EmboDrone: towards mobile proximal spatial intelligence for elderly outdoor assistance

Abstract

Outdoor mobility presents persistent safety challenges for older adults, particularly in environments with uneven surfaces, dynamic traffic conditions, and dense crowds. Existing assistive technologies, ranging from wearables to walking companion robots and assistive drones, provide useful support but often operate within single scenarios, rely on command-driven behaviors, and lack legible interaction cues aligned with older adults’ cognitive tendencies. This study introduces EmboDrone, a near-body assistive drone designed to explore coherent, vision-based hazard perception across multiple outdoor situations. Using a Research-through-Design (RtD) approach, we first introduce Proximal Spatial Intelligence (PSI) as a conceptual framework for understanding how mobile assistance may coordinate environmental sensing, action responses, and user feedback within the user’s near-body space. Guided by this framework, we designed a mid-fidelity drone prototype that integrates RGB-D sensing and a YOLO-based visual recognition pipeline on an edge-computing flight platform, enabling automatic human-following and simple auditory alerts for potential hazards such as obstacles, traffic lights, and pedestrians. We then conducted a multi-stakeholder evaluation (n = 39) involving older adults, family caregivers, and experts to examine how different stakeholder roles perceive and respond to PSI-guided interaction behaviors. The findings provide preliminary insights into how proximal spatial intelligence is interpreted and trusted across stakeholder roles. Together, the PSI framework, the EmboDrone design exemplar, and the multi-stakeholder evaluation provide design directions for future mobile, proximity-based assistive systems for older adults in dynamic outdoor environments.