Designing Robot Companions: Exploring the Impact of Robot Personality on Perceived Empathy, Trust, Sociability, and Enjoyability

How should a companion robot behave? In this research, we present a cognitive architecture based on a tailored personality model to investigate the impact of robotic personalities on the perception of companion robots. Drawing on existing literature, we identified empathy, trust, enjoyability, and sociability as key factors in building companionship with social robots. We have enhanced an existing cognitive architecture by integrating an LLM-based, personality-dependent emotion generator, acknowledging the crucial role of robot emotions in human-robot interaction. We then conducted a user study involving 84 dyadic conversation sessions with the emotional robot Navel, which exhibited different personalities. Results were derived from a multimodal analysis, including questionnaires, open-ended responses, and behavioral observations. The results allow us to explore the relationship between the personality traits of Agreeableness, Extroversion, Conscientiousness, and perceived empathy. Furthermore, we provide initial evidence about how these traits influence relational trust, capability trust, enjoyability, and sociability. The conclusions drawn from the user study can be considered a starting point for understanding how to design robotic personality in order to support the design of socially engaging robots.