Summary
Virtual worlds often rely on visual information that blind or visually impaired people cannot easily access. Existing tools each handle only one task like naming objects or describing scenes. The authors present MetaBlind, a system that uses multiple specialized agents working together to gather and prioritize useful information, and then shares only the most relevant details with the user through speech or touch. This approach aims to reduce information overload and make virtual worlds more accessible. The paper describes the system design and how to evaluate it, but no prototype or user testing has been conducted yet.
What this means in practice
- •For virtual reality platform developers: Create virtual environments that deliver only the most relevant nonvisual cues to blind users by integrating multiple specialized agents with an accessibility orchestrator.
- •For assistive technology designers: Design tools that combine various sensory and interaction agents to provide personalized, context-aware nonvisual navigation and interaction in live virtual rooms.
A position paper. It proposes an approach and reports no results.
Authors
Toqeer Ali Syed, Ali Akarma, Adeel Ahmad, Danial Hameed
Abstract
Virtual worlds now host classrooms, meetings, conferences, shops, and social venues, and nearly every interaction they expose assumes a user who can scan a three-dimensional scene, follow avatars, and read floating panels. Blind and visually impaired (BVI) users are left with assistive tools that each solve one task in isolation: naming an object, reading text, describing a scene, or planning a route. A live virtual room defeats that model: obstacles, speakers, gestures, chat, slides, and notifications arrive together, and a tool that narrates all of them trades a visual barrier for an auditory one. This paper presents MetaBlind, an architecture that distributes nonvisual access across eight specialized agents, spanning perception, navigation, social and object interaction, communication, safety and trust, memory, and personalization, and that places an Accessibility Orchestrator between those agents and the user. Agents publish candidate information into a shared accessibility context instead of speaking to the user directly. The orchestrator scores each candidate on safety relevance, goal relevance, urgency, confidence, user relevance, and estimated listening load, then releases only the items it judges relevant at that moment through speech, structured audio, or haptic output. We give the selection step a formal statement, specify the orchestration cycle as an algorithm, and define an evaluation protocol against a single-agent assistant. MetaBlind is reported at the design stage, with no prototype measurement or user study, and the protocol states which outcomes would support the design and which would refute it.