Interactive Registration Methods for Augmented Reality in Robotics: A Comparative Evaluation

Abstract

Augmented Reality (AR) visualization has shown potential for supporting intuitive and efficient human-robot interaction in a range of tasks. Since all these tasks are spatially related to the robot, the precise positioning of the AR content is critical to the applicability. However, most research has primarily focused on developing visualizations rather than exploring methods for aligning AR content in the robotic workspace. This paper aims to bridge this gap by implementing and comparing different interactive registration methods, including two point-based and one manual approach. We comparatively evaluated these registration methods in a user study (n=21), measuring registration accuracy, duration, and subjective user feedback. Our results indicate that the point-based methods outperform the manual approach in terms of both accuracy and perceived workload. Furthermore, participants achieved significantly faster performance with a point-based approach using physically defined registration points compared to a point-based approach using markers attached to the robot.