Related Experiment Video
Updated: Jan 7, 2026
07:34
Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues
Published on: June 3, 2013
17.8K
Evaluating human perceptions of android robot facial expressions based on variations in instruction styles
Ayaka Fujii1, Carlos Toshinori Ishi1,2, Kurima Sakai1,2
1Guardian Robot Project, RIKEN, Kyoto, Japan.
Frontiers in Robotics and AI
|January 1, 2026
Summary
Abstract instructions enhance human perceptions of robot expressiveness and agency. Participants found the android robot Nikola more appropriate and emotionally expressive when given abstract commands, suggesting improved human-robot interaction.
Area of Science:
- Robotics
- Human-Robot Interaction
- Artificial Intelligence
Background:
- Human-robot interaction necessitates context-appropriate emotional expressions from robots.
- Existing research often overlooks nuanced emotional expressions beyond basic emotions.
- Real-world applications demand robots capable of complex and varied emotional displays.
Purpose of the Study:
- To extend the expressive capabilities of the android robot Nikola with 63 facial expressions.
- To investigate the impact of abstract versus explicit instructions on perceived robot agency and expressiveness.
- To analyze how robot expressions and user personality traits influence human perceptions.
Main Methods:
- Implemented 63 facial expressions on the android robot Nikola, including complex emotions, physical conditions, and intensity variations.
- Collected interaction data from over 600 participants at Expo 2025, who described desired robot facial expressions.
- Utilized a large language model for emotion inference and corresponding facial expression generation.
- Administered questionnaires to assess participant perceptions of robot appropriateness and emotional expressiveness.
Main Results:
- Participants rated Nikola's behavior as more appropriate and emotionally expressive when given abstract instructions compared to explicit ones.
- Abstract instructions were found to enhance the perceived agency of the robot.
- Impressions of the robot varied based on the specific expressions performed and the participants' personality traits.
Conclusions:
- Adaptive facial expressions, combined with abstract instruction styles, significantly shape human perceptions of social robots.
- Abstract instructions can foster a greater sense of agency in robots, improving human-robot interaction.
- This research provides insights into designing more socially intelligent and engaging robots through nuanced emotional expression and interaction design.
Related Concept Videos
02:16Stereotype Content Model
15.3K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
15.3K
01:24Facial Feedback Hypothesis
526
Charles Darwin proposed that facial expressions are an evolutionary adaptation for communication. He argued that these expressions are not influenced by culture but are universal across species. For example, a snarling expression with exposed teeth signals a threat in many animals, including humans. Darwin also suggested that displaying an emotion can intensify the feeling. Smiling, for example, could enhance one's sense of happiness. This idea laid the foundation for understanding the role...
526