EM-Fall: Embodied mmWave Sensing for Day-and-Night Fall Detection on Humanoid Robots

2026-06-09

AI Summary

This work addresses the limitations of existing fall detection systems, which rely on wearable devices or fixed sensors and suffer from performance degradation due to poor user compliance, limited spatial coverage, occlusion, and low-light conditions. To overcome these challenges, the authors propose an active perception approach that integrates millimeter-wave radar with embodied intelligence on a humanoid robot, enabling autonomous navigation and dynamic adjustment of observation viewpoints for robust, all-weather, cross-room fall detection. The system incorporates a lightweight temporal modeling module and a human-centric perception pipeline, achieving high detection accuracy across eight real-world home environments. Furthermore, the study introduces the first indoor millimeter-wave fall detection dataset, significantly enhancing the continuity and reliability of monitoring in complex domestic settings.

Abstract

Falls are one of the leading causes of injury and hospitalization among elderly individuals, making reliable fall awareness an essential capability for safety monitoring in residential environments. However, existing fall detection systems often rely on wearable devices or fixed sensing installations, which may suffer from low user compliance, limited spatial coverage, or degraded performance under occlusion and poor lighting conditions. In this work, we propose \textbf{EM-Fall}, an embodied fall detection framework deployed on a mobile humanoid robot. The system integrates millimeter-wave (mmWave) sensing with robotic mobility, allowing the robot to actively adjust its sensing viewpoint and maintain target observability across rooms and under occlusion. To address interference in complex residential environments, including pet motion and multipath artifacts, we design a human-centered perception pipeline combined with lightweight temporal modeling to capture motion evolution before, during, and after fall events. We evaluate the proposed system across eight real indoor environments with four participants and construct an in-home mmWave fall detection dataset. Experimental results show that the embodied mobile sensing paradigm improves monitoring continuity and maintains robust fall detection performance under diverse environmental conditions. The proposed framework provides a practical solution for robot-assisted safety monitoring in home environments.

Problem

• fall detection
• mmWave sensing
• humanoid robots
• occlusion
• residential environments

Innovation

• embodied sensing
• mmWave radar
• fall detection
• humanoid robot
• mobile sensing