Differences
This shows you the differences between two versions of the page.
Both sides previous revisionPrevious revisionNext revision | Previous revisionNext revisionBoth sides next revision | ||
jobs [2014/02/18 17:01] – tenorth | jobs [2015/10/15 09:22] – [Theses and Jobs] froggy86 | ||
---|---|---|---|
Line 3: | Line 3: | ||
If you are looking for a bachelor/ | If you are looking for a bachelor/ | ||
- | ====Theses==== | ||
- | == Web-based knowledge visualizations (BA/HiWi) == | ||
- | {{ :research:knowledge-visualization.png?200}} | + | == Kitchen Activity Games in a Realistic Robotic Simulator (BA/ |
+ | {{ :research:gz_env1.png?200|}} | ||
- | The knowledge base visualization allows to display semantic environment maps, | + | Developing new activities |
- | objects, human poses, trajectories | + | |
- | robot' | + | |
- | is written in Java and has grown old over the years. Recently, there has been | + | |
- | much progress in creating | + | |
- | 3D visualizations]] for ROS that can also be accessed with a | + | |
- | [[http:// | + | |
- | a web-based version of the visualization using these techniques. | + | |
Requirements: | Requirements: | ||
- | * Good programming skills | + | * Good programming skills |
- | * Experience with JavaScript development | + | * Basic physics/ |
- | * Knowledge of Web technologies (HTML, XML, OWL) | + | * Gazebo simulator basic tutorials |
- | Contact: [[team:moritz_tenorth|Moritz Tenorth]] | + | Contact: [[team:andrei_haidu|Andrei Haidu]] |
+ | == Integrating Eye Tracking in the Kitchen Activity Games (BA/MA)== | ||
+ | {{ : | ||
- | == Statistical relational models of human activities (MA) == | + | Integrating the eye tracker in the [[http://gazebosim.org/|Gazebo]] based Kitchen Activity Games framework and logging |
- | + | ||
- | As part of the [[http://cogwatch.eu|CogWatch EU project]], we are working on | + | |
- | the analysis | + | |
- | these patients lack important motor coordination skills that result in various | + | |
- | kinds of errors in performing everyday | + | |
- | extensive patient trials, the student is to learn statistical relational | + | |
- | models that characterize which errors are made in which circumstances. | + | |
Requirements: | Requirements: | ||
- | * Good knowledge of machine learning (Bayesian networks, statistical relational models) | + | * Good programming skills in C/C++ |
- | * Programming skills (Java) | + | * Gazebo simulator basic tutorials |
- | Contact: [[team:moritz_tenorth|Moritz Tenorth]] | + | Contact: [[team:andrei_haidu|Andrei Haidu]] |
+ | == Hand Skeleton Tracking Using Two Leap Motion Devices (BA/MA)== | ||
+ | {{ : | ||
- | == Tools for knowledge acquisition from the Web (BA/MA/HiWi) == | + | Improving |
- | There are several options | + | The tracked hand can then be used as input for the Kitchen Activity Games framework. |
- | knowledge from Web sources like online shops, repositories of object models, | + | |
- | recipe databases, etc. | + | |
Requirements: | Requirements: | ||
- | * Programing | + | * Good programming |
- | * Experience with Web languages and datamining techniques is helpful | + | |
- | * Depending on the focus of the project, experience with database technology, natural-language processing or computer vision may be helpful | + | |
- | Contact: [[team:moritz_tenorth|Moritz Tenorth]] | + | Contact: [[team:andrei_haidu|Andrei Haidu]] |
+ | == Fluid Simulation in Gazebo (BA/MA)== | ||
+ | {{ : | ||
- | == GPU-based Parallelization of Numerical Optimization Techniques (BA/MA/HiWi)== | + | [[http://gazebosim.org/ |
- | In the field of Machine Learning, numerical optimization techniques play a focal role. However, as models grow larger, traditional implementations | + | Currently there is an [[http:// |
- | Requirements: | + | The computational method for the fluid simulation is SPH (Smoothed-particle Dynamics), however newer and better methods based on SPH are currently present |
- | * Skills in numerical optimization algorithms | + | and should be implemented (PCISPH/IISPH). |
- | * Good programming skills in Python | + | |
- | Contact: [[team: | + | The interaction between the fluid and the rigid objects is a naive one, the forces and torques are applied only from the particle collisions (not taking into account pressure and other forces). |
- | == Online Learning | + | Another topic would be the visualization |
- | Markov Logic Networks (MLNs) combine the expressive power of first-order logic and probabilistic graphical models. In the past, they have been successfully applied to the problem | + | Here is a [[https:// |
Requirements: | Requirements: | ||
- | * Experience | + | * Good programming skills |
- | * Experience with statistical relational learning (e.g. MLNs) is helpful. | + | * Interest in Fluid simulation |
- | * Good programming skills in Python. | + | * Basic physics/ |
+ | * Gazebo simulator and Fluidix basic tutorials | ||
- | Contact: [[team:daniel_nyga|Daniel Nyga]] | + | Contact: [[team:andrei_haidu|Andrei Haidu]] |
- | < | + | == Automated sensor calibration toolkit (BA/MA)== |
- | ====Open Positions==== | + | |
- | ==HiWi-Position: | + | |
- | In the context | + | Computer vision is an important part of autonomous robots. For robots the image sensors are the main source of information |
- | are investigating methods for combining multimodal sources of knowledge (e.g. video, natural-language recipes or computer | + | |
- | The Institute | + | The topic for this thesis |
- | development and the integration of probabilistic methods in AI, which enable intelligent robots to understand, interpret and execute natural-language instructions from recipes from the World Wide Web. | + | |
- | This HiWi-Position can serve as a starting point for future Bachelor' | + | {{ : |
+ | The system should: | ||
+ | * be independent of the camera type | ||
+ | * estimate intrinsic and extrinsic parameters | ||
+ | * calibrate depth images (case of RGB-D) | ||
+ | * integrate capabilities from Halcon [1] | ||
+ | * operate autonomously | ||
- | Tasks: | + | Requirements: |
- | * Implementation of an interface to the Robot Operating System (ROS). | + | * Good programming skills in Python and C/C++ |
- | * Linkage of the knowledge base to the executive of the robot. | + | * ROS, OpenCV |
- | * Support for the scientific staff in extending and integrating components onto the robot platform PR2. | + | |
- | Requirements: | + | [1] http:// |
- | * Studies in Computer Science (Bachelor' | + | |
- | * Basic skills in Artificial Intelligence | + | |
- | * Optional: basic skills in Probability Theory | + | |
- | * Optional: basic skills in Machine Learning | + | |
- | * Good programming skills in Python and Java | + | |
- | Hours: 10-20 h/week | + | Contact: [[team: |
- | Contact: [[team: | + | == On-the-fly 3D CAD model creation (MA)== |
- | [1] www.robohow.eu\\ | + | Create models during runtime for unknown textured objets based on depth and color information. Track the object and update the model with more detailed information, |
- | [2] http://www.youtube.com/ | + | |
- | == HiWi position: Segmentation and interpretation of 3D object models (HiWi/MA) == | + | Requirements: |
+ | * Good programming skills in C/C++ | ||
+ | * strong background in computer vision | ||
+ | * ROS, OpenCV, PCL | ||
- | {{ :research:cup2-segmented.png? | + | Contact: [[team:thiemo_wiedemeyer|Thiemo Wiedemeyer]] |
- | Competent object interaction requires knowledge about the structure and | + | == Simulation |
- | composition | + | |
- | how part-based object models can automatically be extracted from CAD models | + | |
- | found on the Web, e.g. on the [[http:// | + | |
- | We are looking for a student research assistant | + | Create |
- | In close collaboration with the researchers of the Institute for Artificial | + | |
- | Intelligence, the student will work on extending the software for mesh | + | |
- | segmentation, | + | |
- | methods into the robot' | + | |
- | the segmentation results. Depending on the results, cooperation on joint | + | |
- | publications may be possible. | + | |
- | This HiWi position can serve as a starting point for future Bachelor' | + | Requirements: |
- | Master' | + | * Good programming skills in C/C++ |
- | project that could be worked on as a Master' | + | * strong background in computer vision |
+ | * Gazebo, OpenCV, PCL | ||
- | Requirements: | + | Contact: [[team: |
- | * Good Java programming skills | + | |
- | * Basic knowledge of 3D geometry calculations | + | == Multi-expert segmentation of cluttered and occluded scenes == |
- | * Experience with working with 3D models | + | |
+ | Objects in a human environment are usually found in challenging scenes. They can be stacked upon eachother, touching or occluding, can be found in drawers, cupboards, refrigerators and so on. A personal robot assistant in order to execute a task, needs to detect these objects and recognize them. In this thesis a multi-modal approach to interpreting cluttered scenes is going to be investigated, | ||
+ | |||
+ | Requirements: | ||
+ | * Good programming skills | ||
+ | * strong background in 3D vision | ||
+ | * basic knowledge of ROS, OpenCV, PCL | ||
+ | |||
+ | Contact: [[team: | ||
+ | |||
+ | == Robot control systems in underwater robotics == | ||
+ | |||
+ | The use of robots in underwater missions shows a challenging task. The dynamic terrain and its different conditions makes it difficult for robots to perform tasks correctly. In order to accomplish tasks in a proper way, the robot control routines have to be coordinated. The topic of this thesis | ||
- | Contact: [[team: | + | Requirements: |
+ | * Good programming skills in C/C++ or JAVA | ||
+ | * basic knowledge of ROS, OpenCV | ||
+ | Contact: [[team: |
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: