What is it about?
When people explain an indoor environment by introducing regions, workplaces, and objects to a mobile robot, their behaviour allows to draw conclusions about the underlying category of the item. This can be used to disambiguate certain situations, for example if a region is presented only through the door leading into it, or to generate a hypothesis of which category to use for a previously unknown item.
Featured Image
Why is it important?
The idea is based on observations of the entire interaction history that precedes the moment of presentation. We are not only looking at the gestures and movements that accompany the utterance (e.g., "this is my office"), but also at the preparation of this utterance, that might include to move the robot into a better position for observing what is presented.
Perspectives
The work consolidates ideas and results from several studies, and can thus be seen as the conclusion for a number of questions the author had previously aspired to answer.
Elin Anna Topp
Lunds Universitet
Read the Original
This page is a summary of: Interaction patterns in human augmented mapping, Advanced Robotics, January 2017, Taylor & Francis,
DOI: 10.1080/01691864.2017.1281758.
You can read the full text:
Contributors
The following have contributed to this page
