Proactive description

The ability of an assistive system to automatically provide relevant visual or environmental information without requiring the user to explicitly request it. For blind and visually impaired users navigating real-world environments, proactive description is critical — a human sighted guide would naturally warn about approaching obstacles, mention relevant signs, or describe changes in the environment without being asked. Current AI video assistants typically operate in a turn-taking interaction pattern where they only respond to direct queries, creating a significant gap compared to human assistance. Proactive description requires the system to understand what information is relevant, timely, and safety-critical in the user's current context, and to balance helpfulness with avoiding information overload.