Team Projects - RoboCup@Work - robOTTO
Lecturer:
- Christoph Steup
Language:
The course will be held in English or German as requested by the participating students.
Participants:
All students of bachelor and master curriculums of the faculty are eligable to visit the course. However it is beneficial if students are familiar with at least one of the following topics:
- Robotics
- Programming in C++
- Image Processing
- Neural Networks
- OpenCV
- Navigation and Path Planning
- Task Generation and Optimization
- Robot Operating System (ROS)
First Meeting:
The first meeting will be used to organize the project. We will describe the available tasks, the used system and group the interested students. The individual projects will be announced on the 17th October at 13:00 in G29-035. There will be a second meeting at the 23th October. If you want to participate, one of the two meetings is mandatory.
Organization:
The course will be taken in groups of 3-4 Students per topic. The students and the groups will be chosen by us depending on your background. The individual topics are not fully fixed, extensions and modifications are possible depending on the skills and interest of participating students. This will be discussed in the first meeting. The result of each project is a working demonstration with commented source code and a written documentation indicating the general concept and a How to to start the demo.
Hardware:
You will work on the robOTTO youbot used for the RoboCup@Work competition. This robot consists of a holonomic base with omni-wheels and a single 5-axis manipulator. The sensory equipment consists of Lidars and cameras. More info is available at the robOTTO webpage.
Available Topics:
Integration of the RoboCup@Work arena description in the MoveIT manipulator control software
- Arena Elements like Shelfs are complex to integrate with manipulation
- Used manipulator control software MoveIT enables planning of complex manipulation tasks
- Integration of Arena Description into MoveIt is necessary
- Creation of Planning Scene
- Evaluation of planned manipulation trajectories
Design and Implementation of a new Referee Box to enable automatic task generation and performance evaluation of robots
- Referee Box is central task generation and visualization hub of the competition
- Current Referee Box is difficult to maintain and does not provide visualization
- Design of new Referee Box software based on ROS is necessary to enable Visitors to understand the current Task
- Task generation is very complex, a new Task description Framework is necessary
- Native ROS task delivery will enable new teams to enter the comppetition more quickly