One MSc thesis to be presented on December 19, 2017.
December 19 one MSc thesis will be presented at the Department of Computer Science.
Note to potential opponents: Register as opponent to the presentation by sending an email to the examiner (firstname.lastname@example.org). Do not forget to specify the presentation you register for! Note that the number of opponents may be limited (often to two), so you might be forced to choose another presentation if you register too late. Registrations are individual, just as the oppositions are! More instructions are found on this page.
|PRESENTERS||Alexander Ganslandt, Andreas Svensson|
|TITLE||Optimal 6DOF Object Positioning in Robotics Using the Next Best View|
|EXAMINER||Elin Anna Topp|
|SUPERVISOR||Mathias Haage (LTH)|
This thesis proposes a system for object identification and localization using multiple 3D point clouds, with a hint system that suggest the next best camera view. The system is designed for applications in robotics with a 3D camera mounted on a robot arm, and it has support for finding any arbitrary previously unseen object using only a CAD model. It uses many different point cloud processing tools and data from the robot to achieve this. The system is evaluated using a YuMi robot and a couple of different objects.