Enabling saccadic redirection through real‐time saccade prediction

Abstract

Our proposed redirected walking technique improves on current solutions by leveraging temporary visual disruption caused by saccades for redirection without requiring additional eye‐tracking hardware and enables saccadic redirection on widely used consumer‐grade hardware, like mobile VR. Using a deep neural network trained on head rotation data, we predict saccades during an apparent head rotation and apply rigid transformations to the virtual environment for redirection. This allows users to infinitely walk in a perceived straight direction from within a physical tracked space of 3.5prefix×3.5$$ 3.5\times 3.5 $$ m2$$ {}^2 $$. The three user studies illustrated in this article validate our approach and demonstrate its efficacy.