Anticipation through Head Pose Estimation: a preliminary study
This work addresses the challenge of enabling natural human-robot interaction through non-verbal communication, but it is a preliminary and incremental study.
The study tackled the problem of anticipating human action goals, such as reaching and transporting movements, using head pose as a visual cue, and found that short-range anticipation is possible by analyzing spatio-temporal connections between the head, hands, and objects.
The ability to anticipate others' goals and intentions is at the basis of human-human social interaction. Such ability, largely based on non-verbal communication, is also a key to having natural and pleasant interactions with artificial agents, like robots. In this work, we discuss a preliminary experiment on the use of head pose as a visual cue to understand and anticipate action goals, particularly reaching and transporting movements. By reasoning on the spatio-temporal connections between the head, hands and objects in the scene, we will show that short-range anticipation is possible, laying the foundations for future applications to human-robot interaction.