HeadRoom: Lightweight, Edge-deployable Pipeline for Adaptive Notification Routing

2026-07-08

AI Summary

This work addresses the challenges of notification disruption and response latency in wearable systems by proposing an adaptive notification routing mechanism grounded in real-time multimodal sensing. Leveraging lightweight audiovisual signal processing from a first-person perspective, the system dynamically assesses the availability of the user’s visual and auditory channels directly on edge devices and intelligently routes notifications to the less occupied sensory modality. This approach represents the first implementation of real-time channel availability estimation under strict resource constraints. In a user study involving 25 participants, the adaptive strategy significantly reduced response times compared to fixed-channel notification delivery, establishing a novel paradigm for intelligent notification management in immersive computing environments.

Abstract

Emerging wearables, such as smart glasses, can deliver notifications through multiple sensory channels, but there is still a limited understanding of how to choose the right channel at the right moment. We propose HeadRoom, a lightweight, edge-deployable pipeline that estimates the availability of visual and auditory channels in real time from egocentric video and audio. Our controlled user study (N=25) shows that, under high perceptual load, routing notifications to the more available channel reduces response time relative to routing them to the less available channel. This work opens up a new possibility for adaptive routing of notifications in wearable and immersive systems.

Problem

• adaptive notification routing
• sensory channels
• wearable systems
• perceptual load
• notification delivery

Innovation

• adaptive notification routing
• egocentric sensing
• multimodal availability estimation
• edge-deployable pipeline
• wearable computing