Nonverbal Cues in Human–Robot Interaction: A Communication Studies Perspective

Abstract

Communication between people is characterized by a broad range of nonverbal cues. Transferring these cues into the design of robots and other artificial agents that interact with people may foster more natural, inviting, and accessible experiences. In this position paper, we offer a series of definitive nonverbal codes for human-robot interaction (HRI) that address the five human sensory systems (visual, auditory, haptic, olfactory, gustatory) drawn from the field of communication studies. We discuss how these codes can be translated into design patterns for HRI using a curated sample of the communication studies and HRI literatures. As nonverbal codes are an essential mode in human communication, we argue that integrating robotic nonverbal codes in HRI will afford robots a feeling of “aliveness” or “social agency” that would otherwise be missing. We end with suggestions for research directions to stimulate work on nonverbal communication within the field of HRI and improve communication between human and robots.

Self-supervised prediction of the intention to interact with a service robot

“…Nonverbal communication cues [21], such as body motion and language, play a central role in HRI, from both users' and robots' perspective [22,23]. However, the perception of social nonverbal behaviors is a challenging task to solve in HRI [24], especially for the first phases of the interactions [8].…”

Uniss-FGD: A Novel Dataset of Human Gazes Over Images of Faces

“…By leveraging data on eye movements, including fixation locations, saccades directions, and gaze duration, it becomes feasible to instruct a social robot to observe humans in a natural and human-like manner [42], [43]. This data can be utilized to train the robot on how to gaze at a person during verbal interaction, while also responding to various expressions.…”

Implementation of Engagement Detection for Human–Robot Interaction in Complex Environments

“…Moreover, the intersection of cognitive neuroscience and robotics [ 7 ] is paving the way for future research directions. Active learning for user profiling [ 8 ], garbage image classification [ 9 ], and the importance of nonverbal cues [ 10 ] further contribute to the personalization and effectiveness of HRI. These studies collectively underscore the importance of human-centered design in the evolution of smart, adaptive, and interactive robotic systems, particularly in the context of Industry 5.0 [ 11 ], while also highlighting areas for future exploration, such as user experience evaluation [ 12 ] and gesture-based communication [ 13 ].…”