PhD Thesis

Human movement and action estimation for Robot-Human Collaboration

Work default illustration

Information

  • If you are interested in the proposal, please contact with the supervisors.

Description

In order to perform collaborative tasks involving robots and humans, the robot needs to predict the 3D motion and intentions of the human person. Based on Deep Learning techniques, this thesis proposal seeks to learn from one or several sequences of positions which action the person is going to do and which specific 3D body position will take. The images will be obtained directly from the mobile robots that is interacting with the human or by means of an aerial robot that oversees the whole sequence of operations.

The work is under the scope of the following projects:

  • MdM: Unit of Excellence María de Maeztu (web)