Identifying nonverbal cues for automated human-robot turn-taking

• Published in: 2012 IEEE RO-MAN: The 21st IEEE International Symposium on Robot and Human Interactive Communication pp. 418 - 423
• Main Authors: Calisgan, E., Haddadi, A., Van der Loos, H. F. M., Alcazar, J. A., Croft, E. A.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.09.2012
• Subjects: Collaboration; Context; Games; Humans; Joints; Service robots
• ISBN: 9781467346047; 1467346047
• ISSN: 1944-9445; 1944-9437
• DOI: 10.1109/ROMAN.2012.6343788

Nonverbal communication cues play an important role in human-human interaction and are expected to take a similar role in human-robot collaboration. In current industrial practice, human-robot turn-taking is explicitly human controlled, via a command channel such as switch or button. However, such a master-slave approach does not permit collaborative interaction, and requires the human to focus on both controlling the robot's behavior and on the task, thereby affecting overall performance. In this paper, implicit, nonverbal communication cues are examined as a non-explicit communication channel during a turn-taking task context. The aim of this study is to characterize the types and frequencies of nonverbal cues important to regulating turn taking during an assembly-task-type collaboration. This analysis will guide the selection of cues that can be expressed by the robot as implicit user inputs while human and robot complete a shared task.