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
jobs [2015/03/23 13:18] – raiderjobs [2019/04/05 10:24] – [Theses and Student Jobs] haidu
Line 1: Line 1:
 ~~NOTOC~~ ~~NOTOC~~
-=====Theses and Jobs===== 
-If you are looking for a bachelor/master thesis or a job as a student research assistant, you may find some interesting opportunities on this page. 
  
 +=====Open researcher positions=====
  
 +=====Theses and Student Jobs=====
 +If you are looking for a bachelor/master thesis or a job as a student research assistant, you may find some interesting opportunities on this page.
  
-== GPU-based Parallelization of Numerical Optimization Techniques (BA/MA/HiWi)==+== Knowledge-enabled PID Controller for 3D Hand Movements in Virtual Environments (BA/MA Thesis)==
  
-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.+Implementing a force-, velocity- and impulse-based PID controller for precise and responsive hand movements in a virtual environment. The virtual environment used in Unreal Engine in combination with Virtual Reality devices. The movements 
 +of the human user will be mapped to the virtual hands, and controlled via the implemented PID controllers. 
 +The controller should be able to dynamically tune itself depending on the executed actions (opening/closing a drawer or lifting a heavy object) in combination with the physical limitations of the physics engine (dynamic update rates).
  
 Requirements: Requirements:
-  * Skills in numerical optimization algorithms +  * Good C++ programming skills 
-  * Good programming skills in Python and C/C+++  * Familiar with PID controllers 
 +  * Experience with simulators/game engines is recommended 
 +  * Experience with Unreal Engine 
 + 
 +Contact: [[team:andrei_haidu|Andrei Haidu]]
  
-Contact: [[team:daniel_nyga|Daniel Nyga]] 
  
-== Online Learning of Markov Logic Networks for Natural-Language Understanding (MA)==+<html><!-- 
 +== Lisp / CRAM support assistant (HiWi) ==
  
-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 of semantically interpreting and completing natural-language instructions from the web. State-of-the-art learning techniques mostly operate in batch mode, i.e. all training instances need to be known in the beginning of the learning process. In context of this thesis, online learning methods for MLNs are to be investigated, which allow incremental learning, when new examples come in one-by-one.+Technical support for the group for Lisp and the CRAM framework. \\ 
 +8+ hours per week for up to 1 year (paid).
  
 Requirements: Requirements:
-  * Experience in Machine Learning. +  * Good programming skills in Common Lisp 
-  * Experience with statistical relational learning (e.g. MLNs) is helpful. +  * Basic ROS knowledge
-  * Good programming skills in Python.+
  
-Contact: [[team:daniel_nyga|Daniel Nyga]]+The student will be introduced to the CRAM framework at the beginning of the job, which is a robot programming framework written in Lisp. The student will then be responsible for assisting not familiar with the framework people, explaining them the parts they don't understand and pointing them to the relevant documentation sources.
  
 +Contact: [[team:gayane_kazhoyan|Gayane Kazhoyan]]
 +--></html>
 +== Mesh Editing / Mesh Segmentation/Cutting (Student Job / HiWi)==
 + {{ :research:human_hand_cutting.png?150|}}
  
-==HiWi-Position: Knowledge Representation & Language Understanding for Intelligent Robots== + Editing and cutting a human mesh into different parts in Blender / Maya (or other).
- +
-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 is hiring a student researcher for the +
-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's, Master's or Diploma Theses. +
- +
-Tasks: +
-  * Implementation of an interface to the Robot Operating System (ROS). +
-  * Linkage of the knowledge base to the executive of the robot. +
-  * Support for the scientific staff in extending and integrating components onto the robot platform PR2.+
  
 Requirements: Requirements:
-  * Studies in Computer Science (Bachelor's, Master's or Diploma) +  * Good knowledge in 3D Modeling 
-  * Basic skills in Artificial Intelligence +  * Familiar with Blender / Maya (or other)
-  * 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/mona_abdel-keream|Mona Abdel-Keream]]
  
-Contact: [[team:daniel_nyga|Daniel Nyga]]+== 3D Model / Material / Lightning Developer (Student Job / HiWi)== 
 + {{ :research:kitchen_unreal.jpg?200|}} 
  
-[1] www.robohow.eu\\ +Developing and improving existing 3D models in Blender / Maya (or other). Importing the models in Unreal Engine, where the Materials and Lightning should be improved to be close as possible to realism. 
-[2] http://www.youtube.com/watch?v=0eIryyzlRwA+
  
 +Bonus: Working with state of the art 3D Scanners [[https://www.goscan3d.com/|Go!SCAN]] for creating new realistic models.
  
-== Kitchen Activity Games in a Realistic Robotic Simulator (BA/MA/HiWi)== +Requirements: 
- {{ :research:gz_env1.png?200|}} +  * Experience with Blender / Maya (or other) 
 +  * Knowledge of Unreal Engine material / lightning development
  
-Developing new activities and improving the current simulation framework done under the [[http://gazebosim.org/|Gazebo]] robotic simulator. Creating a custom GUI for the game, in order to launch new scenarios, save logs etc. 
  
-Requirements: 
-  * Good programming skills in C/C++ 
-  * Basic physics/rendering engine knowledge 
-  * Gazebo simulator basic tutorials 
  
 Contact: [[team:andrei_haidu|Andrei Haidu]] Contact: [[team:andrei_haidu|Andrei Haidu]]
  
-== Integrating Eye Tracking in the Kitchen Activity Games (BA/MA)== +<html><!-- 
- {{ :research:eye_tracker.png?200|}} +== Integrating PR2 in the Unreal Game Engine Framework (BA/MA/HiWi)== 
 + {{ :research:unreal_ros_pr2.png?100|}} 
  
-Integrating the eye tracker in the [[http://gazebosim.org/|Gazebo]] based Kitchen Activity Games framework and logging the gaze of the user during the gameplay. From the information typical activities should be inferred.+Integrating the [[https://www.willowgarage.com/pages/pr2/overview|PR2]] robot with [[http://www.ros.org/|ROS]] support in the [[https://www.unrealengine.com|Unreal Engine 4]] Framework.
  
 Requirements: Requirements:
   * Good programming skills in C/C++   * Good programming skills in C/C++
-  * Gazebo simulator basic tutorials+  * Basic physics/rendering engine knowledge 
 +  * Basic ROS knowledge 
 +  * UE4 basic tutorials
  
 Contact: [[team:andrei_haidu|Andrei Haidu]] Contact: [[team:andrei_haidu|Andrei Haidu]]
  
-== Hand Skeleton Tracking Using Two Leap Motion Devices (BA/MA)== 
- {{ :research:leap_motion.jpg?200|}}  
  
-Improving the skeletal tracking offered by the [[https://developer.leapmotion.com/|Leap Motion SDK]], by using two devices (one tracking vertically the other horizontally) and switching between them to the one that has the best current view of the hand.+== Realistic Grasping using Unreal Engine (BA/MA/HiWi) ==
  
-The tracked hand can then be used as input for the Kitchen Activity Games framework.+{{  :teaching:gsoc:topic2_unreal.png?nolink&150|}}
  
-Requirements: +The objective of the project is to implement var- 
-  * Good programming skills in C/C+++ious human-like grasping approaches in a game developed using [[https://www.unrealengine.com/|Unreal Engine]]. 
  
-Contact: [[team:andrei_haidu|Andrei Haidu]]+The game consist of a household environment where a user has to execute various given tasks, such as cooking a dish, setting the table, cleaning the dishes etc. The interaction is done using various sensors to map the users hands onto the virtual hands in the game.
  
-== Fluid Simulation in Gazebo (BA/MA)== +In order to improve the ease of manipulating objects the user should 
- {{ :research:fluid.png?200|}} +be able to switch during runtime the type of grasp (pinch, power 
 +grasp, precision grip etc.) he/she would like to use. 
 +   
 +Requirements:  
 +  * Good programming skills in C++ 
 +  * Good knowledge of the Unreal Engine API.  
 +  * Experience with skeletal control / animations / 3D models in Unreal Engine.
  
-[[http://gazebosim.org/|Gazebo]] currently only supports rigid body physics engines (ODE, Bullet etc.), however in some cases fluids are preferred in order to simulate as realistically as possible the given environment. 
  
-Currently there is an [[http://gazebosim.org/tutorials?tut=fluids&cat=physics|experimental version]] of fluids  in Gazebo, using the [[http://onezero.ca/fluidix/|Fluidix]] library to run the fluids computation on the GPU.+Contact: [[team/andrei_haidu|Andrei Haidu]] 
 +--></html>
  
-The computational method for the fluid simulation is SPH (Smoothed-particle Dynamics), however newer and better methods based on SPH are currently present 
-and should be implemented (PCISPH/IISPH). 
  
-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).+== Unreal Engine Editor Developer (Student Job / HiWi)== 
 + {{ :research:unreal_editor.png?150|}} 
  
-Another topic would be the visualization of the fluid, currently is done by rendering every particle. For the rendering engine [[http://www.ogre3d.org/|OGRE]] is used.+Creating new user interfaces (panel customization) for various internal plugins using the Unreal C++ framework [[https://docs.unrealengine.com/latest/INT/Programming/Slate/|SLATE]].
  
-Here is a [[https://vimeo.com/104629835|video]] example of the current state of the fluid in Gazebo.  
  
 Requirements: Requirements:
-  * Good programming skills in C/C++ +  * Good C++ programming skills 
-  * Interest in Fluid simulation +  * Familiar with the [[https://docs.unrealengine.com/latest/INT/Programming/Slate/|SLATE]] framework 
-  * Basic physics/rendering engine knowledge +  * Familiar with Unreal Engine API
-  * Gazebo simulator and Fluidix basic tutorials+
  
 Contact: [[team:andrei_haidu|Andrei Haidu]] Contact: [[team:andrei_haidu|Andrei Haidu]]
  
  
-== Automated sensor calibration toolkit (BA/MA)== 
  
-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, it is important that the parameters for the cameras in use are well known. The calibration of a camera is a time consuming task, and the result depends highly on the chosen setup and the accuracy of the operator.+== OpenEASE rendering in Unreal Engine (BA/MA Thesis, Student Job / HiWi)==
  
-The topic for this thesis is to develop an automated system for calibrating cameras, especially RGB-D cameras like the Kinect v2. 
  
- {{ :kinect2_calibration_setup_small.jpg?200|}} +Implmenting the rendering of the [[https://data.open-ease.org/|OpenEASE]] knowledge base visualization in Unreal Engine. This will have to be packaged as a HTML5 executable and inserted into the website.
-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+
  
-Requirements:  +Requirements: 
-  * Good programming skills in Python and C/C++ +  * Good C++ programming skills 
-  * ROS, OpenCV+  * Familiar with Unreal Engine API 
 +  * Familiar with HTML5 and JavaScript 
 +  * Familiar with the [[https://docs.unrealengine.com/latest/INT/Programming/Slate/|SLATE]] framework 
 +  * Familiar with basic ROS communication
  
-[1] http://www.halcon.de/ +Contact: [[team:andrei_haidu|Andrei Haidu]]
- +
-Contact: [[team:alexis_maldonado|Alexis Maldonado]] and [[team:thiemo_wiedemeyer|Thiemo Wiedemeyer]] +
- +
-== On-the-fly 3D CAD model creation (MA)== +
- +
-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, completing it's 3D model from multiple views improving redetection. Using the robots manipulator pick up the object and complete the model by viewing it from multiple viewpoints. +
- +
-Requirements:  +
-  * Good programming skills in C/C++ +
-  * strong background in computer vision  +
-  * ROS, OpenCV, PCL +
- +
-Contact: [[team:thiemo_wiedemeyer|Thiemo Wiedemeyer]] +
- +
-== Simulation of a robots belief state to support perception(MA) == +
- +
-Create a simulation environment that represents the robots current belief state and can be updated frequently. Use off-screen rendering to investigate the affordances these objects possess, in order to support segmentation, detection and tracking of these in the real world.  +
- +
-Requirements:  +
-  * Good programming skills in C/C++ +
-  * strong background in computer vision  +
-  * Gazebo, OpenCV, PCL +
- +
-Contact: [[team:ferenc_balint-benczedi|Ferenc Balint-Benczedi]] +
- +
-== Multi-expert segmentation of cluttered and occluded scenes == +
- +
-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, combining the results of multiple segmentation algorithms in order to come up with more reliable object hypotheses. +
- +
-Requirements:  +
-  * Good programming skills in C/C++ +
-  * strong background in 3D vision  +
-  * basic knowledge of ROS, OpenCV, PCL +
- +
-Contact: [[team:ferenc_balint-benczedi|Ferenc Balint-Benczedi]]+
- 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: