MASTER´S THESIS: Robot and Human Pose Estimation with Deep Learning

Finding the pose of a human within an image has a multitude of applications, such as human-machine interaction (gesture recognition, gaming), action recognition, positioning. An important application field for SICK is collaborative robotics where humans and robots can work next to each other. From a safety perspective it is of interest to map the human and robot positions in order to avoid collisions and injuries.

The task in this Master’s Thesis is to investigate a Deep Learning-based system that jointly finds the pose of a human and a robot arm in an image for this purpose.

 Problems to address include:

• Automatic collection of ground truth data for the robot arm pose detection
• Evaluation of Deep Learning architectures
• Evaluation of system performance

Contact:

For more information, contact R&D manager Ola Friman (ola.friman@sick.se) and apply below at "ANSÖKAN"  before  the 19th of October. Please notice: Application must include CV, Cover letter and LADOK (study results including courses)