Point of View: How Perspective Affects Perceived Robot Sociability

Abstract

Ensuring that robot navigation is safe and socially acceptable is crucial for comfortable human-robot interaction in shared environments. However, existing validation methods often rely on a bird's-eye (allocentric) perspective, which fails to capture the subjective first-person experience of pedestrians encountering robots in the real world. In this paper, we address the perceptual gap between allocentric validation and egocentric experience by investigating how different perspectives affect the perceived sociability and disturbance of robot trajectories. Our approach uses an immersive VR environment to evaluate identical robot trajectories across allocentric, egocentric-proximal, and egocentric-distal viewpoints in a user study. We perform this analysis for trajectories generated from two different navigation policies to understand if the observed differences are unique to a single type of trajectory or more generalizable. We further examine whether augmenting a trajectory with a head-nod gesture can bridge the perceptual gap and improve human comfort. Our experiments suggest that trajectories rated as sociable from an allocentric view may be perceived as significantly more disturbing when experienced from a first-person perspective in close proximity. Our results also demonstrate that while passing distance affects perceived disturbance, communicative social signaling, such as a head-nod, can effectively enhance the perceived sociability of the robot's behavior.

Figures (4)

• Figure 2: Example robot trajectory from different perspectives as evaluated in our user study. The allocentric perspective is rated as socially acceptable robot behavior. The egocentric-proximal perspective experienced by the person closest to the robot results in high perceived discomfort, whereas the egocentric-distal perspective experienced by the person farthest away from the robot shows the robot at a comfortable distance. Based on these findings, we provide design insights for navigation strategies.
• Figure 3: The different perspectives of the same trajectory presented to participants: (a) allocentric perspective showing the bird's-eye view of the trajectories representative of simulation environments, (b) egocentric-proximal perspective of the pedestrian P3 from (a), and (c) egocentric-distal perspective of the pedestrian P5 from (a).
• Figure 4: DWA and RL-based trajectories used for the user study. The DWA trajectory (green) is smooth, whereas the RL-based trajectory (blue) changes lane early. Both trajectories have similar passing distances ($0.95\,m$) to the closest pedestrian. The passing distance from the farthest pedestrian ($2.53\,m$) is also similar.
• Figure 5: The sociability and disturbance rating results from 24 participants. a) Sociability ratings show the highest sociability for the egocentric-distal case, but the differences amongst viewpoints are not significant. In all cases, the RL-based trajectory augmented with head-nodding received the highest sociability score. b) Disturbance ratings show the highest disturbance for the egocentric-proximal case, which has a significant difference compared to the other two viewpoints. The augmentation did not cause any significant effects on these ratings across viewpoints.