TFG

User posture recognition for robot-assisted shoe dressing task

Work default illustration

Information

  • Started: 03/02/2017
  • Finished: 05/07/2017

Description

The goal of this project is to develop a user-tracking algorithm for a robot assistant in dressing, which is capable of recognizing the presence of the user and the user's body posture during the dressing task. The body posture can give insight into the user's state and intended actions, which will allow more natural human-robot interaction.

The system will consist of a Barrett WAM robot manipulator and a Microsoft Kinect camera. The algorithm will use as input the depth images from the camera to perform user tracking, and it will be implemented using the Robot Operating System (ROS), which has become a standard framework for robotics developments in recent years. Development and testing will be performed in the laboratory environment.

The work is under the scope of the following projects:

  • I-DRESS: Assistive interactive robotic system for support in dressing (web)