated an unsupervised gaze controller for a listener robot that tries to alleviate this problem of engineered gazing behavior.
The system utilizes two major learning mechanisms. First, it learns a set of recurrent gaze patterns called basic interactive acts using a motif discovery algorithm. A hierarchical controller of the activation level of these interactive acts is then learned. The system was implemented and evaluated in comparison with our previous reactive gaze controller that was previously shown to provide human-like gazing behavior using an explanation scenario and was shown to be superior in terms of naturalness, human-likeness and comfort of the human partner.
Videos
- Gaze Control using L0EICA (no learning) [youtube]
- Gaze Control using Interaction Structure Learning [youtube]
Publications
Yasser Mohammad and Toyoaki Nishida, Learning where to look: Autonomous Development of Gaze Behavior for Natural Human-Robot Interaction, International Journal of Interaction Studies, Springer (Accepted on October 21st 2013).
Yasser Mohammad and Toyoaki Nishida, Controlling Gaze with an Embodied Interactive Control Architecture, Applied Intelligence, Vol. 32, No. 2, 2010, pp 148-163 [original article | local copy]
Yasser Mohammad and Toyoaki Nishida, Reactive Gaze Control for a Humanoid Robot, In Proceedings of IEEE International Conference on Robotics and Mechatronics (RAM 2008), September 2008, China, pp 47:54. [original article | local copy]
Yasser Mohammad, Mutual Intention in Human-Robot Teams (Abstract), In Proceedings of First Egyptian Japanese International Symposium on Science and Technology (EJISST 2008), June 2008, Japan, pp 122-122.