Robocup@Work Software and Scientific Team Projects
Lecturers
- Christoph Steup
- Sanaz Mostaghim
Time and location
- Time: The first meeting will take place on October 14th 2015 at 15:00 (Note: If you are interested to take this project, you must attend this meeting in which we assign you in groups)
- Location: G29 - 035
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 Howto to start the demo.
All topics will be done in cooperation with the RobOTTO Team and will relate to the RoboCup @Work-Leauge.
Available Topics:
Evaluation of the Alternative Navigation Algorithm Nav2D:
The RobOTTO team currently uses the ROS Nav-Stack with a modified local planner to plan an execute the movement of the robot. We now want to evaluate alternative planners to navigate the robot through the arena. The aim of this project is to integrate the Nav2D planner in an existing demo navigation setup and evaluate its performance against the tasks of the @Work-League. The focus shall be on a running prototype and a parameter evaluation of the planning algorithm.
Evaluation of the Alternative Navigation Algorithm OMPL (Open Motion Planning Library):
The RobOTTO team currently uses the ROS Nav-Stack with a modified local planner to plan an execute the movement of the robot. We now want to evaluate alternative planners to navigate the robot through the arena. The aim of this project is to integrate OMPL (Open Motion Planning Library) in an existing demo navigation setup and evaluate its performance against the tasks of the @Work-League. The focus shall be on a running prototype and a parameter evaluation of the planning algorithm. It is not generally necessary to integrate OMPL with the ROS Nav stack, but it may ease the task of providing map servers and sampling. To this end, the existing alpha OMPL-Planner Plugin may be used.
Simulator for the @Work League:
The current testing of development on the Kuka YouBot of the RoboCup-team is done completely on the robot itself, which has shown to be a serious bottle neck in the development process. Therefore, a simulator using the existing simulation framework VREP shall be constructed and integrated with the existing code base of the RobOTTO Team. TO this end a virtual counterpart of the used robot needs to be created and equipped with an interface mimicing the interface of the real youbot. The work shall focus on the basic platform and the roobotic arm. There are already models and some simulation components, which may be integrated. The choice of components and the design of the simulators extensions are up to the students.
Evaluation of Vision-based Object Recognition
The current object recognition of the team is based on 3D point clouds, which are processed using the Point Cloud Library (PCL). The used sensor is an Intel Real Sense, which uses structured light to construct 3D point clouds out of viewed objects. This task will evaluate the existing object recognition in different scenarios (viewing angles, illuminations and different object configurations). Depending on the outcome of the evaluation solutions for the observed problems shall be searched together with the team and possibly evaluated.
More topics are yet to come. Special topics are available on demand. If students have own ideas we will gladly try to provide appropriate topics.
Slides
Teams
not yet defined