Millimeter Wave Radar-based Human Activity Recognition for Healthcare Monitoring Robot

TL;DR

This paper introduces RobHAR, a robot-mounted mmWave radar system with lightweight deep learning models for real-time human activity recognition, addressing challenges of sparse data, limited range, and continuous classification in healthcare monitoring.

Contribution

The paper presents a novel movable robot-mounted mmWave radar system with lightweight neural networks and a transition optimization strategy for improved real-time human activity recognition.

Findings

RobHAR outperforms previous methods in discrete and continuous HAR tasks.

The system achieves real-time monitoring on a robot-mounted edge platform.

Experimental results demonstrate robustness and accuracy in real-world scenarios.

Abstract

Healthcare monitoring is crucial, especially for the daily care of elderly individuals living alone. It can detect dangerous occurrences, such as falls, and provide timely alerts to save lives. Non-invasive millimeter wave (mmWave) radar-based healthcare monitoring systems using advanced human activity recognition (HAR) models have recently gained significant attention. However, they encounter challenges in handling sparse point clouds, achieving real-time continuous classification, and coping with limited monitoring ranges when statically mounted. To overcome these limitations, we propose RobHAR, a movable robot-mounted mmWave radar system with lightweight deep neural networks for real-time monitoring of human activities. Specifically, we first propose a sparse point cloud-based global embedding to learn the features of point clouds using the light-PointNet (LPN) backbone. Then, we learn the temporal pattern with a bidirectional lightweight LSTM model (BiLiLSTM). In addition, we implement a transition optimization strategy, integrating the Hidden Markov Model (HMM) with Connectionist Temporal Classification (CTC) to improve the accuracy and robustness of the continuous HAR. Our experiments on three datasets indicate that our method significantly outperforms the previous studies in both discrete and continuous HAR tasks. Finally, we deploy our system on a movable robot-mounted edge computing platform, achieving flexible healthcare monitoring in real-world scenarios.