Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards Embedding Dynamic Personas in Interactive Robots: Masquerading Animated Social Kinematics (MASK)

Jeongeun Park, Taemoon Jeong, Hyeonseong Kim, Taehyun Byun, Seungyoon Shin, Keunjun Choi, Jaewoon Kwon, Taeyoon Lee, Matthew Pan, Sungjoon Choi

TL;DR

The design and development of an innovative interactive robotic system to enhance audience engagement using character-like personas and the role of personas in interactive agents are discussed and the factors to consider for creating an engaging user experience are discussed.

Abstract

This paper presents the design and development of an innovative interactive robotic system to enhance audience engagement using character-like personas. Built upon the foundations of persona-driven dialog agents, this work extends the agent's application to the physical realm, employing robots to provide a more captivating and interactive experience. The proposed system, named the Masquerading Animated Social Kinematic (MASK), leverages an anthropomorphic robot which interacts with guests using non-verbal interactions, including facial expressions and gestures. A behavior generation system based upon a finite-state machine structure effectively conditions robotic behavior to convey distinct personas. The MASK framework integrates a perception engine, a behavior selection engine, and a comprehensive action library to enable real-time, dynamic interactions with minimal human intervention in behavior design. Throughout the user subject studies, we examined whether the users could recognize the intended character in both personality- and film-character-based persona conditions. We conclude by discussing the role of personas in interactive agents and the factors to consider for creating an engaging user experience.

Towards Embedding Dynamic Personas in Interactive Robots: Masquerading Animated Social Kinematics (MASK)

TL;DR

The design and development of an innovative interactive robotic system to enhance audience engagement using character-like personas and the role of personas in interactive agents are discussed and the factors to consider for creating an engaging user experience are discussed.

Abstract

This paper presents the design and development of an innovative interactive robotic system to enhance audience engagement using character-like personas. Built upon the foundations of persona-driven dialog agents, this work extends the agent's application to the physical realm, employing robots to provide a more captivating and interactive experience. The proposed system, named the Masquerading Animated Social Kinematic (MASK), leverages an anthropomorphic robot which interacts with guests using non-verbal interactions, including facial expressions and gestures. A behavior generation system based upon a finite-state machine structure effectively conditions robotic behavior to convey distinct personas. The MASK framework integrates a perception engine, a behavior selection engine, and a comprehensive action library to enable real-time, dynamic interactions with minimal human intervention in behavior design. Throughout the user subject studies, we examined whether the users could recognize the intended character in both personality- and film-character-based persona conditions. We conclude by discussing the role of personas in interactive agents and the factors to consider for creating an engaging user experience.
Paper Structure (23 sections, 5 equations, 5 figures, 2 tables)

This paper contains 23 sections, 5 equations, 5 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Proposed Method
  4. Non-Verbal Cues
  5. Automated Persona Infuser via LLMs
  6. Motion Selection
  7. Expression Integration
  8. Transition Estimation
  9. Perception Engine
  10. Behavior Selection Engine
  11. Action Library
  12. Persona-Based Design Outcomes
  13. Experiments
  14. Experimental Setup
  15. Human Subject Study Results
  16. ...and 8 more sections

Figures (5)

  • Figure 1: The proposed system architecture. The system is composed of a perception engine, a behavior selection engine, and an action library, where the action library and the behavior databases are pre-built components.
  • Figure 2: Illustration of the proposed Persona Infuser, which generates the behavior database via LLM.
  • Figure 3: Demonstrations of the system. The first and second rows demonstrate the personality-based persona interaction, while the third and fourth rows demonstrate the character-based persona interaction. The emojis on the top indicate the facial expression that is displayed on the robot's screen. The caption under each image denotes the motion name.
  • Figure 4: Results from survey phase 1 with questions S1 and S2. (a) E-score of extroverted factor and A-score of agreeable factor. (b) E-score of extroverted persona with agreeable persona. (c) A-score of agreeable persona with extroverted persona. Agr., Dis., Ext., and Int. denote agreeable, disagreeable, extroverted, and introverted personas, respectively. * as $0.01<p<0.05$, ** as $p<0.01$, and *** as $p<0.001$. The error bars represent 95% confidence intervals.
  • Figure 5: Classification Confusion Matrix for the character-based persona representing the characters Cowardly Lion (LO), Minion (MM), Scrooge (SC), Spock (SS), Sloth (SZ), and Captain America (CA), respectively.