Mental health issues are receiving more and more attention in society. In this paper, we introduce a preliminary study on human–robot mental comforting conversation, to make an android robot (ERICA) present an understanding of the user’s situation by sharing similar emotional experiences to enhance the perception of empathy. Specifically, we create the emotional speech for ERICA by using CycleGAN-based emotional voice conversion model, in which the pitch and spectrogram of the speech are converted according to the user’s mental state. Then, we design dialogue scenarios for the user to talk about his/her predicament with ERICA. In the dialogue, ERICA shares other people’s similar predicaments and adopts a low-spirit voice to express empathy to the interlocutor’s situation. At the end of the dialogue, ERICA tries to encourage with a positive voice. Subsequently, questionnaire-based evaluation experiments were conducted with the recorded conversation. In the questionnaire, we use the Big Five scale to evaluate ERICA’s personality. In addition, the perception of emotion, empathy, and encouragement in the dialogue are evaluated. The results show that the proposed emotional expression strategy helps the android robot better present low-spirit emotion, empathy, the personality of extroversion, while making the user better feel the encouragement.

The emotion expressions of social robots are some of the most important developments in recent studies on human–robot interactions (HRIs). Several research studies have been conducted to assess effective factors to improve the quality of emotion expression of the robots. In this study, we examined the effects of a robot’s vertical oscillation and transition on the quality of its emotion expression, where the former indicates the periodic up/down movement of the body of the robot, while the latter indicates a one-time up or down movement. Short-term and long-term emotion expressions of the robot were studied independently for the four basic emotions described in the circumplex model of emotions: joy, anger, sadness, and relief. We designed an experiment with an adequate statistical power and minimum sample size of human subjects based on a priori power analysis. Human subjects were asked to evaluate the robot’s emotion expressions by watching its video with/without vertical movement. The results of the experiment showed that for the long-term emotions, the speed of vertical oscillation corresponded to the degree of arousal of the emotion expression as noted in the circumplex model; this indicated that fast oscillations improved the emotion expression with a higher degree of arousal, such as joy and anger, while slow or no oscillations were more suited to emotions with a lower degree of arousal, such as sadness and relief. For the short-term emotions, the direction of the vertical transition corresponded to the degree of valence for most of the expressed emotions, while the speed of vertical oscillation reflected the degree of arousal. The findings of this study can be adopted in the development of conversational robots to enhance their emotion expression.

A question in research is concerning the most important factors for increasing the motivation of a human to continue interacting with an interactional robot. Previous studies have argued that the perceptions of mind and interactability of the robot by the interacting human are essential factors. However, ways of improving such perceptions have not sufficiently investigated. In this study, we focused on the case of a home-use interactional robot and investigated ways to improve such perceptions. We proposed the perceived interaction history of the robot to be another essential factor and hypothesized that adding this factor can promote the perceptions of mind and positive relationship. We conducted a human–robot interaction experiment with 32 human subjects, and the experimental results verified our hypothesis.

For a conversational robot, conveying its intention explicitly to the communicating human is one of the most important but challenging tasks in the field of human–robot interaction (HRI). Expressing the robot’s current mental state or feeling while conversing may help achieve a more effective communication. In this study, a robot equipped with a projecting system is implemented, in which the mental state of the robot is projected onto the backside wall to better convey its intention. To verify the effectiveness of the implemented system, as a first step, the effect of projecting only the text of the robot’s speech on the subjective evaluation of the communicating human was examined from different aspects of the robot. To this end, two experiments were conducted: a video watching experiment, in which several human subjects watched a video of a speaking robot equipped with the projecting system, and a participating experiment, in which a limited number of human subjects participated in listening to the speech of such a robot in a real-world environment. The experimental results revealed that the projection of the speech information can improve some elements of the human perception of the robot’s speech and mind. GRAPHICAL ABSTRACT

Joint attention related behaviors (JARBs) are some of the most important and basic cognitive functions for establishing successful communication in human interaction. It is learned gradually during the infant's developmental process, and enables the infant to purposefully improve his/her interaction with the others. To adopt such a developmental process for building an adaptive and social robot, previous studies proposed several contingency evaluation methods, by which an infant robot becomes able to sequentially learn some primary social skills. These skills included gaze following and social referencing, and could be acquired through interacting with a human caregiver model in a computer simulation. However, to implement such methods to a real-world robot, two major problems, that were not addressed in the previous research, have remained unresearched: (1) dependency of histogram of the observed events by the robot to each other, which increases the error of the internal calculation and consequently decreases the accuracy of contingency evaluation; and (2) unsynchronized teaching/learning phase of the teaching-caregiver and the learning-robot, which leads the robot and the caregiver not to understand the suitable timing for the learning and the teaching, respectively. In this paper, we address these two problems, and propose two algorithms in order to solve them: (1) exclusive evaluation of policies (XEP) for the former, and (2) ostensive-cue sensitive learning (OsL) for the latter. To show the effect of the proposed algorithms, we conducted a real-world human-robot interaction experiment with 48 subjects, and compared the performance of the learning robot with/without proposed algorithms. Our results show that adopting proposed algorithms improves the robot's performance in terms of learning efficiency, complexity of the learned behaviors, predictability of the robot, and even the result of the subjective evaluation of the participants about the intelligence of the robot as well as the quality of the interaction.

This study examined whether social robots influence 4-5-year-olds' persistence. Almost all participants (97%) were Japanese. Most participants lived in urban or suburban areas in Osaka and came from middle socioeconomic backgrounds. The data were collected in 2023-2025. In Experiment 1 (N = 108, 45 girls), a robot's verbal time updates enhanced persistence, but robot interactions did not. In Experiment 2 (N = 27, 12 girls), providing time updates from a personal computer (PC) did not increase persistence. In Experiment 3 (N = 54, 24 girls), children worked with a robot (from Experiment 1), a human, or alone. Verbal time updates from both agents increased persistence compared to working alone although children behaved differently, for example, making qualitatively different comments to each agent. Findings indicate that robots and humans can foster children's persistence, though their roles may differ, reflecting robots' growing presence in children's lives.