More Like this

1. Gaze Sharing, a Double-Edged Sword: Examining the Effect of Real-Time Gaze Sharing Visualizations on Team Performance and Situation Awareness

   https://doi.org/10.1177/00187208241272060  

   Atweh, Jad A; Riggs, Sara L (March 2025, Human Factors: The Journal of the Human Factors and Ergonomics Society)

   ObjectiveThe goal of this study was to assess how different real-time gaze sharing visualization techniques affect eye tracking metrics, workload, team situation awareness (TSA), and team performance. BackgroundGaze sharing is a real-time visualization technique that allows teams to know where their team members are looking on a shared display. Gaze sharing visualization techniques are a promising means to improve collaborative performance on simple tasks; however, there needs to be validation of gaze sharing with more complex and dynamic tasks. MethodsThis study evaluated the effect of gaze sharing on eye tracking metrics, workload, team SA, and team performance in a simulated unmanned aerial vehicle (UAV) command-and-control task. Thirty-five teams of two performed UAV tasks under three conditions: one with no gaze sharing and two with gaze sharing. Gaze sharing was presented using a fixation dot (i.e., a translucent colored dot) and a fixation trail (i.e., a trail of the most recent fixations). ResultsThe results showed that the fixation trail significantly reduced saccadic activity, lowered workload, supported team SA at all levels, and improved performance compared to no gaze sharing; however, the fixation dot had the opposite effect on performance and SA. In fact, having no gaze sharing outperformed the fixation dot. Participants also preferred the fixation trail for its visibility and ability to track and monitor the history of their partner’s gaze. ConclusionThe results showed that gaze sharing has the potential to support collaboration, but its effectiveness depends highly on the design and context of use. ApplicationThe findings suggest that gaze sharing visualization techniques, like the fixation trail, have the potential to improve teamwork in complex UAV tasks and could have broader applicability in a variety of collaborative settings. 

   more » « less
2. Gaze transition entropy as a measure of attention allocation in a dynamic workspace involving automation

   https://doi.org/10.1038/s41598-024-74244-4  

   Cui, Zixin; Sato, Tetsuya; Jackson, Austin; Jayarathna, Sampath; Itoh, Makoto; Yamani, Yusuke (December 2024, Scientific Reports)

   Abstract Real-world work environments require operators to perform multiple tasks with continual support from an automated system. Eye movement is often used as a surrogate measure of operator attention, yet conventional summary measures such as percent dwell time do not capture dynamic transitions of attention in complex visual workspace. This study analyzed eye movement data collected in a controlled a MATB-II task environment using gaze transition entropy analysis. In the study, human subjects performed a compensatory tracking task, a system monitoring task, and a communication task concurrently. The results indicate that both gaze transition entropy and stationary gaze entropy, measures of randomness in eye movements, decrease when the compensatory tracking task required more continuous monitoring. The findings imply that gaze transition entropy reflects attention allocation of operators performing dynamic operational tasks consistently. 

   more » « less
3. Semantic gaze labeling for human-robot shared manipulation

   https://doi.org/10.1145/3314111.3319840  

   Aronson, Reuben M.; Admoni, Henny (June 2019, Symposium on Eye Tracking Research and Applications (ETRA))

   Human-robot collaboration systems benefit from recognizing people’s intentions. This capability is especially useful for collaborative manipulation applications, in which users operate robot arms to manipulate objects. For collaborative manipulation, systems can determine users’ intentions by tracking eye gaze and identifying gaze fixations on particular objects in the scene (i.e., semantic gaze labeling). Translating 2D fixation locations (from eye trackers) into 3D fixation locations (in the real world) is a technical challenge. One approach is to assign each fixation to the object closest to it. However, calibration drift, head motion, and the extra dimension required for real-world interactions make this position matching approach inaccurate. In this work, we introduce velocity features that compare the relative motion between subsequent gaze fixations and a finite set of known points and assign fixation position to one of those known points. We validate our approach on synthetic data to demonstrate that classifying using velocity features is more robust than a position matching approach. In addition, we show that a classifier using velocity features improves semantic labeling on a real-world dataset of human-robot assistive manipulation interactions. 

   more » « less
4. Semantic Gaze Labeling for Human-Robot Shared Manipulation

   Aronson, Reuben M; Admoni, Henny (June 2019, ACM Symposium on Eye Tracking Research & Applications)

   Human-robot collaboration systems benefit from recognizing people’s intentions. This capability is especially useful for collaborative manipulation applications, in which users operate robot arms to manipulate objects. For collaborative manipulation, systems can determine users’ intentions by tracking eye gaze and identifying gaze fixations on particular objects in the scene (i.e., semantic gaze labeling). Translating 2D fixation locations (from eye trackers) into 3D fixation locations (in the real world) is a technical challenge. One approach is to assign each fixation to the object closest to it. However, calibration drift, head motion, and the extra dimension required for real-world interactions make this position matching approach inaccurate. In this work, we introduce velocity features that compare the relative motion between subsequent gaze fixations and a nite set of known points and assign fixation position to one of those known points. We validate our approach on synthetic data to demonstrate that classifying using velocity features is more robust than a position matching approach. In addition, we show that a classifier using velocity features improves semantic labeling on a real-world dataset of human-robot assistive manipulation interactions. 

   more » « less
5. Unsupervised Gaze Prediction in Egocentric Videos by Energy-based Surprise Modeling

   Aakur, Sathyanarayanan N.; Bagavathi, Arunkumar (April 2021, International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications)

   null (Ed.)

   Egocentric perception has grown rapidly with the advent of immersive computing devices. Human gaze prediction is an important problem in analyzing egocentric videos and has primarily been tackled through either saliency-based modeling or highly supervised learning. We quantitatively analyze the generalization capabilities of supervised, deep learning models on the egocentric gaze prediction task on unseen, out-of-domain data. We find that their performance is highly dependent on the training data and is restricted to the domains specified in the training annotations. In this work, we tackle the problem of jointly predicting human gaze points and temporal segmentation of egocentric videos without using any training data. We introduce an unsupervised computational model that draws inspiration from cognitive psychology models of event perception. We use Grenander's pattern theory formalism to represent spatial-temporal features and model surprise as a mechanism to predict gaze fixation points. Extensive evaluation on two publicly available datasets - GTEA and GTEA+ datasets-shows that the proposed model can significantly outperform all unsupervised baselines and some supervised gaze prediction baselines. Finally, we show that the model can also temporally segment egocentric videos with a performance comparable to more complex, fully supervised deep learning baselines. 

   more » « less