Perceptive Recommendation Robot: Enhancing Receptivity of Product Suggestions Based on Customers' Nonverbal Cues.

Service robots that coexist with humans in everyday life have become more common, and they have provided customer service in physical shops around the world in recent years. However, their potential in effective sales strategies has not been fully realized due to their low social presence. This study aims to clarify what kind of robot behavior enhances the social presence of service robots and how it affects human-robot interaction and purchasing behavior. We conducted two experiments with a sales robot, Pepper, at a retail shop in Kyoto. In Experiment 1, we showed that the robot's social presence increased and that customers looked at the robot longer when the robot understood human gaze information and was capable of shared attention. In Experiment 2, we showed that the probability of customers picking up products increased when the robot suggested products based on the humans' degree of attention from gaze and posture information. These results indicate that the robot's ability to understand and make utterances about a customer's orientation and attention effectively enhances human-robot communication and purchasing motivation.

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

Robotic salespeople are often ignored by people due to their weak social presence, and thus have difficulty facilitating sales autonomously. However, for robots that are remotely controlled by humans, there is a need for experienced and trained operators. In this paper, we suggest crowdsourcing to allow general users on the internet to operate a robot remotely and facilitate customers' purchasing activities while flexibly responding to various situations through a user interface. To implement this system, we examined how our developed remote interface can improve a robot's social presence while being controlled by a human operator, including first-time users. Therefore, we investigated the typical flow of a customer-robot interaction that was effective for sales promotion, and modeled it as a state transition with automatic functions by accessing the robot's sensor information. Furthermore, we created a user interface based on the model and examined whether it was effective in a real environment. Finally, we conducted experiments to examine whether the user interface could be operated by an amateur user and enhance the robot's social presence. The results revealed that our model was able to improve the robot's social presence and facilitate customers' purchasing activity even when the operator was a first-time user.

"That Robot Stared Back at Me!": Demonstrating Perceptual Ability Is Key to Successful Human-Robot Interactions.

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.