University of Twente Student Theses


Pose estimation and motion set-point generation for robotics

Schooten, N.E.W. van (2015) Pose estimation and motion set-point generation for robotics.

[img] PDF
Abstract:Through developments in different disciplines, robotic applications become more autonomous. For the Bobbie robot, this development takes shape in the task of autonomously manipulating objects with the Philips Robotic Arm (PRA). For this task it is required that the controller of the PRA receives an input for the pose of the end-effector. The input is generated with the motion set-point generator. The end-effector of the robotic arm is guided in an appropriate manner to the desired destinations. A design and implementation of the motion set-point generator are presented. In the application of autonomous care robotics pose estimation is an essential task for the manipulation of objects. For the manipulation of objects, object recognition is required and the estimation of the pose of objects. Linemod is a template matching method with which objects can be recognized. Experiments were performed to verify if the method of Linemod is suited for the application of pose estimation for autonomous care robotics. It is concluded that it is plausible that pose estimation of objects can be performed by Linemod.
Item Type:Essay (Master)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Programme:Electrical Engineering MSc (60353)
Link to this item:
Export this item as:BibTeX
HTML Citation
Reference Manager


Repository Staff Only: item control page