Studies

Biomechatronics

Subpixel localization with deep learning

Motivation To improve the absolute accuracy of industrial robot arms computer vision based approaches are applied. The 6D pose of a sample mounted at the robot endeffector has to be estimated very accurately within a large measuring range. The image resolution of conventional cameras is not good eno... Weiterlesen

6DoF pose estimation with deep learning

Motivation To improve the absolute accuracy of robot arms computer vision based approaches are applied. The 6DoF pose of a sample mounted at the robot endeffector has to be estimated. Topics  Deep learning models for 6DoF pose estimation with subpixel accuracy Keypoint detection based on RGB, RGB-D ... Weiterlesen

Visual servoing with deep reinforcement learning

Motivation To improve the absolute accuracy of robot arms visual servoing approaches are applied. The goal is to achieve a high 6DoF pose accuracy of a sample mounted at the robot endeffector. A deep reinforcement learning robot model that uses feedback from visual data in order to compensate motion... Weiterlesen

Image registration for robotics

Motivation To improve the absolute accuracy of robot arms computer vision based approaches are applied. The 6DoF pose of a sample mounted at the robot endeffector has to be estimated very accurately within a large measuring range. Multiple cameras are necessary to achieve these diverging goals. With... Weiterlesen

Absolute accuracy of 6-axis industrial robots

Motivation The goal of this research project in neutron diffractometry is the realization of the automated sample positioning in the focus point of the neutron source with a classical 6-axis industrial robot. To achieve the necessary absolute accuracy of 50 μm, a measuring and control system is deve... Weiterlesen