Examining the legibility of humanoid robot arm movements in a pointing task

TL;DR

This study explores how humans interpret humanoid robot arm movements in a pointing task, focusing on the effects of truncated trajectories and bodily cues on predicting robot intentions.

Contribution

It provides empirical evidence on the influence of multimodal cues and movement truncation on the legibility of robot actions in human-robot interaction.

Findings

Multimodal cues improve prediction accuracy.

Gaze and pointing cues influence intention understanding.

Truncated movements still convey sufficient intent.

Abstract

Human--robot interaction requires robots whose actions are legible, allowing humans to interpret, predict, and feel safe around them. This study investigates the legibility of humanoid robot arm movements in a pointing task, aiming to understand how humans predict robot intentions from truncated movements and bodily cues. We designed an experiment using the NICO humanoid robot, where participants observed its arm movements towards targets on a touchscreen. Robot cues varied across conditions: gaze, pointing, and pointing with congruent or incongruent gaze. Arm trajectories were stopped at 60\% or 80\% of their full length, and participants predicted the final target. We tested the multimodal superiority and ocular primacy hypotheses, both of which were supported by the experiment.