Augmented Reality Navigation Assistance System for Visually Impaired Individuals

Abstract

Visually impaired people face a lot of issues navigating and moving around their environment, mostly depending on their mobility cane, memory, and familiarity with the environment to navigate. Technologies designed for them are usually expensive, hard to get, or uncomfortable. This research presents the design, implementation and evaluation of an Augmented Reality (AR)-based indoor navigation system for visually impaired individuals, compatible with Android and iOS devices. Using an Agile methodology, we conducted interviews, gave out questionnaires, and made observations with a number of visually impaired individuals in order to establish user requirements and refine the scope of the project. The system was implemented using the AR library, Niantic Lightship ARDK with real time meshing and semantic segmentation features, the Unity 3D engine, and the C# programming language. The AR navigation tool digitally maps the environment, detecting obstacles and filtering out the ground. When an obstacle is detected within one meter, the system provides haptic and auditory feedback, alerting the user until they move away. Usability testing was conducted with 18 visually impaired participants through questionnaires, interviews, and observations. The system’s usability was assessed using the John Brooke System Usability Scale (SUS), achieving a score of 81.39, classified as “Best Imaginable.” This research contributes to the field of AR-based assistive technologies.