direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

Learning to Manipulate Articulated Objects From Human Demonstration

MSc. thesis


Robots operating in everyday human environments require interacting with articulated objects, such as locks and drawers. These articulated objects are usually specifically designed for humans to be easily used. To this end, the function of many objects is encoded in their kinematic structure. For example, there are over 1000 types of scissors with distinct appearances and sizes, but the type of their kinematic models remains the same. This enables humans to transfer experience between objects of the same type. This insight can be leveraged by learning robot manipulation skills from human demonstrations. Using kinematic models of objects as the underlying representation for Learning from Demonstration, we can impart similar transfer abilities to robots, which can be shown in this video: www.youtube.com/watch.

Description of Work

In this thesis, you will develop a probabilistic framework for extracting the kinematic structures from a human demonstration on an articulated object. In particular, this probabilistic framework allows the robot to extract candidate models (e.g., prismatic or revolute joints) with uncertainty. This information will then feed into the robot to generate explorative action to verify and distinguish these candidate models. 

For this project you need good C++/Python programming skills. Experience with probabilistic model learning is a plus.


Xing Li
Oliver Brock

Zusatzinformationen / Extras


Schnellnavigation zur Seite über Nummerneingabe