A novel AI-driven approach to redirected walking in virtual reality that eliminates the need for eye-tracking hardware.
Our patent "Methods and Systems for Real-Time Saccade Prediction" has been granted.
TL;DR: A machine learning system that predicts natural saccadic eye movements in real-time, enabling redirected walking in virtual environments by leveraging inattentional blindness—without requiring expensive eye-tracking equipment or artificially triggering major saccades in users.
Navigating virtual environments that are larger than your physical space has always been a challenge in VR. Redirected walking offers an elegant solution by subtly rotating the virtual world while users walk, allowing them to explore vast digital landscapes within a confined room. However, current implementations come with significant trade-offs: they either require costly eye-tracking hardware integrated into head-mounted displays, or they deliberately induce major saccades to mask the redirection—both approaches that increase system complexity, cost, and potential user discomfort.
This invention introduces an AI-based prediction system that anticipates when users will naturally experience saccadic eye movements. During these brief moments of inattentional blindness—when visual processing is temporarily suppressed—the system applies subtle trajectory corrections that go unnoticed by the user. The result is a seamless, natural walking experience through expansive virtual worlds, all achieved without additional hardware or forced visual disruptions.