PACE: Persona Adaptation through Conversational Elicitation in Human-Robot Interaction
RoboticsHuman-Computer Interaction
Summary
The authors created a system called PACE that lets a humanoid robot develop a personal identity by asking questions to the user during conversation. This helps the robot adapt its personality to fit the user better instead of using a fixed character. They tested the robot’s new dynamic personality and found it improved trust, connection, and how natural the interaction felt compared to a generic robot. Their work shows a way to make robot personalities more flexible and engaging in real-time conversations.
Authors
Peizhen Li, Longbing Cao, Megani Rajendran, Timothy Liu, Aik Beng Ng, Simon See
Abstract
Equipping humanoid robots with coherent and adaptable personas is crucial for fostering natural, engaging, and trustworthy human-robot interaction (HRI). However, existing approaches often rely on static, hard-coded identities that lack the flexibility to adapt to individual user contexts. In this paper, we present PACE (Persona Adaptation through Conversational Elicitation), a novel framework for the interactive generation and deployment of structured personas on the Ameca humanoid robot. Our system introduces an Interactive Persona Elicitation Pipeline, enabling the robot to dynamically synthesize a tailored, psychologically grounded identity through user Q&A. This elicitation process feeds into a persona prompt compilation phase, generating a structured persona prompt built upon multi-perspective dimensions. We detail the Embodied System Integration required to translate this structured specification into expressive, multimodal humanoid behaviors. Through a comprehensive empirical HRI evaluation, we assess the impact of dynamically generated personas on user trust, perceived anthropomorphism, persona consistency, personal relevance, and interaction quality compared to a generic baseline. These contributions establish a scalable pathway for deploying personalized, interactive, and reliable identities in embodied humanoid assistants. Video demo is available at: https://lipzh5.github.io/PACE/