Collaborative Fall Detection and Response using Wi-Fi Sensing and Mobile Companion Robot
Yunwang Chen, Yaozhong Kang, Ziqi Zhao, Yue Hong, Lingxiao Meng, Max Q. -H. Meng
TL;DR
This work addresses indoor fall detection for the elderly in privacy-sensitive, NLOS environments by integrating Wi-Fi sensing with a mobile companion robot. It introduces a CSI-based fall detector using a two-stream convolution-augmented transformer, enhanced by transfer learning from existing CSI HAR data, and couples this to a dual-arm robot capable of navigating, opening doors, and providing assistance. The approach yields 90.1% base test accuracy and 96.3% after transfer learning, with fall-response trials achieving 87% success and arrival within 3 minutes. This demonstrates a practical, non-intrusive, autonomous system for timely elder-care support in real-world settings.
Abstract
This paper presents a collaborative fall detection and response system integrating Wi-Fi sensing with robotic assistance. The proposed system leverages channel state information (CSI) disruptions caused by movements to detect falls in non-line-of-sight (NLOS) scenarios, offering non-intrusive monitoring. Besides, a companion robot is utilized to provide assistance capabilities to navigate and respond to incidents autonomously, improving efficiency in providing assistance in various environments. The experimental results demonstrate the effectiveness of the proposed system in detecting falls and responding effectively.