Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
Next revisionBoth sides next revision
teaching:gsoc2014 [2014/02/25 13:29] – [Proposed Topics] tenorthteaching:gsoc2014 [2014/02/25 14:04] – [Topic 2: CRAM -- Symbolic Reasoning Tools with Bullet] tenorth
Line 1: Line 1:
 +{{ :teaching:gsoc:gsoc-logo.png?nolink&200| }}
 ====== Google Summer of Code 2014 ====== ====== Google Summer of Code 2014 ======
 ~~NOTOC~~ ~~NOTOC~~
Line 72: Line 73:
 robot's control program.} robot's control program.}
  
 +==== Topic 2: CRAM -- Symbolic Reasoning Tools with Bullet ====
 +{{  :teaching:gsoc:handle_detection_2.png?nolink&200|}}
 +**Main Objective:**Mapping the environment to the internal belief state representation and keeping track of changes in the environment to keep the belief state up to date based on manipulation and interaction tasks performed by the robot.\\  
 +**Task Difficulty:** Relatively simple, when making the existing track changes more robust, and more challenging when introducing new change tracking (like noting the angle of open doors after opening them and storing it in the belief state).\\  
 +**Requirements:** At least basic understanding in functional programming is advisable (ideally Lisp), basic knowledge in ROS helps. Also a good understanding of geometric shapes and coordinate transformations helps.\\
 +**Expected Results:** We expect operational and robust contributions to the software library that can be used as part of a robot's control
 +
 +==== Topic 3: KnowRob -- Reasoning about 3D CAD models of objects ====
 +<html><div style="float:right; margin-left:10px;"><iframe src="//player.vimeo.com/video/83977706" width="300" height="200" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe></div></html>
 +**Main Objective:** Whenever robots interact with objects, they
 +need information about their geometry. While the overall shape is 
 +sufficient for picking up an object, more information about its 
 +composition from parts and their meaning (e.g. a handle or a container)
 +is needed when using objects as tools in more complex activities.
 +We have developed an initial version of a program library that is able 
 +to analyze CAD models of objects, as they can be found in large databases 
 +on the Web, and to automatically identify such functional components.
 +As part of this project, that software library is to be extended in 
 +order to recognized additional geometric primitives (e.g. torus, box)
 +and to improve the segmentation and make it more robust. Alternatively,
 +the focus could be more on improving the analysis infrastructure and
 +integrating it more closely with the robot's control program.\\
 +**Task Difficulty:** The difficulty depends on the exact topic and
 +ranges from rather simple tasks at the infrastructure level to 
 +interesting research problems for the geometric analysis.\\
 +**Requirements:** The algorithms for segmenting 3D meshes require 
 +solid understanding of 3D geometry. Good programming skills in Java
 +are needed for implementing the algorithms and for evaluating their
 +results. Depending on the exact topic, knowledge of machine learning
 +methods or the ability to learn about them could be helpful.\\
 +**Expected Results:** We expect operational and robust contributions
 +to the software library that can be used as part of a robot's control
 +program.
- Impressum - Datenschutz



Prof. Dr. hc. Michael Beetz PhD
Head of Institute

Contact via
Andrea Cowley
assistant to Prof. Beetz
ai-office@cs.uni-bremen.de

Discover our VRB for innovative and interactive research


Memberships and associations:


Social Media: