Predictive robot eyes enhance attentional guidance in cooperative human–robot interaction

Abstract

Abstract A key factor in successful human–robot interaction (HRI) is the predictability of a robot’s actions. Visual cues, such as eyes or arrows, can serve as directional indicators to enhance predictability, potentially improving performance and increasing trust. This study investigated the effects of predictive cues on performance, trust, and visual attention allocation in an industrial HRI setting. Using a 3 (predictive cues: abstract anthropomorphic eyes, directional arrows, no cue) $$\times$$ 3 (experience in three experimental blocks) mixed design, 42 participants were tasked with predicting a robot’s movement target as quickly as possible. Contrary to our expectations, predictive cues did not significantly affect trust or prediction performance. However, eye-tracking revealed that participants exposed to anthropomorphic eyes identified the target earlier than those without cues. Interestingly, participant’s self-reports showed infrequent use of the cues as directional guidance. Still, greater cue usage, as indicated by fixation data, was associated with faster predictions, suggesting that predictive cues, particularly anthropomorphic ones, guide visual attention and may improve efficiency. These findings highlight the nuanced role of predictive cues in HRI: even when not heavily relied on or reflected in performance, they can subtly guide attention and support interaction.