MASTER´S THESIS: Deep Learning Robotic Grasp

In many applications it would be an advantage if we could make a robot system that is able to grasp arbitrary objects, without first having to teach it how to grasp that particular object type. Thus, the system should be able to  grasp objects it has never seen before.

Several attempts to do this have been made, for example GraspNet from Nvidia that uses a 2.5D image data, e.g., from a stereo camera to control a robot arm.

 The task of this Master Theses is to survey the literature in this field and evaluate/implement one or several methods for industrial robot picking applications.

Prerequisites:

• Computer Vision knowledge
• Machine Learning knowledge
• Programming skills

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).