Intention prediction and human-robot interaction, Eye
tracking and EEG sensing, Computational topology for
modelling spatiotemporal phenomena
My work addresses the problem of predicting the
activity of people by combining models obtained from,
e.g., eye tracking (or even wearable EEG sensors),
with robotic perception. This allows us to obtain
contextual information which is key for human-robot
co-work applications. A particularly unique aspect of
my work is the use of novel computational methods,
e.g., based on topology, that allows us to abstract
over the spatiotemporal processes associated with
S. Penkov, A. Bordallo, S. Ramamoorthy, Physical symbol grounding and instance learning through demonstration and eye tracking, IEEE International Conference on Robotics and Automation, 2017.
Preprint, Video, Bibtex
S. Penkov, A. Bordallo, S. Ramamoorthy, Inverse eye tracking for intention inference and symbol grounding in human-robot collaboration, Robotics: Science and Systems Workshop on Planning for Human-Robot Interaction, 2016.
Preprint, Publisher's link, Bibtex