AIDEN: Design and Pilot Study of an AI Assistant for the Visually Impaired

This paper presents AIDEN, an artificial intelligence–based assistant designed to enhance the autonomy and daily quality of life of visually impaired individuals, who often struggle with object identification, text reading, and navigation in unfamiliar environments. Despite these advancements, a significant research gap remains: there is a lack of integrated solutions that provide real-time, actionable guidance without compromising the user’s environmental awareness or data privacy. Current systems force a trade-off between functional assistance and sensory safety. AIDEN addresses these limitations through a novel system integration that combines real-time object detection and Object Description within a multimodal interaction framework, prioritizing the reduction of auditory overload through tactile feedback. A central design feature is that AIDEN offloads spatial guidance to continuous haptic feedback for object retrieval, while audio is primarily used for semantic content (OCR and VQA), the privacy is preserved by ensuring that no personal data are stored. Empirical evaluations with visually impaired participants assessed perceived ease of use and acceptance using the Technology Acceptance Model (TAM). Results indicate high user satisfaction, particularly regarding intuitiveness and perceived autonomy. Moreover, the ‘‘Find an Object’’ achieved low-latency performance under the tested conditions. These findings suggest that multimodal haptic–visual feedback may support daily usability and independence relative to traditional audio-centric methods, motivating larger-scale validations.