Teleoperation through eye gaze (TeleGaze): a multimodal approach

Authors:
Hemin Omer Latif;Nasser Sherkat;Ahmad Lotfi
Affiliations:
School of Science and Technology, Nottingham Trent University, Nottingham, UK;School of Science and Technology, Nottingham Trent University, Nottingham, UK;Department of Computing and Technology, School of Science and Technology, Nottingham Trent University, Nottingham, UK
Venue:
ROBIO'09 Proceedings of the 2009 international conference on Robotics and biomimetics
Year:
2009

Citing 5
Cited 1

What you look at is what you get: eye movement-based interaction techniques

CHI '90 Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Keeping an Eye for HCI

SIBGRAPI '99 Proceedings of the XII Brazilian Symposium on Computer Graphics and Image Processing
Active Gaze Tracking for Human-Robot Interaction

ICMI '02 Proceedings of the 4th IEEE International Conference on Multimodal Interfaces
Fixation Precision in High-Speed Noncontact Eye-Gaze Tracking

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
A Novel Gaze Estimation System With One Calibration Point

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Move it there, or not?: the design of voice commands for gaze with speech

Proceedings of the 4th Workshop on Eye Gaze in Intelligent Human Machine Interaction

Quantified Score

Hi-index	0.00

Visualization

Abstract

Most mobile robot teleoperation require monitoring as well as controlling from a remote location. This engages both the hands and the eyes of the human operator for the whole duration of the operation. Aiming at minimizing the human body engagement by freeing the hands of the operator from the controlling task, previous works by the authors proved that both monitoring and controlling can be achieved using solely inputs from the operator's eyes. The TeleGaze interface, which has been developed as a novel interface for teleoperation through eye gaze, enabled the operator to control a robotic platform, an onboard active vision and some aspects of the interface using eye-gaze tracking. However, the advantage of free hands using TeleGaze was accompanied by an increase in the task's general workload causing some extra stress on the operator. In the aim of optimizing the human-robot interaction experience while using TeleGaze, a multimodal approach is believed to be necessary. Therefore, in addition to some further refinements in the design of the interface a multimodal TeleGaze system has also been developed. In this paper the multimodal version of TeleGaze using an accelerator pedal and the native version of TeleGaze using dwell time are both presented. Details of the refinements in the design of the interface and the results of a task-oriented evaluation for three different modes of interaction, including both modes of TeleGaze, are also included.