Reliability-Aware Multi-Agent Sonification for Visually Impaired Indoor Navigation

Abstract

Indoor navigation systems for visually impaired (VI) users typically rely on continuous sonification over pre-built semantic maps, which leads to two compounding problems: auditory fatigue from constant audio output, and unsafe guidance when the map becomes stale due to environmental changes. We propose a multi-agent architecture that addresses both challenges. The system consists of three collaborating agents: an Environment Perception Agent that monitors spatial complexity and maintains per-object reliability scores that reflect the likelihood that mapped objects remain accurate, a User State Inference Agent that estimates user confidence from movement patterns, and a Sonification Planning Agent trained via reinforcement learning to decide when and how much audio feedback to provide. The system adapts its sonification not only to user state and spatial context, but also to map uncertainty, increasing audio support in areas where the map may be outdated. We evaluate the system in simulation with a literature-grounded user behavior model across varying levels of map staleness. Results across 5,000 episodes show that our approach reduces sonification volume by 53% compared to always-on sonification baselines while maintaining a 98.7% hazard notification rate under fresh maps. Under severely stale maps (one week old), our system degrades only 21% in navigation efficiency compared to 27-33% for the other baselines.