Diploma Thesis DIP-2016-07

BibliographyZielke, Viktor: Design and implementation of Next-Best-View algorithms for automatic robotic-based (dis)assembly tasks.
University of Stuttgart, Faculty of Computer Science, Electrical Engineering, and Information Technology, Diploma Thesis (2016).
75 pages, english.
CR-SchemaI.2.9 (Robotics)
I.2.10 (Vision and Scene Understanding)
Abstract

Robots tasked with the autonomous interaction of objects, such as assembly and disassembly tasks, in a dynamic environment require the ability to explore their environment and detect objects for interactions. State-of-the-art methods exist which can handle these tasks separately. This work describes a method for combining both tasks and therefor reduce the amount of costly operations like motion and sensing. A next-best-view system is developed which incrementally builds a map of the environment and enables the selection of view poses for an eye-in-hand robot system. The system and the performance of the selected view poses is evaluated on a robotic system. The evaluations showed that the method selected view poses which explored the environment and detected objects.

Full text and
other links
PDF (3646324 Bytes)
Department(s)University of Stuttgart, Institute of Parallel and Distributed Systems, Machine Learning und Robotics
Superviser(s)Toussaint, Prof. Marc; Friedrich, Christian
Entry dateJuly 3, 2018
   Publ. Computer Science