Robot deictics

Abstract

As robots collaborate with humans in increasingly diverse environments, they will need to effectively refer to objects of joint interest and adapt their references to various physical, environmental, and task conditions. Humans use a broad range of deictic gestures-gestures that direct attention to collocated objects, persons, or spaces-that include pointing, touching, and exhibiting to help their listeners understand their references. These gestures offer varying levels of support under different conditions, making some gestures more or less suitable for different settings. While these gestures offer a rich space for designing communicative behaviors for robots, a better understanding of how different deictic gestures affect communication under different conditions is critical for achieving effective human-robot interaction. In this paper, we seek to build such an understanding by implementing six deictic gestures on a humanlike robot and evaluating their communicative effectiveness in six diverse settings that represent physical, environmental, and task conditions under which robots are expected to employ deictic communication. Our results show that gestures which come into physical contact with the object offer the highest overall communicative accuracy and that specific settings benefit from the use of particular types of gestures. Our results highlight the rich design space for deictic gestures and inform how robots might adapt their gestures to the specific physical, environmental, and task conditions.

Speech and Gesture Emphasis Effects for Robotic and Human Communicators

“…Previous work in human robot-interaction on how coverbal gestures affect comprehension has largely focused on pointing (deictic) gestures [5][23] [28], revealing that better understanding of relative locations of referents was achieved by supplementing speech information with deictic gestures. This provides some first evidence for speech and gesture integration.…”

Efficiency of speech and iconic gesture integration for robotic and human communicators - a direct comparison

“…When presented with speech, robot-performed pointing (deictic) gestures [8][9] [10], revealed that better understanding of relative locations of referents could be achieved by supplementing speech information with such gestures. Thus providing evidence for speech and gesture integration.…”

“…First studies using coverbal pointing gestures to improve robot communication seem to suggest that, at least for pointing, such integration can occur [8][9] [10]. Other types of gestures, however, have not yet been examined.…”

Designing effective strategies for human-robot collaboration

“…Robots will require an understanding of how gesture choice can affect communication in order to communicate with their human partners. To better inform our understanding of deictic gestures, I designed and implemented six different deictic gestures from literature and evaluated them in six diverse scenarios that represent physical, environmental, and task conditions under which robots are expected to employ deictic referencing [5]. For each gesture, participants identified the accuracy with which the gesture communicated and rated the effectiveness and naturalness of the robots gestures.…”