Blinking into Emotion: How Context and LED Frequency Shape Non-Humanoid Robots� Emotional Transparency
Patrizio Scarpato, Luca Raggioli, Raffaella Esposito, Silvia Rossi
AI summary
Problem
Non-humanoid robots lack facial expressiveness, making it difficult to communicate emotional states clearly. This study investigates how limited non-verbal cues like LED blinking, combined with contextual information, can improve emotional transparency.
Approach
The team programmed a non-humanoid robot to express six emotions using varying LED blink frequencies, colors, facial animations, sounds, and movements. Two online user studies compared a blinking-only condition, a blinking-plus-face condition, and a full multimodal model, both with and without short contextual sentences.
Key results
- Blinking LEDs alone provide a minimal but functional emotional channel
- Short contextual sentences significantly improve accurate perception of robot arousal
- Optimized blinking with context matches or exceeds full multimodal performance for specific emotions
- Context consistently reduces the gap between intended and perceived emotional states
Why it matters
Offers robot developers a practical, low-cost method for emotional expression in non-humanoid platforms, enhancing trust and naturalness in human-robot interactions.
Abstract
In social contexts, correctly interpreting commu- nicative signals is essential for understanding an interlocutor’s reactions. Emotional cues provide important context, enhancing mutual understanding and enabling more natural, adaptive interactions. For non-humanoid robots, which typically have more limited interaction capabilities, it could be necessary to combine multiple non-verbal signals and to consider the context in which they are used. In this work, we present the design of non-verbal behaviors that enable a non-humanoid robot to communicate its intended emotional state effectively. Our strategy focuses on the use of LEDs as non-verbal cues along with facial expressions for conveying emotions. We conducted a user study to evaluate the effect of these channels with and without context. Our results show that the robot conveys emotions more transparently when context is included, and that blinking LEDs can be an effective channel for communicating emotion. Results suggest that blinking alone is a minimal but functional cue, with richer models performing better without context. When short contextual sentences and more spaced blink frequencies are added, the blinking-only condition performs on par with, or even better than, the full multimodal model for some emotions and, in particular, with respect to participants’ perceived arousal. This indicates that carefully designed, simple visual cues can be an effective affect channel for non-humanoid robots.