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 [2014/08/29 09:33] – [Theses and Jobs] ahaidu | jobs [2016/03/03 07:58] – [Theses and Jobs] ahaidu | ||
---|---|---|---|
Line 3: | Line 3: | ||
If you are looking for a bachelor/ | If you are looking for a bachelor/ | ||
+ | == Lisp / CRAM support assistant (HiWi) == | ||
+ | Technical support for the group for Lisp and the CRAM framework. \\ | ||
+ | 5 hours per week for up to 1 year (paid). | ||
- | == GPU-based Parallelization of Numerical Optimization Techniques (BA/ | + | Requirements: |
+ | * Good programming skills in Common Lisp | ||
+ | * Basic ROS knowledge | ||
- | In the field of Machine Learning, numerical optimization techniques play a focal role. However, as models grow larger, traditional implementations on single-core CPUs suffer from sequential execution causing a severe slow-down. In this thesis, state-of-the-art GPU frameworks (e.g. CUDA) are to be investigated in order implement numerical optimizers that substantially profit from parallel execution. | + | The student will be introduced to the CRAM framework at the beginning |
- | Requirements: | + | Contact: [[team: |
- | * Skills in numerical optimization algorithms | + | |
- | * Good programming skills in Python and C/C++ | + | |
- | Contact: [[team: | ||
- | == Online Learning of Markov Logic Networks for Natural-Language Understanding | + | == Integrating PR2 in the Unreal Game Engine Framework |
+ | {{ : | ||
- | Markov Logic Networks (MLNs) combine | + | Integrating |
Requirements: | Requirements: | ||
- | * Experience | + | * Good programming skills |
- | * Experience with statistical relational learning (e.g. MLNs) is helpful. | + | * Basic physics/ |
- | * Good programming skills in Python. | + | * Basic ROS knowledge |
+ | * UE4 basic tutorials | ||
- | Contact: [[team:daniel_nyga|Daniel Nyga]] | + | Contact: [[team:andrei_haidu|Andrei Haidu]] |
- | ==HiWi-Position: | + | == Realistic Grasping using Unreal Engine (BA/ |
- | In the context of the European research project RoboHow.Cog [1,2] we | + | {{ : |
- | are investigating methods for combining multimodal sources of knowledge (e.g. video, natural-language recipes or computer games), in order to enable mobile robots to autonomously acquire new high level skills like cooking meals or straightening up rooms. | + | |
- | The Institute for Artificial Intelligence | + | The objective of the project |
- | development and the integration of probabilistic methods | + | ious human-like grasping approaches |
- | This HiWi-Position can serve as a starting point for future Bachelor' | + | The game consist of a household environment where a user has to execute various given tasks, such as cooking |
- | Tasks: | + | In order to improve the ease of manipulating objects the user should |
- | * Implementation | + | be able to switch during runtime |
- | * Linkage of the knowledge | + | grasp, precision grip etc.) he/she would like to use. |
- | * Support for the scientific staff in extending and integrating components onto the robot platform PR2. | + | |
+ | Requirements: | ||
+ | * Good programming skills in C++ | ||
+ | * Good knowledge of the Unreal Engine API. | ||
+ | * Experience with skeletal control / animations / 3D models | ||
- | Requirements: | ||
- | * 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/andrei_haidu|Andrei Haidu]] |
- | Contact: [[team:daniel_nyga|Daniel Nyga]] | + | == Kitchen Activity Games in a Realistic Robotic Simulator (BA/MA)== |
+ | | ||
- | [1] www.robohow.eu\\ | + | Developing new activities and improving the current simulation framework done under the [[http://gazebosim.org/ |
- | [2] http://www.youtube.com/ | + | |
+ | Requirements: | ||
+ | * Good programming skills in C/C++ | ||
+ | * Basic physics/ | ||
+ | * Gazebo simulator basic tutorials | ||
- | == Depth-Adaptive Superpixels (BA/MA)== | + | Contact: [[team:andrei_haidu|Andrei Haidu]] |
- | | + | |
- | We are currently investigating a new set of sensors (RGB-D-T), which is a combination of a kinect with a thermal image camera. Within this project we want to enhance the Depth-Adaptive Superpixels (DASP) to make use of the thermal sensor data. Depth-Adaptive Superpixels oversegment an image taking into account the depth value of each pixel. | + | |
- | Since the current implementation of DASP is not very performant for high resolution images, there are several options for doing a project in this field like reimplementing DASP using CUDA, investigating how thermal data can be integrated, ... | ||
- | Requirements: | ||
- | * Basic knowledge of image processing | ||
- | * Good programming skills in C/C++. | ||
- | * Experience with CUDA is helpful | ||
- | Contact: [[team: | ||
+ | == Automated sensor calibration toolkit (BA/MA)== | ||
- | == Physical Simulation | + | Computer vision is an important part of autonomous robots. For robots the image sensors are the main source of information of the surrounding world. Each camera is different, even if they are from the same production line. For computer vision, especially for robots manipulating their environment, |
- | {{ : | + | |
- | For tracking people, the use of particle filters is a common approach. However, the quality of those filters heavily depends on the way particles are spread. In this thesis, | + | The topic for this thesis |
- | Requirements: | + | {{ : |
- | * Good programming skills in C/C++ | + | The system should: |
- | * Optional: Experience in working with physics libraries such as Bullet | + | * 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 | ||
- | Contact: [[team: | + | Requirements: |
+ | * Good programming skills in Python and C/C++ | ||
+ | * ROS, OpenCV | ||
- | == Kitchen Activity Games in a Realistic Robotic Simulator | + | [1] http:// |
- | {{ : | + | |
+ | Contact: [[team: | ||
+ | |||
+ | == On-the-fly 3D CAD model creation | ||
- | Developing new activities | + | Create models during runtime for unknown textured objets based on depth and color information. Track the object and update |
- | Requirements: | + | Requirements: |
* Good programming skills in C/C++ | * Good programming skills in C/C++ | ||
- | * Basic physics/ | + | * strong background in computer vision |
- | * Gazebo simulator basic tutorials | + | * ROS, OpenCV, PCL |
- | Contact: [[team:andrei_haidu|Andrei Haidu]] | + | Contact: [[team:thiemo_wiedemeyer|Thiemo Wiedemeyer]] |
- | == Integrating Eye Tracking in the Kitchen Activity Games (BA/MA)== | + | == Simulation of a robots belief state to support perception(MA) == |
- | {{ : | + | |
- | Integrating | + | Create a simulation environment that represents |
- | and logging the gaze of the user during the gameplay. From the information typical activities should be inferred. | + | |
- | Requirements: | + | Requirements: |
* Good programming skills in C/C++ | * Good programming skills in C/C++ | ||
- | * Gazebo | + | |
+ | | ||
- | Contact: [[team:andrei_haidu|Andrei Haidu]] | + | Contact: [[team:ferenc_balint-benczedi|Ferenc Balint-Benczedi]] |
- | == Hand Skeleton Tracking Using Two Leap Motion Devices (BA/MA)== | + | == Multi-expert segmentation of cluttered and occluded scenes |
- | {{ : | + | |
- | Improving the skeletal tracking offered by the Leap Motion SDK, by using two devices (one tracking vertically the other horizontally) | + | 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 |
- | The tracked hand can then be used as input for the Kitchen Activity Games framework. | + | Requirements: |
- | + | ||
- | Requirements: | + | |
* Good programming skills in C/C++ | * Good programming skills in C/C++ | ||
+ | * strong background in 3D vision | ||
+ | * basic knowledge of ROS, OpenCV, PCL | ||
+ | |||
+ | Contact: [[team: | ||
+ | |||
- | 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: