Control Methodology Impact on User Cognitive Workload in Gaze-Controlled Robotic Manipulation Tasks

He, Yiyang and Wang, Ziwei and Yan, Lei and Xue, Tao and Fei, Haolin (2025) Control Methodology Impact on User Cognitive Workload in Gaze-Controlled Robotic Manipulation Tasks. In: 2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN) :. IEEE. ISBN 9798331587727

Text (ROMAN_20_March_2025)
ROMAN_20_March_2025.pdf - Accepted Version
Download (5MB)

Abstract

This paper investigates two distinct paradigms for gaze-based control in human-robot collaboration (HRC). While gaze tracking offers a promising hands-free interaction method, the optimal mapping between eye movements and robot control remains an open research question. We examine two fundamentally different control approaches: (1) position-based control, which utilizes fiducial markers for spatial referencing and maps gaze positions directly to physical target locations; and (2) velocity-based control, whose functions are similar to a joystick where gaze position relative to camera frame centers determines movement direction and speed. Participants completed standardized pick-and-place tasks with both control methods. Performance was assessed through objective metrics including task completion time, trajectory efficiency, and error rates. Subjective experiences were evaluated using NASA Task Load Index questionnaires. Both systems incorporate a blink detection mechanism for gripper activation, enabling completely hands-free operation. This research addresses fundamental questions in eye-based robotic control for HRC, with applications spanning assistive technologies for mobility-impaired users, industrial settings that require hands-free operation, and medical environments where maintaining sterility is crucial. Results indicate significant differences between control paradigms, providing design insights for more intuitive and effective gaze-based interfaces in human-robot systems.