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 13:28] – [CRAM -- Robot Plans] tenorthteaching:gsoc2014 [2014/02/25 13:32] – [Topic 3: KnowRob -- Reasoning about 3D CAD models of objects] tenorth
Line 54: Line 54:
  
  
-==== Proposed Topics ====+===== Proposed Topics =====
  
-=== CRAM -- Virtual Robot Scenarios in Gazebo ===+==== CRAM -- Virtual Robot Scenarios in Gazebo ====
 **Main Objective:** The development of scenarios and tasks **Main Objective:** The development of scenarios and tasks
-  for human-sized robots. This is done using ROS, the Gazebo robot +for human-sized robots. This is done using ROS, the Gazebo robot 
-  simulator, and CRAM. The scenarios to develop range from setups for +simulator, and CRAM. The scenarios to develop range from setups for 
-  comparatively simple tasks, such as pick and place, to more sophisticated +comparatively simple tasks, such as pick and place, to more sophisticated 
-  workspaces requiring interaction with the environment, such as opening +workspaces requiring interaction with the environment, such as opening 
-  and closing drawers and doors. +and closing drawers and doors. 
-   +This involves designing virtual environments for Gazebo and/or writing robot plans in Lisp using the CRAM high-level language, sending commands to virtual PR2 or REEM(-C) robots in Gazebo, and manipulating the artificial environment in there. The connection to an elaborate high-level system holds a lot of interesting opportunities. 
-  This involves designing virtual environments for Gazebo and/or writing robot plans in Lisp using the CRAM high-level language, sending commands to virtual PR2 or REEM(-C) robots in Gazebo, and manipulating the artificial environment in there. The connection to an elaborate high-level system holds a lot of interesting opportunities. +The produced code will, when working in a simulated environment, be run on the real robot in our laboratory and become part of the high-level behaviour library for the connected robots.
-   +
-  The produced code will, when working in a simulated environment, be run on the real robot in our laboratory and become part of the high-level behaviour library for the connected robots. +
-   +
-**Task Difficulty:** The difficulty depends on the environment setup and task chosen. The design of pick and place scenarios in a simple environment work towards ensuring the system's robustness, while more elaborate interaction tasks require more situational intelligence in the robot plan. +
- +
-**Requirements:** At least basic understanding in functional programming is advisable (ideally Lisp), basic knowledge in ROS helps, and ideally already having experience in simulation environments.+
  
 +**Task Difficulty:** The difficulty depends on the environment setup and task chosen. The design of pick and place scenarios in a simple environment work towards ensuring the system's robustness, while more elaborate interaction tasks require more situational intelligence in the robot plan.\\
 +**Requirements:** At least basic understanding in functional programming is advisable (ideally Lisp), basic knowledge in ROS helps, and ideally already having experience in simulation environments.\\
 **Expected Results:** We expect operational and robust **Expected Results:** We expect operational and robust
-  contributions to the software library that can be used as part of a +contributions to the software library that can be used as part of a 
-  robot's control program.}+robot's control program.} 
 + 
 +==== Topic 2: CRAM -- Symbolic Reasoning Tools with Bullet ==== 
 + 
 +**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 ====
 +**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: