An experimental investigation of gaze behavior modeling in virtual reality

Esmer, Elif
The purpose of this study is to investigate if gaze behavior modeling on a robot avatar makes any difference in the engagement of human interlocutors. To that end, visual interaction patterns and impressions of participants during a one-on-one active conversation setting in the form of a mock-up job interview with an avatar agent have been analyzed. Experiments were conducted through eye-tracking methodology, questionnaires, and open-ended post-experimental evaluations. A robot avatar as an artificial agent programmed with pre-recorded speech and pre-planned gaze behavior, based on human gaze patterns, took the role of the human resource manager, in other words, the interviewer. The eye-tracking data of the participants, namely interviewees, were collected and analyzed to investigate whether the human-like gaze behavior of the artificial agent had any effect on the gaze allocation of the human interlocutors. Results of the questionnaires and the TF-IDF analysis of the post-experimental evaluations were inspected to detect reflections of participants’ gaze behavior and further patterns for the perception of the avatar.


Trust attribution in collaborative robots: An experimental investigation of non-verbal cues in a virtual human-robot interaction setting
Ahmet Meriç, Özcan; Şahin, Erol; Acartürk, Cengiz; Department of Bioinformatics (2021-6)
This thesis reports the development of non-verbal HRI (Human-Robot Interaction) behaviors on a robotic manipulator, evaluating the role of trust in collaborative assembly tasks. Towards this end, we developed four non-verbal HRI behaviors, namely gazing, head nodding, tilting, and shaking, on a UR5 robotic manipulator. We used them under different degrees of trust of the user to the robot actions. Specifically, we used a certain head-on neck posture for the cobot using the last three links along with the gr...
An artificial neural network model for virtual Superpave asphalt mixture design
Ozturk, Hande I.; Öztürk, Hande Işık (Informa UK Limited, 2014-02-07)
This study presents an artificial neural network (ANN) model to predict the asphalt mixture volumetrics at Superpave gyration levels. The input data-set needed by the algorithm is composed of gradation of the mix, bulk specific gravity of aggregates, low- and high-performance grade of the binder, binder content of the mix and the target number of gyrations (i.e. N-ini, N-des and N-max). The proposed ANN model uses a three-layer scaled conjugate gradient back-propagation (feed-forward) network. The ANN was t...
The learning and use of traversability affordance using range images on a mobile robot
Ugur, Emre; Dogar, Mehmet R.; Cakmak, Maya; Şahin, Erol (2007-04-14)
We are interested in how the concept of affordances can affect our view to autonomous robot control, and how the results obtained from autonomous robotics can be reflected back upon the discussion and studies on the concept of affordances. In this paper, we studied how a mobile robot, equipped with a 3D laser scanner, can learn to perceive the traversability affordance and use it to wander in a room filled with spheres, cylinders and boxes. The results showed that after learning, the robot can wander around...
Important factors in mobile robot user interface design
Sekmen, A; Goldman, S; Koku, Ahmet Buğra; Zein-Sabatto, S; Wilkes, M (2001-07-25)
In this study, four factors are considered to be important in the interactions between a mobile robot and a human. These factors are robot location, user's prior knowledge about the robot's environment, spatial reasoning ability of the user, and user interfaces. The first objective of this study is to determine if providing a user interface component showing the relative position of the robot with respect to the user results in any improvement. The second objective is to have an overall evaluation of the us...
Karasakal, Esra; Bozkurt, Ahmet (2019-08-01)
In this study, an approach based on PROMETHEE is developed to correctly reflect the choice behavior of the decision maker that is not explained by the utility theory. The prospect theory argues that losses have higher impact than gains. We integrate the prospect theory into PROMETHEE through defining new preference functions. The proposed approach is behaviorally realistic and tolerates some degree of intransitivities in the preferences of the decision maker. For determining the criteria weights, we utilize...
Citation Formats
E. Esmer, “An experimental investigation of gaze behavior modeling in virtual reality,” M.S. - Master of Science, Middle East Technical University, 2022.