“That Robot Stared Back at Me!”: Demonstrating Perceptual Ability Is Key to Successful Human–Robot Interactions

Abstract

Communication robots, such as robotic salespeople and guide robots, are increasingly becoming involved in various aspects of people's everyday lives. However, it is still unclear what types of robot behavior are most effective for such purposes. In this research, we focused on a robotic salesperson. We believe that people often ignore what such robots have to say owing to their weak social presence. Thus, these robots must behave in ways that attract attention encouraging people to nod or reply when the robots speak. In order to identify suitable behaviors, we conducted two experiments. First, we conducted a field experiment in a shop in a traditional Kyoto shopping street to observe customers' real-world interactions with a robotic salesperson. Here, we found that the first impression given by the robot had a crucial influence on its subsequent conversations with most customer groups and that it was important for the robot to indicate it could understand how much attention customers were paying to the robot in the early stages of its interactions if it was to persuade customers to respond to what it said. Although the field experiment enabled us to observe natural interactions, it also included many external factors. In order to validate some of our findings without the involving these factors, we further conducted a laboratory experiment to investigate whether having the robot look back at the participants when they looked at it increased their perception that the robot was aware of their actions. These results supported the findings of the field experiment. Thus, we can conclude that demonstrating that a robot can recognize and respond to human behavior is important if it is to engage with people and persuade them to nod and reply to its comments.

Tell me more! Assessing interactions with social robots from speech

“…A variety of different physical cues to embodiment serve to signal reciprocation during a conversation, including touch and dynamic gaze, and previous work documents how these cues hold potential to elicit rich disclosures (e.g. [69,[108][109][110]). Hence, a valuable avenue for further investigation will be to examine how disclosure reciprocity can be achieved with variety of embodiment cues, and which of these cues is responsible for a meaningful elicitation.…”

State-Transition Modeling of Human–Robot Interaction for Easy Crowdsourced Robot Control

“…Moreover, personalizing human–robot interaction contents can enhance the social interactions [ 8 ]. In other research, it was demonstrated that when a robotic salesperson attempted to start a conversation with customers in a real store, the robot could succeed in interactive conversation by making a short speech that was easy to respond to [ 9 ], and the robot’s presence was strengthened by indicating that it understood the state of the customer [ 10 ]. In the present study, we examined which series of actions are useful when a robot provides services to customers.…”

“…Allowing a robot to read social cues is one of the indispensable means for communicating with humans. There is also a study demonstrating that a robot’s ability to recognize and respond to human behavior is important for the robot to successfully engage with people and persuade them to nod and reply to its comments [ 10 ]. Based on this finding, we developed an attention estimation model (AEM) based on data of customers’ nonverbal cues in the field experiment, and examined whether the model was effective in a real-world environment.…”

“…The customers may have then felt a sense of guilt if they ignored the robot. Consequently, they may have been more willing to respond to the robot [ 10 ]. Thus, an automatic greeting based on the AEM was effective in a real-world environment and was able to strengthen the robot’s social presence.…”

Behavioral Cues of Humanness in Complex Environments: How People Engage With Human and Artificially Intelligent Agents in a Multiplayer Videogame

“…The extent to which non-human agents can trigger the perception of mind is still an active topic of study in Human-Robot Interactions (HRI; Wiese et al, 2017 ; Iwasaki et al, 2019 ; Schellen and Wykowska, 2019 ), and important consideration in Human-AI Interactions (HAI). Some studies have demonstrated that only agents with very humanlike physical appearance can elicit humanlike social interactions (MacDorman and Ishiguro, 2006 ) or expectations of social experience (Martini et al, 2016 ).…”