How Age Influences the Interpretation of Emotional Body Language in Humanoid Robots -- long paper version

2025-07-25

AI Summary

This study investigates how age modulates perception of affective bodily expressions in the humanoid robot NAO, comparing children, young adults, and older adults. Using a cross-sectional behavioral experiment, we systematically assessed recognition accuracy and response patterns for four basic emotions (happiness, anger, sadness, fear). Results reveal a striking similarity in emotion recognition performance between children and older adults—both significantly underperforming relative to young adults—thereby identifying an empirically grounded “bipolar age similarity” effect. Critically, NAO demonstrated robust cross-generational expressivity, particularly for emotions with high intersubjective consensus. This work provides the first empirical evidence of age-related convergence at developmental extremes in socio-affective robot perception. It advances foundational knowledge for designing emotionally intelligent social robots tailored to aging populations, offering empirically validated cognitive principles and concrete pathways for age-inclusive interaction design.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Humans and AI: Emotional Intelligence

Application Category

• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

This paper presents an empirical study investigating how individuals across different age groups, children, young and older adults, interpret emotional body language expressed by the humanoid robot NAO. The aim is to offer insights into how users perceive and respond to emotional cues from robotic agents, through an empirical evaluation of the robot's effectiveness in conveying emotions to different groups of users. By analyzing data collected from elderly participants and comparing these findings with previously gathered data from young adults and children, the study highlights similarities and differences between the groups, with younger and older users more similar but different from young adults.

Problem

• How age affects emotional body language interpretation in robots
• Compare emotional perception of NAO robot across age groups
• Identify similarities and differences in robot emotion recognition

Innovation

• Humanoid robot NAO conveys emotional body language
• Empirical study across children and adults
• Comparative analysis of age group responses