Visual alignment tasks, such as perspective pointing, inherently involve ambiguity because either the left or right eye can dominate, serving as the vantage point. Previous work presented eye dominance as dynamic, influenced by horizontal gaze angle to the target. In this work, we investigate prediction based on both target-based and user-dependent features, with machine learning models trained from data collected from a perspective-pointing task (N=28). We confirm that vertical target angle influences eye dominance, strengthening the effect of horizontal angles, specifically below eye level. Models using target information alone performed poorly, particularly for left-eye cases. Including user-specific features improved accuracy and class balance, with gradient boosted classifiers achieving the highest performance. These results underscore the significance of personalized features for eye dominance prediction, with practical implications for virtual reality (VR) interfaces.

Figure 1: The experimental setup for investigating eye dominance in virtual reality (VR).A participant, wearing a VR headset, aligns a virtual cursor with a distant target using a controller.The two insets display the rendering for the left and right eye views, demonstrating target-controller alignment with the right eye only.In this trial, the participant is right-eye dominant.

This paper presents a head-mounted virtual reality study that compared gaze, head, and controller pointing for selection of dynamically revealed targets. Existing studies on head-mounted 3D interaction have focused on pointing and selection tasks where all targets are visible to the user. Our study compared the effects of screen width (field of view), target amplitude and width, and prior knowledge of target location on modality performance. Results show that gaze and controller pointing are significantly faster than head pointing and that increased screen width only positively impacts performance up to a certain point. We further investigated the applicability of existing pointing models. Our analysis confirmed the suitability of previously proposed two-component models for all modalities while uncovering differences for gaze at known and unknown target positions. Our findings provide new empirical evidence for understanding input with gaze, head, and controller and are significant for applications that extend around the user.

Social interactions are essential in the everyday lives of humans. People with an autism spectrum disorder (ASD) display shortages of social skills, thus making their day-to-day encounters more difficult. This paper reports on two small-scale studies, investigating whether the use of collaborative robot tasks in an educational setting stimulates the collaborative behavior of children with ASD, and whether robotic task complexity affects collaborative behavior. A total of 24 children participated in robotic tasks of varying complexities. The sessions were videotaped and analyzed. Children's supervisors completed questionnaires, evaluating the social behavior of participants. Results demonstrate that children collaborated during the robot activities. The influence of robotic task complexity on collaboration skills was not significant, possibly due to the small number of participants. The results show the promise of using robots in education for children with ASD, although further research is needed to investigate the implementation of robots in special education.