Do Robots Need Body Language?
Comparing Communication Modalities for Legible Motion Intent in Human-Shared Spaces
Abstract
Comparing communication modalities — expressive motion, lights, text, and audio — for legible robot navigation intent in human-shared spaces.
Robots in shared spaces often move in ways that are difficult for people to interpret, placing the burden on humans to adapt. High-DoF robots exhibit motion that people read as expressive — intentionally or not — making it important to understand how such cues are perceived. This project asks whether a robot’s body language alone can convey where it is about to go, or whether explicit signals do the job better.
Overview
We present an online video study evaluating how different signaling modalities — expressive motion, lights, text, and audio — shape people’s ability to understand a quadruped robot’s upcoming navigation actions, using Boston Dynamics’ Spot. Across four common scenarios, we measure how each modality influences viewers’:
- Accuracy in predicting the robot’s next navigation action
- Confidence in that prediction
- Trust in the robot to act safely
Research Questions
- How do implicit expressive motions compare to explicit channels (lights, text, audio) for communicating intent?
- Do aligned multimodal cues enhance interpretability beyond any single channel?
- How do conflicting cues affect a viewer’s confidence and trust?
Results
Explicit channels — especially text and audio — let viewers predict the robot’s next action far more accurately than implicit body motion alone, while expressive motion still outperformed having no signal at all. Redundant multimodal cues modestly raised confidence and trust, whereas conflicting cues eroded both.
Contribution
The study contributes initial evidence on the relative effectiveness of implicit versus explicit signaling strategies for legible motion intent — informing how robots in human-shared spaces should communicate what they are about to do.
Publication
Do Robots Need Body Language? Comparing Communication Modalities for Legible Motion Intent in Human-Shared Spaces — Companion of the 21st ACM/IEEE International Conference on Human-Robot Interaction (HRI ’26). arXiv:2604.03451
Research Groups
- Fluid Interfaces & City Science, MIT Media Lab
- New England Innovation Academy