Skeleton Timed Up and Go on MARIO Robot

摘要

Current robotic technology shows promise in improving medical monitoring routines. In this work, we present an example of automatic monitoring and analysis of human gait in the Timed Up and Go test, using the Microsoft Kinect 2 sensor. The approach was implemented in the mobile robot developed during the MARIO (Managing active and healthy Aging with use of caRing servIce rObots) project, with the aim to assess the risk of falling through daily measurements of temporal and spatial gait parameters. Thanks to the robot's capability to approach the user in an unstructured environment, the mobility measurements can be obtained passively, in normal daily activity, without any patient's instruction. We describe the technique used to extract gait parameters from the Kinect 2 data and present some of the performance results.