Quantitative Measurement of Parkinson’s Disease Gait Based on the Rehabilitation Monitoring Robot

Abstract

This article presents a gait monitoring method for the home-based rehabilitation of Parkinson’s disease using a following robot. We use robot-based 2-D light detection and ranging (LiDAR) to collect environmental point clouds. The point clouds of the monitored person’s legs are identified from the static environment by an intersection of union (IOU) matching algorithm and the legs are continuously tracked with the Kalman filter (KF). The spatiotemporal information of gait is subsequently determined by legs segmentation. During this process, the robot follows behind the person along the trajectory just walked by the person, ensuring that both legs are always in the robot’s view. For Parkinson’s abnormal gait during rehabilitation, we propose a quantitative indicator to assess the patient’s recovery status. The experimental results demonstrate that the proposed method can effectively monitor and score the abnormality of Parkinson’s gait. In terms of gait detection, it achieves an F1 detection score of 0.983 and a root mean square error (RMSE) within 0.050 m while significantly extending the monitoring radius to 10 m of the room. This makes the method practical for home rehabilitation applications.