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

Dynamic persona generation and embodied deployment on the Ameca humanoid robot

Anonymous Authors

Supplementary video demonstrating PACE running on the Ameca humanoid robot.

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.

Motivation and overview of the PACE framework
Fig. 1. Motivation and overview of the proposed PACE framework. When a user asks the Ameca robot to adopt a specific, familiar conversational style, a traditional static system prompt offers limited adaptability. In contrast, PACE uses Dynamic Persona Prompt Generation: an Interactive Q&A process builds a Persona Elicitation Specification, extracts theory-grounded psychological dimensions, and compiles them into a structured persona prompt that is mapped to embodied robot behavior.
PACE system architecture overview
Fig. 2. End-to-end system architecture for dynamic persona generation and deployment. PACE transitions from (1) Interactive Q&A for initial trait elicitation, to (2) Persona Specification Generation for transcription and attribute extraction, and finally to (3) Dynamic Persona Activation, which compiles the prompt and executes the physical persona switch on humanoid hardware.