PACE: Persona Adaptation through Conversational Elicitation in Human-Robot Interaction

2026-07-16

AI Summary

This work addresses the limitations of current robotic systems that rely on static, hard-coded personality profiles, which hinder natural and credible human–robot interaction by failing to adapt dynamically to user context. To overcome this, the authors propose the PACE framework, which introduces an interactive personality induction mechanism that constructs a psychologically plausible, multidimensional personality representation in real time through conversational questioning. This abstract personality model is then translated into both verbal and nonverbal behaviors of a humanoid robot (Ameca) via structured prompt compilation and embodied system integration. Experimental results demonstrate that, compared to generic baselines, the proposed approach significantly enhances users’ perceptions of the robot’s trustworthiness, anthropomorphism, personality consistency, personal relevance, and overall interaction quality.

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/

Problem

• human-robot interaction
• persona adaptation
• adaptive identity
• personalized interaction
• embodied agents

Innovation

• Persona Adaptation
• Conversational Elicitation
• Human-Robot Interaction
• Embodied AI
• Interactive Persona Generation